30 results about "Individual item" patented technology

The embodiment of the invention discloses an article loss alarm method and device for a self-service purchase scene, equipment and a medium. A specific embodiment of the method comprises the following steps: in response to a detected article code scanning event, synchronously reading code scanning article identification information and caching a video stream; performing code scanning area cutting processing on the cached video stream to obtain a code scanning area image sequence; performing object overlapping detection on the code scanning area image sequence to obtain an overlapping detection result; article main body positioning is carried out on the code scanning area image sequence to obtain position information of each article main body; performing article image segmentation on the code scanning area image sequence to obtain each article image; performing enhanced feature extraction processing on each article image to generate enhanced feature information of each article; determining the similarity of each article; and according to the similarity of each article, article loss alarm operation is executed through the self-service settlement equipment. According to the embodiment, the article loss prevention accuracy and the processing efficiency can be improved, so that the article loss is reduced.

A palletizing head (1) and a method for palletizing layers of individual items using a palletizing head (1) are disclosed. The palletizing head (1) has a support level (2) for each layer of individual items to be picked up and transferred from a receiving station to a destination. This support level (2) can be removed from under the layer of individual items at the destination. The placement direction (A) of the layer of individual items at the destination is oriented approximately perpendicular to a loading direction (B) at the receiving station. The layer of individual items can be stabilized and positioned within the palletizing head (1) both when picked up at the receiving station and when placed at the destination, in coordination with a positioning movement of the palletizing head (1) between the receiving station and the destination. The process involves picking up individual loads at a receiving station and transferring them onto a support level (2) of the palletizing head (1). The palletizing head (1) then deposits the loads at a destination location by removing the support level (2) from beneath the loads within the palletizing head (1). The discharge direction (A) of the loads at the destination is approximately perpendicular to the loading direction (B) of the loads at the receiving station. The loads are initially positioned within and relative to the palletizing head (1). As the palletizing head (1) moves to the destination, the loads are further advanced on the support level (2) in the loading direction (B). Upon reaching the destination, the support level (2) is removed from beneath the loads to be deposited.

A transaction system selects an individual item from an inventory associated with an online seller in an online e-commerce platform. The transaction system obtains, from a database of the online e-commerce platform, information associated with the individual item. The transaction system processes the information associated with the individual item by one or more large language models (LLMs) and one or more machine learning models to identify a target item that is associated with the individual item and generates a recommendation for presentation to the online seller to expand the inventory associated with the online seller to include the target item.

The application discloses a kind of heterogeneous multi-view enhancement subsequence unit learning session recommendation method, specifically related to the technical field based on session recommendation, solve the interaction between single item in the prior art, lack rich global context information, it is difficult to understand the intention of user from higher dimensional angle technical problem;Its technical scheme is: multiple continuous items are regarded as a subsequence unit, and learning is carried out on the subsequence level;It explores the intention of user within a certain range by subsequence, but not just focus on the direct relationship between items;The number of items in subsequence can be dynamically adjusted, so as to explore the influence of subsequence of different lengths on recommendation performance;The application can apply subsequence unit learning user intention in multiple sessions, better capture the context information in global session.

Exemplary embodiments relate to a machine-learning based approach to detecting individual items in a chaotic moving pick-and-place environment. In such an environment, objects may move relative to a robotic arm. As the objects move through the environment, their locations may change. A relatively more-processing-intensive procedure is employed once on an upstream side of the pick and place station in order to identify or initially segment objects in the environment. Identified items are then tracked using less intensive methods as the object moves through the environment. In order to provide rapid picks, the robot's vision system coordinates with the robot's gripper to image the target when the gripper is out of the image area. A pick location is transmitted back to the gripper within a few hundred milliseconds of the last pick.

Exemplary embodiments relate to a machine-learning based approach to detecting individual items in a chaotic moving pick-and-place environment. In such an environment, objects may move relative to a robotic arm. As the objects move through the environment, their locations may change. A relatively more-processing-intensive procedure is employed once on an upstream side of the pick and place station in order to identify or initially segment objects in the environment. Identified items are then tracked using less intensive methods as the object moves through the environment. Detection is performed once on an upstream side of the pick and place station and then identified items are tracked using less intensive methods as the object moves through the pick-and-place station.

Examples provide a system and method for dynamically filtering candidate item identifiers (IDs) from a pool of item IDs in real-time for automatic labeling of images for use as training data used to train computer vision (CV) models. Images of carts are paired with item receipts. Candidate item IDs are extracted from the receipts. Item recognition inference results generated by CV models are used to pair images of individual items with item IDs identifying the item in each item image. As each candidate item ID is assigned to an item image, the item ID is dynamically filtered. Any candidate item IDs remaining after filtering are assigned to any item images failing to pair with an item ID based on the infer results. The results are presented for review and status update via a user interface device for faster and more accurate auto-labeling of training data for CV models.

Exemplary embodiments relate to a machine-learning based approach to detecting individual items in a chaotic moving pick-and-place environment. In such an environment, objects may move relative to a robotic arm. As the objects move through the environment, their locations may change. A relatively more-processing-intensive procedure is employed once on an upstream side of the pick and place station in order to identify or initially segment objects in the environment. Identified items are then tracked using less intensive methods as the object moves through the environment. In order to provide rapid picks, the robot's vision system coordinates with the robot's gripper to image the target when the gripper is out of the image area. A pick location is transmitted back to the gripper within a few hundred milliseconds of the last pick.

Systems, methods, apparatuses, and computer-readable media are provided for determining individual item-level details associated with a transaction. A plurality of purchase transactions associated with different merchants may be displayed via a user interface. Responsive to a user selection of a first transaction, of the plurality of transactions, a camera may capture an image of at least a portion of a user receipt associated with the first transaction. The image of the user receipt may be analyzed using one or more optical character recognition (OCR) algorithms to convert the image of the user receipt into textual data. One or more character strings associated with line item-level details may be extracted from the textual data associated with the first transaction. Additional information associated with the line item details may be determined and the line item details and the additional information may be displayed via a user interface.

To improve the convenience of a user.SOLUTION: A program makes a computer execute processes of: storing common item information related to a plurality of items that are common between data of a plurality of BOM structures, the data of the plurality of BOM structures storing project information and item information in a hierarchical structure; storing individual item information related to the item constituting the BOM structure in each of the data of the plurality of BOM structures; and managing the individual item information and the common item information corresponding to the item of the individual item information in association with each other.SELECTED DRAWING: Figure 1

Examples provide a system and method for dynamically filtering candidate item identifiers (IDs) from a pool of item IDs in real-time for automatic labeling of images for use as training data used to train computer vision (CV) models. Images of carts are paired with item receipts. Candidate item IDs are extracted from the receipts. Item recognition inference results generated by CV models are used to pair images of individual items with item IDs identifying the item in each item image. As each candidate item ID is assigned to an item image, the item ID is dynamically filtered. Any candidate item IDs remaining after filtering are assigned to any item images failing to pair with an item ID based on the infer results. The results are presented for review and status update via a user interface device for faster and more accurate auto-labeling of training data for CV models.

The invention relates to a vending machine with an enclosed housing and an interior for storing merchandise, wherein the housing comprises at least one housing body and a housing door pivotably connected to the housing body, and with at least one main lock by which the housing door can be securely locked to the housing body, wherein the housing body has at least one rear housing wall, one upper housing side wall, one lower housing side wall, one left housing side wall, and one right housing side wall. The vending machine can be configured, in particular, as a vending machine for the sale of individual items, e.g., packs of cigarettes. The vending machine can be configured, in particular, as a cigarette vending machine.

This invention discloses an electronic prescription review method and system for smart pharmacies, relating to the field of smart pharmacy transaction control technology. It addresses the problem of how to achieve an electronic prescription review method that can adaptively adapt to inventory status, intelligently match prescriptions with physical medications, and accurately manage the risks of substitute dispensing. The method includes: obtaining the set of individual items to be dispensed corresponding to the electronic prescription to be reviewed and the set of actually scanned individual items obtained from actual scanning; generating an inventory constraint identifier for each individual item based on the real-time inventory status of the medication corresponding to each individual item in the set of individual items; determining the optimal mapping relationship between each individual item in the set of individual items and the individual items in the set of actually scanned individual items; determining the compliance risk value of each individual item based on the optimal mapping relationship and the inventory constraint identifier; and executing corresponding control instructions for the current transaction based on the compliance risk values ​​of all individual items in the set of individual items.

1. Name of the product in this design: Packaging Kit (Floral Design for Individual Item Packaging). 2. Purpose of this design: For holding face cream. 3. The key design elements of this product are the combination of shape, pattern, and color. 4. The image or photograph that best illustrates the design points: 3D model of Kit 2. 5. The design for which protection is sought includes color. 6. Other situations requiring explanation: Package description: Packages 1, 3, 5, 7, 9, 11, 13, and 15 are cylindrical inner packages, each containing one of eight different scented face creams; Packages 2, 4, 6, 8, 10, 12, 14, and 16 are square outer packages, which, in sequence, package packages 1, 3, 5, 7, 9, 11, 13, and 15 and the face creams they contain; Package 17 is a square package placed between the various inner and outer packages; This package is sold and used simultaneously.

A method for individually handling articles capable of managing the risk of simultaneous picking of more than one article, comprising the steps of transporting articles on a first collective movement unit (CONV); acquiring an image of a picking zone (PickZ) of the articles using a first image sensor (CAM1); analyzing the image and locating an article (IT); commanding an individual handling unit (MA) equipped with a second image sensor (CAM2) and positioning the second sensor above the located article; acquiring an image (IMG2) of this article; analyzing this image (IMG2) and assessing the risk of multiple picking if the article is picked up by the individual handling unit (MA); then commanding the individual handling unit (MA) to pick up the article and move it to a destination (INS, RET, REJ) chosen from at least one reject bin (REJ) and a second collective movement unit (INS). Figure to be published with the abbreviation: Fig. 2

Systems and methods for a two-part recommendation system wherein a non-personalized item-to-candidate item list is generated without personalization and the items within the corresponding candidate list may be ranked in order to personalize that list to the particular user. In an embodiment, ranking occurs based on a distance function between individual items in the list and the reference item, such as a distance between the items within an embedding space that represents relevant features of items as vectors in latent space. Accordingly, ranking by a candidate ranker can select which items in the candidate list are most pertinent and personalized to the user at a present time. Because ranking can require significantly fewer resources than generating the candidate list, this two-part system can enable real-time recommendations that are personalized to the user.

In accordance with an embodiment, an individual item management system includes an information terminal and an information processing apparatus. The information processing apparatus changes the price included in the product information in accordance with a predetermined rule according to a lapse of time from the reference date and time. The information processing apparatus acquires, upon receiving the identification information in units of the individual item from the information terminal, the product information that includes at least the reference date and time and the price and is stored in association with the identification information in units of the individual item from a storage device and transmits the acquired information to the information terminal.

The invention relates to a transport vehicle (1) having a receiving platform (3) for receiving single-piece goods (S), a single-piece goods displacement device (4) which can be displaced relative to the receiving platform, and transport means which are arranged opposite one another and are mounted so as to be pivotable about a pivot axis (SA) and which can be adjusted between a starting position and a plurality of actuation positions, wherein the roll-out angle (alpha) is 0 DEG in the starting position and is greater than 0 DEG in each case in the actuating position. The invention further relates to a storage system having such a transport vehicle (1), and to a method for handling single goods, which can be implemented with such a transport vehicle (1).

A method of operating a storage and retrieval system including a plurality of storage containers. The method includes, for each storage container, storing a content record including an item type and bounding box for each item previously determined to be placed in the storage container. Upon receiving an indication that an item of a specified item type has been added to the content of the selected storage container: acquiring one or more images of the content; processing the image to detect a single item and generate a current bounding box for each detected item; identifying that one of the current bounding boxes is related to the added item; and updating the content record to include the specified item type of the added item and the identified current bounding box.

A method of operating a storage and retrieval system comprising a plurality of storage containers. The method comprises, for each storage container, storing a contents record comprising, for each item previously determined to be contained in the storage container, an item type and a bounding box. Upon receiving an indication that an item of a specified item type has been added to plurality of contents of a selected storage container: capturing one or more images of the plurality of contents; processing the images to detect individual items and generate a current bounding box for each; identifying one of the current bounding boxes as relating to the added item; and updating the contents record to include, for the added item, the specified item type and the identified current bounding box.

Exemplary embodiments relate to a machine-learning based approach to detecting individual items in a chaotic moving pick-and-place environment. In such an environment, objects may move relative to a robotic arm. As the objects move through the environment, their locations may change. A relatively more-processing-intensive procedure is employed once on an upstream side of the pick and place station in order to identify or initially segment objects in the environment. Identified items are then tracked using less intensive methods as the object moves through the environment. Detection is performed once on an upstream side of the pick and place station and then identified items are tracked using less intensive methods as the object moves through the pick-and-place station.

The present disclosure relates to an order processing method and device, electronic equipment and storage medium, and belongs to the technical field of Internet. The method comprises the following steps: displaying an order that has been created, the order comprising a plurality of items that have been ordered, each item in the order corresponding to a respective order address; in response to an address modification operation on a target item in the plurality of items, obtaining a modified order address, and updating the order address of the target item in the order to the modified order address. The user can perform an address modification operation on any item in the order, thereby updating the order address of the item in the order to the modified order address, meeting the user's demand to modify the order address for individual items after ordering, the operation is simple and convenient, the user's operation cost is reduced, and the human-computer interaction efficiency is improved.

In an example embodiment, a technique is presented that accesses training data that includes information about items, queries for items, and labels for the combinations of items and queries. The labels may correspond to different events, and there may be multiple different labels for the same combination of item and query. A machine learned model is then trained to learn a function for embedding each item to which a label pertains and a function for embedding each query to which a label pertains. Then, for each item in the training data, the items are embedded using the machine learned model, and the item embeddings for the item are concatenated into a single item embedding. At inference time, a similar concatenation is performed for multiple query embeddings. The concatenated embeddings are then used as input to an approximate k-nearest neighbor search function.

The present invention relates to a wooden skewer (2) for holding food in the form of individual items, comprising a holding section (16), a receiving section (20) for holding the food, and an attachment section (24) onto which the food can be attached. The receiving section (20) has at least one predetermined breaking point (36; 38; 40). Furthermore, the present invention relates to the use of such a wooden skewer and a method for manufacturing a wooden skewer for holding food in the form of individual items.

Systems and methods for a two-part recommendation system wherein a non-personalized item-to-candidate item list is generated without personalization and the items within the corresponding candidate list may be ranked in order to personalize that list to the particular user. In an embodiment, ranking occurs based on a distance function between individual items in the list and the reference item, such as a distance between the items within an embedding space that represents relevant features of items as vectors in latent space. Accordingly, ranking by a candidate ranker can select which items in the candidate list are most pertinent and personalized to the user at a present time. Because ranking can require significantly fewer resources than generating the candidate list, this two-part system can enable real-time recommendations that are personalized to the user.

To provide a virtual stock sales method and a system for implementing the same that forms a virtual stock based on a bulk purchase contract of a customer, which allows the customer to take home individual items at a bulk purchase unit price.SOLUTION: The virtual stock sales method comprises: a purchasing system 200 in which a customer C1 transmits an individual take-home signal S3 to a virtual stock via a mobile terminal to purchase products at a bulk purchase unit price; a management system 300 in which a manufacturer A and / or retailer B record the bulk purchase of products and store them in an inventory in response to transmission of a bulk purchase signal S2 from the customer C1, and when the individual take-home signal S3 is received from the customer C1, updates the inventory record of virtual stocks 301, 302 or 303 and transmits a purchased signal S4 for a product G1 to a retailer B's cash register; and a settling system 400 in which the retailer B distinguishes between the products for which the purchased signal S4 has been received and other general products when the customer pays for the products at the cash register, and settles the purchase price of the products for which the purchased signal S4 has been received, at the bulk purchase unit price.SELECTED DRAWING: Figure 6

A method of operating a storage and retrieval system comprising a plurality of storage containers. The method comprises, for each storage container, storing a contents record comprising, for each item previously determined to be contained in the storage container, an item type and a bounding box. Upon receiving an indication that an item of a specified item type has been added to plurality of contents of a selected storage container: capturing one or more images of the plurality of contents; processing the images to detect individual items and generate a current bounding box for each; identifying one of the current bounding boxes as relating to the added item; and updating the contents record to include, for the added item, the specified item type and the identified current bounding box.

A method for layouting a flat warehouse involves dividing the usable storage area and its area into at least one item storage block. Within this item storage block, at least one parallel aisle is established. On either side of the aisle, there are aisles for storing individual items and aisles for storing bulk items, each with varying numbers of storage spaces. This forms an asymmetrical layout of the flat warehouse, including at least one aisle for individual items and one aisle for bulk items. This flat warehouse layout method differs from existing flat warehouse layouts, adapting to complex inventory scenarios involving multiple varieties, multiple batches, and uncertain batch or quantity of items. It effectively improves the warehouse's volumetric efficiency and item retrieval efficiency, reduces the honeycomb effect in storage, lowers storage and management costs, and enhances economic benefits. It constructs a novel flat warehouse layout model and management system, possessing significant inspirational and application value.

A method for generating a source container sequence by a control device of a storage and picking system and a corresponding system for picking individual items of a plurality of customer orders are disclosed, wherein the orders comprise at least one multi-line order and a plurality of single-line orders, each order line of each of the orders corresponding to an item type that is stored in a source container, wherein the system comprises: a warehouse configured to store a plurality of the source containers; a picking station with a number of buffer locations for destination containers; a transport system configured to transport the source containers from the warehouse to the picking station, and vice versa;and a control device configured to generate a source container sequence representing an order in which the source containers are to be provided for the successive processing of the orders at the WzP station; wherein the control device is further configured to bundle the single-line orders into a bundle order, which represents another multi-line order and which replaces the single-line orders during the generation of the source container sequence.