US2022092568A1PendingUtilityA1

Data-driven partial rescan precision booster

Assignee: NCR CORPPriority: Nov 26, 2019Filed: Dec 3, 2021Published: Mar 24, 2022
Est. expiryNov 26, 2039(~13.3 yrs left)· nominal 20-yr term from priority
G06Q 20/4014G07G 1/0036G06Q 20/4016G07G 3/003G06Q 20/18G06Q 20/208G06Q 20/202G06N 20/00
56
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A transaction is identified for a partial rescan security check based at least in part on basket items of the transaction. A total number of rescan items from the basket items is identified for rescan; the total number of rescan items selected for rescan is less than a total number of the basket items in the transaction. Based on the basket items and transaction features for the transaction, item categories or item departments are identified from which the total number of rescan items are to be selected from the basket items for the rescan security check. The total number of rescan items and the item categories for selection are provided to an attendant terminal for the rescan security check. The rescan security check is processed to determine whether the transaction was associated with theft or not associated with theft.

Claims

exact text as granted — not AI-modified
1 . A method, comprising:
 obtaining a transaction identifier for a transaction that was designated for a partial rescan;   identifying a number from a total number of transaction items that are to be processed with the partial rescan using the transaction identifier;   determining item categories for the number from which the transaction items are to be selected from with the partial rescan; and   providing the number and the item categories to an attendant terminal to process the partial rescan.   
     
     
         2 . The method of  claim 1 , wherein obtaining further includes receiving a theft score for the transaction identifier from a first trained machine-learning algorithm. 
     
     
         3 . The method of  claim 2 , wherein identifying further includes selecting the number based on comparison of the theft score to one or more threshold scores. 
     
     
         4 . The method of  claim 3 , wherein determining further includes providing item identifiers and transaction features for the transaction items and the transaction as input to a second trained machine-learning algorithm. 
     
     
         5 . The method of  claim 4 , wherein providing further includes receiving as output a ranked and scored listing of potential item categories. 
     
     
         6 . The method of  claim 5 , wherein receiving further includes obtaining the item categories based on top ranked ones of the potential item categories. 
     
     
         7 . The method of  claim 6 , wherein obtaining the item categories further includes determining a percentage of the number to select for the partial rescan for each item category based on ranked scores for the potential item categories. 
     
     
         8 . The method of  claim 7 , wherein providing further includes providing the percentage for each item category to select from the number to the attendant terminal. 
     
     
         9 . The method of  claim 1 , wherein determining further includes determining a percentage of the number for each item category based on a probability of theft assigned to each item category. 
     
     
         10 . The method of  claim 1 , wherein providing further includes sending the number and the item categories as instructions for processing the partial rescan on the attendant terminal. 
     
     
         11 . The method of  claim 1  further comprising, determining based on results of processing the partial rescan against the number of the transaction items selected from the item categories whether a full rescan of all transaction items is required or whether the transaction was deemed to not be associated with any theft. 
     
     
         12 . A method, comprising:
 receiving a transaction identifier for a transaction flagged for a rescan and an audit check;   obtaining transaction features for the transaction and items of the transaction;   determining select item categories of select items to perform the rescan on for the audit check based on the transaction features;   determining an item rescan total from a total number of the items based on the transaction features; and   providing the select item categories and the item rescan total to an attendant to perform the rescan and the audit check against the items of the transaction.   
     
     
         13 . The method of  claim 12 , wherein receiving further includes receiving a theft score for the transaction that triggered the receiving of the transaction identifier for the transaction. 
     
     
         14 . The method of  claim 13 , wherein determining the select item categories further includes determining the select item categories based on the transaction features and the theft score. 
     
     
         15 . The method of  claim 14 , wherein determining the item rescan total further includes determining the item rescan total based on the total number of items, the transaction features, and the theft score. 
     
     
         16 . The method of  claim 12 , wherein providing further includes sending the transaction identifier, the select item categories, and the item rescan total to an attendant device operated by the attendant to perform the rescan and the audit check. 
     
     
         17 . The method of  claim 12 , wherein determining the select item categories further includes determining the select item categories based on a basket or a collection of the items that comprise the transaction and the transaction features. 
     
     
         18 . The method of  claim 17 , wherein determining the item rescan total further includes determining the item rescan total based on the basket or the collection of the items that comprise the transaction and the transaction features. 
     
     
         19 . A system, comprising:
 a server comprising a processor and a non-transitory computer-readable storage medium;   the non-transitory computer-readable storage medium comprises executable instructions; and   the executable instructions executed by the processor from the non-transitory computer-readable storage medium causing the processor to perform operations, comprising:
 receiving a transaction identifier for a transaction that was designated for a partial rescan of items in the transaction; 
 obtaining a basket or a collection of the items for the transaction; 
 obtaining transaction features for the transaction, the basket or the collection, and the items; 
 determining a rescan total from a total number of the items in the transaction for the partial rescan based on the basket of the collection and based on the transaction features; and 
 providing the rescan total to an attendant device operated by an attendant to perform the partial rescan against the items of the transaction as an audit check or a security check. 
   
     
     
         20 . The system of  claim 19 , wherein the attendant device is a transaction terminal, a tablet computer, a laptop computer, a desktop computer, a phone, or a wearable processing device.

Join the waitlist — get patent alerts

Track US2022092568A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.