RFID-based precise instrument warehouse goods allocation light-assisted guiding system
By combining RFID technology, AI cargo space recommendation algorithm and light assist guidance system, using AI deep reinforcement learning model to optimize cargo space allocation, the problems of intelligent cargo space recommendation and low-cost unattended in the warehouse management system are solved, and efficient space management and space utilization.
Patent Information
- Application Number
- CN202411323390.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2025-01-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing warehouse management system cannot achieve intelligent cargo space recommendation and auxiliary guidance, resulting in high labor costs. In the absence of manpower, traditional shelves are costly to be guided quickly, making it difficult to achieve low-cost solutions.
Combining RFID technology, AI cargo space recommendation algorithm and light auxiliary guidance system, through the WMS warehousing management system, self-service settlement station, RFID cargo space identification system and light guidance system, AI deep reinforcement learning model is used to optimize cargo space recommendation to achieve intelligent Cargo space allocation and guidance.
It improves the accuracy of cargo space allocation and space utilization rate, reduces labor costs and search time, and realizes unmanned warehouse management.
Smart Images
Figure CN119250697A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of warehouse management of precision instruments, and in particular to an RFID-based light-assisted guidance system for cargo positions in a precision instrument warehouse. Background Art
[0002] In response to the digital management needs of precision instruments, the existing warehouse management system cannot realize intelligent cargo location recommendations and auxiliary guidance, and when there are people on duty, the labor cost is extremely high, which is not conducive to the operation and development of the enterprise. Under the unmanned management requirements, compared with the cargo location guidance of smart containers, the combination of optical guidance and traditional shelves has lower costs and strong flexibility, and can adjust the storage location at any time, and is more adaptable to changes in the form of stored goods.
[0003] The traditional shelf quick guide under unattended conditions, the use of electronic tag system will be costly, and it is inevitable to seek a low-cost solution. The present invention combines RFID technology, AI The combination of the storage location recommendation algorithm and the light-assisted guidance system with traditional shelves can achieve the goal of unmanned warehouse operation and convenient use for users. Summary of the invention
[0004] In order to overcome the above technical problems, the purpose of the present invention is to provide a precision instrument warehouse cargo light auxiliary guidance system based on RFID, including a WMS warehouse management system, a self-service checkout counter, an RFID cargo location identification system, AI Storage location recommendation system and light guidance system.
[0005] Preferably, the method further comprises the following steps:
[0006] S1: The user arrives at the self-service checkout counter and returns / borrows the instrument;
[0007] S2: In the instrument return process, the self-service checkout counter identifies the instrument ID and the WMS warehouse management system background is started AI The cargo location recommendation algorithm is AI The cargo location recommendation algorithm recommends cargo locations to users. AI The cargo location recommendation algorithm can determine the specific cargo location that needs to be recommended based on whether it is a measuring instrument and whether the measurement is expired;
[0008] S3: In the process of borrowing instruments, check the instrument to be borrowed at the self-service checkout counter. The RFID cargo location identification system will identify the location of the instrument, and the query result will display the cargo location;
[0009] S4: After completing step S2 or S3, click the light guidance system to achieve efficient cargo location guidance;
[0010] S5: After the instrument is returned or loaned out, the RFID cargo location identification system will make an identification confirmation to determine whether the instrument has been loaned out or returned, and can identify the specific planned cargo location.
[0011] Preferably, it also includes determining instrument characteristics, collecting data, establishing an AI cargo location recommendation algorithm (based on an AI deep reinforcement learning model), and continuous monitoring and adjustment.
[0012] Preferably, the determining of instrument characteristics includes instrument attributes and warehouse layout.
[0013] Preferably, the instrument attributes include weight, size, type, whether it is a measuring instrument, measuring cycle, etc., and the warehouse layout includes shelf number, area, distance, etc.
[0014] Preferably, the data collection includes collecting historical in-and-out warehouse data and current cargo location information.
[0015] Preferably, the historical sales data records the frequency of in-and-out storage and inventory of instruments, and the current cargo location information records the current cargo location number and position of each instrument.
[0016] Preferably, the AI cargo location recommendation algorithm (based on the AI deep reinforcement learning model) is established, based on the collected data and analysis, with the goal of training the AI deep reinforcement learning model.
[0017] Preferably, for instruments with special properties (e.g., measuring instruments), they are placed on shelves suitable for their properties, with those that have expired placed in specific areas and those that have not expired placed in normal areas;
[0018] Frequently taken items can be placed in locations that are easy to find and take;
[0019] According to the reward function design of AI deep reinforcement learning model, each time AI When the storage location recommendation algorithm is executed, a score is assigned to each storage location;
[0020] For the goods that need to be placed, the storage location with the highest score is selected as the recommended storage location based on the storage location score;
[0021] If multiple storage locations have the same highest score, multiple recommended storage locations may be displayed for the user to choose from.
[0022] Preferably, the continuous monitoring and adjustment is to regularly collect sales data, update AI The cargo location recommendation algorithm (based on the AI deep reinforcement learning model) adjusts and optimizes the AI deep reinforcement learning model parameters according to the actual results.
[0023] Beneficial effects of the present invention:
[0024] The present invention is based on the characteristics of the instrument and AI The combination of the cargo location recommendation algorithm can achieve a better cargo location allocation. At the same time, the AI cargo location recommendation algorithm (based on the AI deep reinforcement learning model) can be continuously upgraded and iterated according to the historical instrument in and out of the warehouse and inventory data, which can allocate cargo locations more accurately and reasonably, and improve the space utilization rate and cargo management efficiency of the warehouse;
[0025] Based on the intelligent management of warehouse instruments, quick search and storage location recommendations can be made, and users can be guided to find the required storage location through light, reducing the time and labor costs of searching for instruments. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The present invention will be further described below in conjunction with the accompanying drawings.
[0027] Picture 1 is a flow chart of the present invention;
[0028] Picture 2 is a layout diagram of the present invention;
[0029] Picture 3 This is a structural diagram of the AI deep reinforcement learning model of the present invention;
[0030] Picture 4 This is a flow chart of the AI cargo location recommendation algorithm of the present invention. DETAILED DESCRIPTION
[0031] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0032] See also Picture 1-4 As shown, a light-assisted guidance system for precision instrument warehouse cargo positions based on RFID includes a WMS warehouse management system, a self-service checkout counter, an RFID cargo position identification system, AI The cargo position recommendation system and the light guidance system also include the following steps:
[0033] S1: The user arrives at the self-service checkout counter and returns / borrows the instrument;
[0034] S2: In the instrument return process, the self-service checkout counter identifies the instrument ID and the WMS warehouse management system background is started AI The cargo location recommendation algorithm is AI The cargo location recommendation algorithm recommends cargo locations to users. AIThe cargo location recommendation algorithm can determine the specific cargo location that needs to be recommended based on whether it is a measuring instrument and whether the measurement is expired;
[0035] S3: In the process of borrowing instruments, check the instrument to be borrowed at the self-service checkout counter. The RFID cargo location identification system will identify the location of the instrument, and the query result will display the cargo location;
[0036] S4: After completing step S2 or S3, click the light guidance system to achieve efficient cargo location guidance;
[0037] S5: After the instrument is returned or loaned out, the RFID cargo location identification system will make an identification confirmation to determine whether the instrument has been loaned out or returned, and can identify the specific planned cargo location.
[0038] 1. Determine instrument characteristics:
[0039] Instrument attributes: for example, weight, size, type, whether it is a measuring instrument, measuring cycle, etc.
[0040] Warehouse layout: e.g. shelf numbers, zones, distances, etc.
[0041] 2. Collect data:
[0042] The historical entry and exit database records the sales frequency and sales volume of the goods.
[0043] Current storage location information: Record the current storage location number and location of each instrument.
[0044] 3. Establish an AI cargo location recommendation algorithm (based on AI deep reinforcement learning model):
[0045] Based on the collected data and analysis, determine AI Parameters of the storage location recommendation algorithm, such as:
[0046] Reward function design: R = w1*space utilization + w2*pick-and-place efficiency + w3*measurement compliance - w4*mobility cost, where w1, w2, w3, and w4 are weight coefficients, which are adjusted according to specific needs. Each result will give each cargo location a matching score. The higher the score, the more worthy of recommendation.
[0047] According to the results of the cargo position rating, AI The storage location recommendation algorithm assigns a score to each storage location at a time.
[0048] Determine the best storage location:
[0049] For the goods that need to be placed, AI The storage location recommendation algorithm selects the storage location with the highest score as the recommended storage location.
[0050] If multiple storage locations have the same highest score, multiple recommended storage locations can be displayed for users to choose from. 4. Continuous monitoring and adjustment:
[0051] Regularly collect sales data and update the AI deep reinforcement learning model of the AI shelf recommendation algorithm.
[0052] Adjust and optimize the parameters of the AI deep reinforcement learning model of the AI cargo location recommendation algorithm based on actual results.
[0053] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0054] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.
Claims
1. A light-assisted guidance system for precision instrument warehouse cargo space based on RFID, characterized in that: It includes WMS warehouse management system (including AI cargo location recommendation algorithm), self-service checkout counter, RFID cargo location instrument identification system, cargo location recommendation system and light guidance system.
2. According to claim 1, a RFID-based precision instrument warehouse cargo light auxiliary guidance system is characterized in that: The following steps are also included: S1: The user arrives at the self-service checkout counter and returns / borrows the instrument; S2: In the instrument return process, the self-service checkout counter identifies the instrument ID, and the WMS warehouse management system background starts the AI cargo location recommendation algorithm. The AI cargo location recommendation algorithm recommends the cargo location to the user. AI The cargo location recommendation algorithm can determine the specific cargo location that needs to be recommended based on multiple factors such as instrument measurement cycle requirements, size specifications, usage frequency, and remaining cargo space; S3: In the process of borrowing instruments, check the instruments to be borrowed at the self-service checkout counter. The RFID instrument identification system will identify the location of the instruments, and the query result will display the location of the instruments. S4: After completing step S2 or S3, click on the light guidance system, which will cause the light guidance system hardware to project laser onto the target cargo location, so that the user can quickly identify the target cargo location and achieve efficient cargo location guidance; S5: After the instrument is returned or loaned out, the RFID cargo location instrument identification system will make an identification confirmation to determine whether the instrument has been loaned out or returned, and can identify the specific cargo location where the instrument is returned.
3. According to claim 2, a RFID-based precision instrument warehouse cargo light auxiliary guidance system is characterized in that: It also includes determining instrument characteristics, collecting data, establishing an AI cargo location recommendation algorithm (based on an AI deep reinforcement learning model), and continuous monitoring and adjustment.
4. According to claim 3, the RFID-based precision instrument warehouse cargo light auxiliary guidance system is characterized in that: The determination of the instrument characteristics includes instrument attributes, warehouse layout and cargo space size.
5. According to claim 4, a RFID-based precision instrument warehouse cargo light auxiliary guidance system is characterized in that: The instrument attributes include the weight, size, type, whether it is a measuring instrument, the measuring cycle, etc. The warehouse layout includes the shelf number, area, distance, etc. The cargo space size refers to the original size space and remaining space of the cargo space, etc.
6. According to claim 3, a RFID-based precision instrument warehouse cargo light auxiliary guidance system is characterized in that: The data collection includes collecting historical in-and-out warehouse data, current cargo location information and instrument attribute information.
7. The RFID-based light-assisted guidance system for precision instrument warehouse cargo space according to claim 6 is characterized in that: The historical in-and-out warehouse data records the usage frequency and inventory quantity of precision instruments, and the current storage location information records the current inventory storage location number and position of each precision instrument.
8. According to claim 3, the RFID-based precision instrument warehouse cargo light auxiliary guidance system is characterized in that: The AI cargo location recommendation algorithm (based on the AI deep reinforcement learning model) is established, and the AI deep reinforcement learning model is trained according to the collected data and analysis to more accurately recommend cargo locations.
9. The RFID-based light-assisted guidance system for precision instrument warehouse cargo space according to claim 8 is characterized in that: For commodities with special attributes (e.g., measuring instruments), they should be placed on shelves suitable for their attributes, with those that have expired placed in specific areas and those that have not expired placed in normal areas; Frequently taken items can be placed in locations that are easy to find and take; According to the reward function design of AI deep reinforcement learning model: R = w1*space utilization + w2*pick-and-place efficiency + w3*measurement compliance - w4*mobility cost, where w1, w2, w3, and w4 are weight coefficients, which are adjusted according to specific needs. When the AI cargo location recommendation algorithm is executed, each cargo location will have a score, and the cargo location score is used to make cargo location recommendations; If multiple storage locations have the same highest score, multiple recommended storage locations may be displayed for the user to choose from.
10. The RFID-based light-assisted guidance system for precision instrument warehouse cargo space according to claim 3 is characterized in that: The continuous monitoring and adjustment mentioned above is to regularly collect inbound and outbound data, update the AI cargo location recommendation algorithm, and adjust and optimize the algorithm parameters according to actual results.