# US 2021/0241337 A1 · Machine learning based procurement as a service

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

- Number: US 2021/0241337 A1
- Document ID: US20210241337A1
- Status: Published application
- Kind: A1
- Application number: 16/777,229
- Filed: 2020-01-30
- Published: 2021-08-05
- Earliest claimed: 2020-01-30
- Assignees: Dell Products L. P.
- Applicants: Dell Products L. P.
- Inventors: Sathish Kumar Bikumala; Deepak NagarajeGowda; Bijan Kumar Mohanty
- Web page: https://patentgrep.com/patent/US20210241337A1

## CPC

- G06Q 30/0621: {by configuring or customising goods or services}
- G06F 40/30: Semantic analysis
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- G06Q 10/0837: Return transactions
- G06Q 10/20: Administration of product repair or maintenance
- G06Q 30/0282: Rating or review of business operators or products
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G06Q 30/0641: {utilising user interfaces specially adapted for shopping}
- Y02P 90/84: Greenhouse gas [GHG] management systems
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

As an example, a software application executing on a computing device of a channel partner may access an application programming interface (API) hosted by a server to access a manufacturer's data. The computing device may provide criteria to the API to identify a subset of a set of configurations. The computing device may be used to select a particular configuration in the subset and to perform one or more modifications to the particular configuration to create a modified configuration. The computing device may use the API to access a verification module to verify whether the modified configuration can be built. If the modified configuration is unbuildable, the computing device may be used to make additional modifications to the particular configuration until the modified configuration is verified as buildable. The channel partner may place an order for a particular quantity of the modified configuration.

## Claims

### Claim 1

A computer-implemented method comprising:
accessing, by a computing device, an applications programming interface (API) hosted by a server;
providing, by the computing device to the API, one or more criteria to filter a set of configurations;
receiving, by the computing device from the API, a subset of the set of configurations, the subset determined based at least in part on the one or more criteria;
receiving a selection, by the computing device, of a particular configuration of the subset;
receiving, by the computing device, a modification to the particular configuration;
creating, by the computing device, a modified configuration based on the particular configuration;
providing, by the computing device to the API, the modified configuration;
requesting, by the computing device using the API, verification that the modified configuration is buildable; and
placing, by the computing device to the API, an order to manufacture a particular quantity of the modified configuration.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, wherein:
the particular configuration is associated with one of a desktop computing device, a laptop computing device, or a tablet computing device, a 2-in-1 computing device.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining service requests associated with the particular configuration, wherein the modification to the particular configuration is based at least in part on the service requests.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining return data associated with the particular configuration, wherein the modification to the particular configuration is based at least in part on the return data.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining sentiment data associated with the particular configuration, wherein the sentiment data is determined based on comments posted on one or more review sites, and wherein the modification to the particular configuration is based at least in part on the sentiment data.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more criteria comprises at least one of:
a particular time period comprising a start date and an end date;
a price range comprising a lowest price and a highest price;
a particular location comprising a postal code, a county, a city, a state, or a country;
a profit margin; or
a number of units sold.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the modified configuration specifies that:
a first particular part be excluded from the particular configuration based at least in part on one or more issues associated with the first particular part, the one or more issues determined based on analyzing service request data and product returns data; and
a second particular part be included in the particular configuration based at least in part on one or more features provided by the second particular part.

### Claim 8

A computing device comprising:
one or more processors; and
one or more non-transitory computer readable media to store instructions executable by the one or more processors to perform operations comprising:
accessing an applications programming interface (API) hosted by a server;
providing, using the API, a set of criteria to filter a set of configurations;
receiving, from the API, a subset of the set of configurations, the subset determined based at least in part on the set of criteria;
receiving a selection of a particular configuration of the subset;
receiving a modification to the particular configuration;
creating a modified configuration based on the modification;
requesting, using the API, verification that the modified configuration is buildable;
determining, using the API, that the modified configuration is buildable; and
placing, using the API, an order to manufacture a particular quantity of the modified configuration.

### Claim 9 (depends on 8)

The one or more non-transitory computer readable media of claim 8, further comprising:
receiving, from the API, a second subset of the set of configurations determined based at least in part on a second set of criteria;
receiving a second selection of a second particular configuration of the subset;
receiving a second modification to the second particular configuration;
creating a second modified configuration based on the second modification;
requesting, using the API, verification of the second modified configuration;
determining, from the API, that the modified configuration is unbuildable;
receiving an additional modification to the second particular configuration;
creating an additional modified configuration based on the additional modification;
requesting, using the API, verification of the additional modified configuration; and
determining, from the API, that the additional modified configuration is buildable.

### Claim 10 (depends on 8)

The one or more non-transitory computer readable media of claim 8, further comprising:
determining service requests associated with the particular configuration;
determining return data associated with the particular configuration; and
determining sentiment data associated with the particular configuration, wherein the sentiment data is determined based on comments posted on one or more review sites; and
wherein the modification to the particular configuration is based at least in part on one or more of:
the service requests;
the return data; or
the sentiment data.

### Claim 11 (depends on 8)

The one or more non-transitory computer readable media of claim 8, wherein the set of criteria comprises at least one of:
a particular time period comprising a start date and an end date;
a price range comprising a lowest price and a highest price;
a particular location comprising a postal code, a county, a city, a state, or a country;
a profit margin; or
a number of units sold.

### Claim 12 (depends on 8)

The one or more non-transitory computer readable media of claim 8, wherein:
the modified configuration specifies that a particular part be excluded from the particular configuration based at least in part on one or more issues associated with the particular part, the one or more issues determined based on analyzing service request data and product returns data.

### Claim 13 (depends on 8)

The one or more non-transitory computer readable media of claim 8, wherein:
the modified configuration specifies that a particular part be included in the particular configuration based at least in part on one or more features provided by the particular part.

### Claim 14

A server comprising:
one or more processors; and
one or more non-transitory computer readable media to store instructions executable by the one or more processors to perform operations comprising:
receiving from a computing device associated with a channel partner, via an applications programming interface (API), one or more criteria to filter a set of configurations;
determining a subset of the set of configurations, the subset determined based at least in part on the one or more criteria;
receiving, via the API, a selection of a particular configuration of the subset;
receiving, via the API, a modification to the particular configuration to create a modified configuration;
determining, using a configuration verification module, that the modified configuration is buildable; and
receiving, via the API, an order to manufacture a particular quantity of the modified configuration.

### Claim 15 (depends on 14)

The server of claim 14, further comprising:
performing, using a long short term memory (LSTM) machine learning module, an analysis of the set of configurations to identify a set of features.

### Claim 16 (depends on 15)

The server of claim 15, further comprising:
clustering, using density-based spatial clustering of applications with noise (DBSCAN), the set of features to create a plurality of configuration clusters based at least in part on:
a number of sales of individual configurations of the set of configurations;
product reviews of the individual configurations;
service request data associated with the individual configurations; and
product return data associated with the individual configurations.

### Claim 17 (depends on 16)

The server of claim 16, further comprising:
performing, using a K-nearest neighbors algorithm, an analysis of the plurality of configuration clusters; and
determining, based on the analysis, a predetermined number of bestselling configurations.

### Claim 18 (depends on 17)

The server of claim 17, wherein:
the subset includes at least one bestselling configuration from the predetermined number of bestselling configurations.

### Claim 19 (depends on 14)

The server of claim 14, wherein:
the modified configuration specifies that a particular part be excluded from the particular configuration based at least in part on one or more issues associated with the particular part, the one or more issues determined based on analyzing service request data and product returns data.

### Claim 20 (depends on 14)

The server of claim 14, wherein:
the modified configuration specifies that a particular part be included in the particular configuration based at least in part on one or more features provided by the particular part.
