# US 12,182,818 B2 · Order processing based on predicted delay time to increase likelihood of order fulfillment within an authorization period

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,182,818 B2
- Document ID: US12182818B2
- Status: Granted
- Kind: B2
- Application number: 18/111,180
- Filed: 2023-02-17
- Published: 2024-08-22
- Granted: 2024-12-31
- Earliest claimed: 2023-02-17
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: Shibi Panikkar; Ravuru Vijaya Sankar
- Web page: https://patentgrep.com/patent/US12182818B2

## CPC

- G06Q 10/0875: Itemisation or classification of parts, supplies or services, e.g. bill of materials
- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06Q 10/0635: Risk analysis of enterprise or organisation activities
- G06Q 10/083: Shipping
- G06Q 20/389: {Keeping log of transactions for guaranteeing non-repudiation of a transaction}
- G06Q 30/06: Buying, selling or leasing transactions
- G06Q 50/04: Manufacturing
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An apparatus comprises a processing device configured to identify a given order for products to be manufactured by an entity, the given order being associated with an authorization period specifying a time in which the given order is to be fulfilled by the entity to initiate capture of blocked funds of a customer that placed the given order. The processing device is also configured, responsive to determining that the given order has at least a threshold likelihood of being delayed utilizing a first machine learning model, to predict a delay time of the given order utilizing a second machine learning model. The processing device is further configured, responsive to determining that the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period, to initiate action to reduce the predicted delay time or extend the authorization period.

## Claims

### Claim 1

An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured:
to identify a given order for one or more products to be manufactured by an entity, the given order being associated with an authorization period specifying a time in which the given order is to be fulfilled by the entity to initiate capture of blocked funds of a customer that placed the given order;
to determine deviations in at least one of testing and repair time for different ones of the one or more products;
to train a first machine learning model utilizing the determined deviations in the at least one of the testing and the repair time for the different ones of the one or more products;
to determine whether the given order has at least a threshold likelihood of being delayed utilizing the first machine learning model;
responsive to the given order having at least the threshold likelihood of being delayed, to predict a delay time of the given order utilizing a second machine learning model;
to determine whether the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period; and
responsive to determining that the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period, to initiate one or more actions to at least one of reduce the predicted delay time of the given order and extend the authorization period associated with the given order;
wherein initiating the one or more actions comprises attempting at least one action to reduce the predicted delay time prior to attempting at least one action to extend the authorization period associated with the given order.

### Claim 2 (depends on 1)

The apparatus of claim 1 wherein the one or more products comprises one or more computing devices.

### Claim 3 (depends on 1)

The apparatus of claim 1 wherein the first machine learning model is further trained utilizing delayed order history information characterizing one or more of order type, shipment location, country of manufacturing factory, and delay codes.

### Claim 4 (depends on 1)

The apparatus of claim 1 wherein determining whether the given order has at least the threshold likelihood of being delayed is based at least in part on determining delay attributed to issues relating to at least one of manufacturing order planning and manufacturing.

### Claim 5 (depends on 1)

The apparatus of claim 1 wherein determining whether the given order has at least the threshold likelihood of being delayed is based at least in part on determining delay attributed to testing of the one or more products manufactured by the entity.

### Claim 6 (depends on 5)

The apparatus of claim 5 wherein the delay attributed to the testing of the one or more products manufactured by the entity comprises delays associated with electro-mechanical repair of one or more issues identified during the testing of the one or more products manufactured by the entity.

### Claim 7 (depends on 6)

The apparatus of claim 6 wherein the delays associated with the electro-mechanical repair of the one or more issues is based at least in part on at least one of electro-mechanical repair failure type, electro-mechanical repair resource availability, skill set of users performing the electro-mechanical repair, and a number of products in an electro-mechanical repair queue.

### Claim 8 (depends on 1)

The apparatus of claim 1 wherein the second machine learning model utilizes (i) a support vector machine algorithm for classifying of the given order based at least in part on product, electro-mechanical repair task, one or more error codes, and time taken factors and (ii) conditional probability analysis for determining electro-mechanical repair time deviation based at least in part on a number of electro-mechanical repair tasks in an electro-mechanical repair queue.

### Claim 9 (depends on 1)

The apparatus of claim 1 wherein the at least one action to reduce the predicted delay time comprises swapping one or more products of the given order with one or more similar products in one or more additional orders having associated authorization periods which end later than the authorization period of the given order.

### Claim 10 (depends on 1)

The apparatus of claim 1 wherein the at least one action to reduce the predicted delay time comprises swapping, in an electro-mechanical repair queue, an ordering of one or more electro-mechanical repair tasks of the given order with one or more electro-mechanical repair tasks of one or more additional orders having associated authorization periods which end later than the authorization period of the given order.

### Claim 11 (depends on 1)

The apparatus of claim 1 wherein the at least one action to extend the authorization period associated with the given order comprises requesting consent from the customer of the given order to extend the authorization period of the given order.

### Claim 12 (depends on 1)

The apparatus of claim 1 wherein, responsive to failure of the one or more actions to at least one of reduce the predicted delay time and extend the authorization period associated with the given order, the at least one processing device is configured to utilize a third machine learning model for classifying a riskiness of the customer based at least in part on the customer's order history with the entity.

### Claim 13 (depends on 12)

The apparatus of claim 12, wherein:
responsive to the classified riskiness of the customer being a first risk level, canceling the given order; and
responsive to the classified riskiness of the customer being a second risk level, fulfilling the given order outside its associated authorization period.

### Claim 14

A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:
to identify a given order for one or more products to be manufactured by an entity, the given order being associated with an authorization period specifying a time in which the given order is to be fulfilled by the entity to initiate capture of blocked funds of a customer that placed the given order;
to determine deviations in at least one of testing and repair time for different ones of the one or more products;
to train a first machine learning model utilizing the determined deviations in the at least one of the testing and the repair time for the different ones of the one or more products;
to determine whether the given order has at least a threshold likelihood of being delayed utilizing the first machine learning model;
responsive to the given order having at least the threshold likelihood of being delayed, to predict a delay time of the given order utilizing a second machine learning model;
to determine whether the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period; and
responsive to determining that the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period, to initiate one or more actions to at least one of reduce the predicted delay time of the given order and extend the authorization period associated with the given order;
wherein initiating the one or more actions comprises attempting at least one action to reduce the predicted delay time prior to attempting at least one action to extend the authorization period associated with the given order.

### Claim 15 (depends on 14)

The computer program product of claim 14 wherein the at least one action to reduce the predicted delay time comprises at least one of:
swapping one or more products of the given order with one or more similar products in one or more additional orders having associated authorization periods which end later than the authorization period of the given order; and
swapping, in an electro-mechanical repair queue, an ordering of one or more electro-mechanical repair tasks of the given order with one or more electro-mechanical repair tasks of one or more additional orders having associated authorization periods which end later than the authorization period of the given order.

### Claim 16 (depends on 14)

The computer program product of claim 14 wherein the program code when executed by the at least one processing device further causes the at least one processing device, responsive to failure of the one or more actions to at least one of reduce the predicted delay time and extend the authorization period associated with the given order, to utilize a third machine learning model for classifying a riskiness of the customer based at least in part on the customer's order history with the entity.

### Claim 17

A method comprising:
identifying a given order for one or more products to be manufactured by an entity, the given order being associated with an authorization period specifying a time in which the given order is to be fulfilled by the entity to initiate capture of blocked funds of a customer that placed the given order;
determining deviations in at least one of testing and repair time for different ones of the one or more products;
training a first machine learning model utilizing the determined deviations in the at least one of the testing and the repair time for the different ones of the one or more products;
determining whether the given order has at least a threshold likelihood of being delayed utilizing the first machine learning model;
responsive to the given order having at least the threshold likelihood of being delayed, predicting a delay time of the given order utilizing a second machine learning model;
determining whether the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period; and
responsive to determining that the predicted delay time of the given order will result in the given order being fulfilled outside of its associated authorization period, initiating one or more actions to at least one of reduce the predicted delay time of the given order and extend the authorization period associated with the given order;
wherein initiating the one or more actions comprises attempting at least one action to reduce the predicted delay time prior to attempting at least one action to extend the authorization period associated with the given order; and
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

### Claim 18 (depends on 17)

The method of claim 17 wherein the at least one action to reduce the predicted delay time comprises at least one of:
swapping one or more products of the given order with one or more similar products in one or more additional orders having associated authorization periods which end later than the authorization period of the given order; and
swapping, in an electro-mechanical repair queue, an ordering of one or more electro-mechanical repair tasks of the given order with one or more electro-mechanical repair tasks of one or more additional orders having associated authorization periods which end later than the authorization period of the given order.

### Claim 19 (depends on 17)

The method of claim 17 further comprising, responsive to failure of the one or more actions to at least one of reduce the predicted delay time and extend the authorization period associated with the given order, utilizing a third machine learning model for classifying a riskiness of the customer based at least in part on the customer's order history with the entity.

### Claim 20 (depends on 19)

The method of claim 19, wherein:
responsive to the classified riskiness of the customer being a first risk level, canceling the given order; and
responsive to the classified riskiness of the customer being a second risk level, fulfilling the given order outside its associated authorization period.