Product classification in procurement systems

• US 8,768,930 B2
• Filed: 04/26/2010
• Issued: 07/01/2014
• Est. Priority Date: 10/10/2009
• Status: Active Grant

• Current Assignee: Oracle International Corporation (Oracle Corporation)
• Original Assignee: Oracle International Corporation (Oracle Corporation)
• Inventors: Yeleshwarapu, Chandra, Rangarajan, Keshava, Agarwal, Sudeep, Bismpigiannis, Athanasios, Srinivasan, Nagaraj, Pathak, Ashish, Ram, Munagala Kodanda
• Primary Examiner(s): Hoang, Son T
• Application Number:
  US12/767,286
• Publication Number:
  US 20110087626A1
• Time in Patent Office: 1,527 Days
• Field of Search: None
• US Class Current: 707/740
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/0641 Shopping interfaces

Abstract

Various embodiments provide solutions to assist in the classification of products in a procurement system. The tools provided by various embodiments include, without limitation, methods, systems, and/or software products. Merely by way of example, a method might comprise one or more procedures, any or all of which are executed by a computer system. Correspondingly, an embodiment might provide a computer system configured with instructions to perform one or more procedures in accordance with methods provided by various other embodiments. Similarly, a computer program might comprise a set of instructions that are executable by a computer system (and/or a processor therein) to perform such operations. In many cases, such software programs are encoded on physical and/or tangible computer readable media (such as, to name but a few examples, optical media, magnetic media, and/or the like).

Claims

1. In a procurement system executing a procurement enterprise application, a method of assisting a user in classifying a product, the method comprising:

providing, from the procurement system, a user interface for receiving input from the user during a procurement process executed by the procurement enterprise application;

obtaining product information at the procurement system about the product the user desires to procure as part of the procurement process;

generating, by the procurement system, one or more keywords based on the obtained product information, wherein

the one or more generated keywords relating to possible classifications for the product,

the possible classifications identifying one or more levels of a hierarchical classification taxonomy,

the hierarchical classification taxonomy comprising multiple levels and representing a plurality of products available for procurement through the procurement process;

clustering, by the procurement system based on a clustering model, similar keywords of the one or more generated keywords together to generate two or more sets of clustered keywords;

enriching, by the procurement system, the product information with the clustered keywords;

evaluating, by the procurement system, the enriched product information to determine a confidence level associated with each of the clustered keywords indicating a level of certainty that an inline-classification engine of the procurement system is able to correctly predict the product'"'"'s categorization;

comparing, by the procurement system, the confidence level of each of the clustered keyword with a specified threshold;

sending, from the procurement system, at least one of the clustered keywords and the enriched product information to a classification engine, based on the comparison of the confidence level for each clustered keyword with a value meeting or exceeding the specified threshold;

generating, by the procurement system, one or more predicted classifications at the classification engine;

rating, by the procurement system, each of the one or more of the predicted classifications so that any of the predicted classifications with a largest rate value has a better predicted fit with the product and the product information;

ranking, by the procurement system, the one or more predicted classifications based on corresponding predicted fits;

presenting, by the procurement system, the one or more ranked predicted classifications to the user, with the user interface while the user is attempting to procure the product during the procurement process;

receiving, by the procurement system at the user interface, a selection of one of the presented, ranked predicted classifications during the procurement process; and

classifying the product, by the procurement system, based at least in part on the selection and during the procurement process.

2. The method of claim 1, wherein the obtaining the product information comprises:

obtaining the product information from the user, via the user interface.

3. The method of claim 1, wherein the obtaining the product information comprises:

obtaining the product information from an online catalog.

4. The method of claim 1, wherein the obtaining the product information comprises:

obtaining the product information from a punchout to a website operated by a supplier of the product.

5. The method of claim 1, the obtaining the product information comprises:

obtaining data pertaining to the product information from a plurality of data sources.

6. The method of claim 5, further comprising:

normalizing the data pertaining to the product information from the plurality of data sources.

7. The method of claim 5, wherein the generating the one or more keywords comprise:

generating a result set from the data pertaining to the product information from the plurality of data sources, wherein the result set comprises the product information about the product the user desires to procure.

8. The method of claim 1, further comprising:

presenting the one or more generated keywords to the user, via the user interface; and

receiving, via the user interface, a selection of one or more keywords;

wherein the sending the at least one of the clustered keyword to the classification engine comprises sending the one or more selected keywords to the classification engine.

9. The method of claim 8, wherein the generating the one or more predicted classifications comprises generating the one or more predicted classifications based on an ontology, and wherein the method further comprises:

updating the ontology based on the one or more keywords selected by the user and the predicted classification selected by the user, to correlate the selected one or more keywords with the selected predicted classification.

10. The method of claim 1, wherein the sending the at least one of the one or more keywords to the classification engine comprises:

sending the at least one of the one or more keywords to the classification engine, based on a comparison of the confidence levels with the specified threshold.

11. The method of claim 1, wherein the one or more predicted classifications reside at a first level of the hierarchical classification taxonomy, the method further comprising:

generating one or more predicted classifications at a second level of the hierarchical classification taxonomy, based on the generated one or more keywords, wherein the second level of the hierarchical classification taxonomy is subordinate to the first level of the hierarchical classification taxonomy.

12. The method of claim 11, wherein the one or more predicted classifications at the second level of the hierarchical classification taxonomy are subclassifications of the predicted classification selected by the user.

13. The method of claim 11, further comprising:

receiving, at the user interface, a selection of one of the one or more predicted classifications at the second level of the classification taxonomy; and

classifying the product, based at least in part on the selection of the predicted classification at the second level of the classification taxonomy.

14. A computer system, comprising:

one or more processors; and

a memory coupled with the one or more processors, the memory having stored therein a set of instructions which, when executed by the processors, causes the processors to perform operations of assisting a user in classifying a product comprising;

providing a user interface for receiving input from the user during a procurement process executed by the procurement enterprise application;

obtaining product information at the procurement system about the product the user desires to procure as part of the procurement process;

generating one or more keywords based on the obtained product information, wherein

the one or more generated keywords relating to possible classifications for the product,

the possible classifications identifying one or more levels of a hierarchical classification taxonomy,

the hierarchical classification taxonomy comprising multiple levels and representing a plurality of products available for procurement through the procurement process;

clustering, based on a clustering model, similar keywords of the one or more generated keywords together to generate two or more sets of clustered keywords;

enriching the product information with the clustered keywords;

evaluating the enriched product information to determine a confidence level associated with each of the clustered keywords indicating a level of certainty that an inline-classification engine of the procurement system is able to correctly predict the product'"'"'s categorization;

comparing the confidence level of each of the clustered keyword with a specified threshold;

sending at least one of the clustered keywords and the enriched product information to a classification engine, based on the comparison of the confidence level for each clustered keyword with a value meeting or exceeding the specified threshold;

generating one or more predicted classifications at the classification engine;

rating each of the one or more of the predicted classifications so that any of the predicted classifications with a largest rate value has a better predicted fit with the product and the product information;

ranking the one or more predicted classifications based on corresponding predicted fits;

presenting the one or more ranked predicted classifications to the user, with the user interface while the user is attempting to procure the product during the procurement process;

receiving, at the user interface, a selection of one of the presented, ranked predicted classifications during the procurement process; and

classifying the product based at least in part on the selection and during the procurement process.

15. A computer-readable storage memory comprising a set of instructions stored therein which, when executed by the processors, causes the processors to perform operations of assisting a user in classifying a product, comprising:

providing a user interface for receiving input from the user during a procurement process executed by the procurement enterprise application;

obtaining product information at the procurement system about the product the user desires to procure as part of the procurement process;

generating one or more keywords based on the obtained product information, wherein

the one or more generated keywords relating to possible classifications for the product,

the possible classifications identifying one or more levels of a hierarchical classification taxonomy,

the hierarchical classification taxonomy comprising multiple levels and representing a plurality of products available for procurement through the procurement process;

clustering, based on a clustering model, similar keywords of the one or more generated keywords together to generate two or more sets of clustered keywords;

enriching the product information with the clustered keywords;

evaluating the enriched product information to determine a confidence level associated with each of the clustered keywords indicating a level of certainty that an inline-classification engine of the procurement system is able to correctly predict the product'"'"'s categorization;

comparing the confidence level of each of the clustered keyword with a specified threshold;

sending at least one of the clustered keywords and the enriched product information to a classification engine, based on the comparison of the confidence level for each clustered keyword with a value meeting or exceeding the specified threshold;

generating one or more predicted classifications at the classification engine;

rating each of the one or more of the predicted classifications so that any of the predicted classifications with a largest rate value has a better predicted fit with the product and the product information;

ranking the one or more predicted classifications based on corresponding predicted fits;

presenting the one or more ranked predicted classifications to the user, with the user interface while the user is attempting to procure the product during the procurement process;

receiving, at the user interface, a selection of one of the presented, ranked predicted classifications during the procurement process; and

classifying the product based at least in part on the selection and during the procurement process.