Similarity searching across digital standards
One embodiment provides a method for identifying similar objects by performing document attribute comparisons, the method including: receiving a reference document, wherein the reference document corresponds to an object and comprises a plurality of attributes of the object; receiving a request for a similarity comparison, wherein the request provides an indication of similarity attributes to be used in the similarity comparison; comparing the reference document to each of a plurality of documents corresponding to other objects; generating a document similarity score for each of the plurality of documents, wherein the document similarity score is generated based upon an aggregation of similarity attribute scores calculated for each of the similarity attributes; and providing at least one of the plurality of documents with an indication of a similarity. Other aspects are described and claimed.
1. A method for identifying similar objects by performing document attribute comparisons, the method comprising:
providing a digital standard system comprising a user interface, at least one machine-learning model, and at least one data store comprising a plurality of digital standards;
receiving, within an input field of the user interface, a reference document, wherein the reference document corresponds to an object and comprises a plurality of attributes of the object, each of the attributes having a data type;
receiving a request for a similarity comparison based upon the reference document, wherein the request provides an indication of similarity attributes corresponding to attributes of the object to be compared with attributes of other objects during the similarity comparison;
comparing, using the digital standard system, the reference document to each digital standard in a group of digital standards of the plurality of digital standards that correspond to other objects having a same type as the reference document, wherein the comparing comprises making the data types for the similarity attributes the same across the reference document and the group of digital standards by substituting a data type of each of the similarity attributes with a defined data type and performing a comparison of the similarity attributes having the substitute data types, wherein the comparison performed is based upon the substitute data type of a given similarity attribute;
generating, using the digital standard system, a document similarity score for each of the digital standards within the group based upon the comparing; and
displaying, within the user interface, at least one of the digital standards within the group with an indication of a similarity of the at least one of the digital standards within the group to the reference document, the indication of similarity being based upon a document similarity score corresponding to the at least one of the digital standards within the group, wherein the at least one of the digital standards displayed is different than the reference document and is a replacement for the object corresponding to the reference document.
2. The method of claim 1 , wherein attributes being similar within a given document have a plurality of different data types.
3. The method of claim 2 , wherein the substitute data type comprises a range substitute data type and wherein the range substitute data type is utilized for attributes having a plurality of different data types including a range data type.
4. The method of claim 3 , wherein the comparing comprises determining a minimum value distance of a minimum value of the similarity attribute within a given of the digital standards within the group with respect to a minimum value of the similarity attribute within the reference document, determining a maximum value distance of a maximum value of the similarity attribute within a given of the digital standards within the group with respect to a maximum value of the similarity attribute within the reference document, and normalizing a range of the similarity attribute within the reference document.
5. The method of claim 2 , wherein the substitute data type comprises a set substitute data type and wherein the set substitute data type is utilized for attributes having a plurality of different data types not including a range data type.
6. The method of claim 1 , wherein the comparing comprises comparing similarity attributes having different data types between the reference document and a document of the digital standards within the group being compared.
7. The method of claim 1 , wherein at least one of the similarity attributes comprises a nominal data type defining a value the user wants to achieve for the attribute and wherein the substitute data types comprises a range substitute data type derived from the nominal data type.
8. The method of claim 1 , wherein the generating comprises normalizing each of the similarity attribute scores assigned to each of the similarity attributes.
9. The method of claim 1 , wherein both the reference document and each of the digital standards within the group comprise standards documents.
10. The method of claim 1 , wherein the object comprises at least one of: a material and a part.
11. A system for identifying similar objects by performing document attribute comparisons, the system comprising:
one or more processors;
a memory device that stores instructions executable by the processor to:
provide a digital standard system comprising a user interface, at least one machine-learning model, and at least one data store comprising a plurality of digital standards;
receive, within an input field of the user interface, a reference document, wherein the reference document corresponds to an object and comprises a plurality of attributes of the object, each of the attributes having a data type;
receive a request for a similarity comparison based upon the reference document, wherein the request provides an indication of similarity attributes corresponding to attributes of the object to be compared with attributes of other objects during the similarity comparison;
compare, using the digital standard system, the reference document to each digital standard in a group of digital standards of the plurality of digital standards that correspond to other objects having a same type as the reference document, wherein the comparing comprises making the data types for the similarity attributes the same across the reference document and the group of digital standards by substituting a data type of each of the similarity attributes with a defined data type and performing a comparison of the similarity attributes having the substitute data types, wherein the comparison performed is based upon the substitute data type of a given similarity attribute;
generate, using the digital standard system, a document similarity score for each of the digital standards within the group based upon the comparing; and
display, within the user interface, at least one of the digital standards within the group with an indication of a similarity of the at least one of the digital standards within the group to the reference document, the indication of similarity being based upon a document similarity score corresponding to the at least one of the digital standards within the group, wherein the at least one of the digital standards displayed is different than the reference document and is a replacement for the object corresponding to the reference document.
12. The system of claim 11 , wherein attributes being similar within a given document have a plurality of different data types.
13. The system of claim 12 , wherein the substitute data type comprises a range substitute data type and wherein the range substitute data type is utilized for attributes having a plurality of different data types including a range data type.
14. The system of claim 13 , wherein the comparing comprises determining a minimum value distance of a minimum value of the similarity attribute within a given of the digital standards within the group with respect to a minimum value of the similarity attribute within the reference document, determining a maximum value distance of a maximum value of the similarity attribute within a given of the digital standards within the group with respect to a maximum value of the similarity attribute within the reference document, and normalizing a range of the similarity attribute within the reference document.
15. The system of claim 12 , wherein the substitute data type comprises a set substitute data type and wherein the set substitute data type is utilized for attributes having a plurality of different data types not including a range data type.
16. The system of claim 11 , wherein the comparing comprises comparing similarity attributes having different data types between the reference document and a document of the digital standards within the group being compared.
17. The system of claim 11 , wherein at least one of the similarity attributes comprises a nominal data type defining a value the user wants to achieve for the attribute and wherein the substitute data types comprises a range substitute data type derived from the nominal data type.
18. The system of claim 11 , wherein the generating comprises normalizing each of the similarity attribute scores assigned to each of the similarity attributes.
19. The system of claim 11 , wherein both the reference document and each of the digital standards within the group comprise standards documents.
20. A product for identifying similar objects by performing document attribute comparisons, the product comprising:
a computer-readable storage device that stores executable code that, when executed by a processor, causes the product to:
provide a digital standard system comprising a user interface, at least one machine-learning model, and at least one data store comprising a plurality of digital standards;
receive, within an input field of the user interface, a reference document, wherein the reference document corresponds to an object and comprises a plurality of attributes of the object, each of the attributes having a data type;
receive a request for a similarity comparison based upon the reference document, wherein the request provides an indication of similarity attributes corresponding to attributes of the object to be compared with attributes of other objects during the similarity comparison;
compare, using the digital standard system, the reference document to each digital standard in a group of digital standards of the plurality of digital standards that correspond to other objects having a same type as the reference document, wherein the comparing comprises making the data types for the similarity attributes the same across the reference document and the group of digital standards by substituting a data type of each of the similarity attributes with a defined data type and performing a comparison of the similarity attributes having the substitute data types, wherein the comparison performed is based upon the substitute data type of a given similarity attribute;
generate, using the digital standard system, a document similarity score for each of the digital standards within the group based upon the comparing; and
display, within the user interface, at least one of the digital standards within the group with an indication of a similarity of the at least one of the digital standards within the group to the reference document, the indication of similarity being based upon a document similarity score corresponding to the at least one of the digital standards within the group, wherein the at least one of the digital standards displayed is different than the reference document and is a replacement for the object corresponding to the reference document.