Implementing a graphical user interface to collect information from a user to identify a desired document based on dissimilarity and/or collective closeness to other identified documents

1. A method of implementing a graphical user interface to collect information from a user, the method comprising:

dynamically displaying, by the graphical user interface, K>1 groupings of M>1 documents from a catalog of documents in an embedding space,

wherein the catalog of documents is from a database, a distance between each pair of the documents in the embedding space corresponding to a predetermined measure of dissimilarity between the pair of documents, and

wherein the K groupings are formed using K-medoid clustering analysis;

receiving a user selection of one grouping of the K groupings;

dynamically displaying, by the graphical user interface, a predetermined number P>0 documents of the cluster which corresponds to the selected grouping;

receiving, from the user, categorical feedback with respect to two or more of the P k documents of the selected grouping, wherein the categorical feedback is a user interaction with the two or more of the P k documents indicating that the user likes at least one of the two or more documents of the P k documents and that the user dislikes at least one of two or more other documents of the P k documents, wherein the liked one or more documents is a set of liked documents and the disliked one or more documents is a set of disliked documents; and

dynamically displaying, by the graphical user interface, an identified subsequent document from the selected grouping in dependence on the set of liked documents and the set of disliked documents.

2. The method of claim 1 , wherein the measure of dissimilarity between the pair of documents is based on at least a color of the documents of the pair of documents.

3. A non-transitory computer-readable recording medium having computer instructions recorded thereon, the computer instructions, when executed on one or more processors, causing the one or more processors to implement the method of claim 1 .

4. A system including one or more processors coupled to memory, the memory being loaded with computer instructions, the computer instructions, when executed on the one or more processors, causing the one or more processors to implement the method of claim 1 .

5. A method for user identification of a desired document, comprising:

providing, accessibly to a computer system, a database identifying (i) a catalog of documents in an embedding space and (ii) a distance between each pair of the documents in the embedding space, the distance corresponding to a predetermined measure of dissimilarity between the pair of documents;

identifying, using the computer system and for dynamic display toward the user, an initial (i=0) collection of N0>1 candidate documents from the catalog of documents in the embedding space, the initial collection having fewer documents than the catalog of documents;

for each i′th iteration in a plurality of iterations, beginning with a first iteration (i=1):

detecting an implicit user action with respect to two or more documents of the (i−1)′th collection of documents, wherein the implicit user action is an input of an interaction with the two or more documents of the (i−1)′th collection of documents,

assigning a meaning to the implicit user action, wherein the meaning is an indication that the user (i) likes at least one of the two or more documents of the (i−1)′th collection of documents and (ii) dislikes at least one of the two or more documents of the (i−1)′th collection of documents,

identifying, using the computer system, an i′th collection of Ni>1 candidate documents from the embedding space such that, according to a predefined definition of collective closeness, the candidate documents in the i′th collection of Ni>1 candidate documents have a collective closeness in the embedding space to the two or more documents that is dependent upon the meaning assigned to the implicit user action, and identifying, for dynamic display toward the user, the i′th collection of Ni>1 candidate documents; and

taking action in response to user selection of a document, of the i′th collection of Ni>1 documents, dynamically identified toward the user,

wherein the predefined definition of collective closeness is defined such that a candidate document X is considered closer to a document A than to a document B if in the embedding space, d(A,X)<d(B,X).

6. A non-transitory computer-readable recording medium having computer instructions recorded thereon, the computer instructions, when executed on one or more processors, causing the one or more processors to implement the method of claim 5 .

7. A system including one or more processors coupled to memory, the memory being loaded with computer instructions, the computer instructions, when executed on the one or more processors, causing the one or more processors to implement the method of claim 5 .

8. A method for user identification of a desired document, comprising:

providing, accessibly to a computer system, a database identifying (i) a catalog of documents in an embedding space and (ii) a distance between each pair of the documents in the embedding space corresponding to a predetermined measure of dissimilarity between the pair of documents;

identifying, using the computer system and for dynamic display toward the user, an initial (i=0) collection of N0>1 candidate documents from an initial (i=0) candidate space within the embedding space, the initial collection having fewer documents than the initial candidate space;

for each i′th iteration in a plurality of iterations, beginning with a first iteration (i=1):

detecting an implicit user action with respect to two or more documents of the (i−1)′th collection of documents, wherein the implicit user action is an input of an interaction with the two or more documents of the (i−1)′th collection of documents,

assigning a meaning to the implicit user action, wherein the meaning is an indication that the user (i) likes at least one of the two or more documents of the (i−1)′th collection of documents and (ii) dislikes at least one of the two or more documents of the (i−1)′th collection of documents,

identifying, using the computer system, an i′th candidate space from the embedding space such that, according to a predefined definition of collective closeness and in dependence on the meaning assigned to the implicit user action, the documents in the i′th candidate space are collectively closer in the embedding space to or collectively farther in the embedding space from documents in an i′th selected subset, than are the documents in the (i−1)′th candidate space, and

identifying, for dynamic display toward the user, an i′th collection of Ni>1 candidate documents from the i′th candidate space, Ni being smaller than the number of documents in the i′th candidate space; and

taking action in response to user selection of a document, of the i′th collection of Ni>1 documents, dynamically identified toward the user,

wherein the predefined definition of collective closeness is defined such that a candidate document X is considered closer to a document A than to a document B if in the embedding space, d(A,X)<d(B,X).

9. A non-transitory computer-readable recording medium having computer instructions recorded thereon, the computer instructions, when executed on one or more processors, causing the one or more processors to implement the method of claim 8 .

10. A system including one or more processors coupled to memory, the memory being loaded with computer instructions, the computer instructions, when executed on the one or more processors, causing the one or more processors to implement the method of claim 8 .

11. A method for user identification of a desired document, comprising:

providing, accessibly to a computer system, a database identifying (i) a catalog of documents in an embedding space and (ii) a distance between each pair of the documents in the embedding space corresponding to a predetermined measure of dissimilarity between the pair of documents;

identifying, using a computer system and for dynamic display toward the user, an initial (i=0) collection of N0>1 candidate documents from the catalog of documents in the embedding space, the initial collection having fewer documents than the catalog of documents;

for each i′th iteration in a plurality of iterations, beginning with a first iteration (i=1):

detecting an implicit user action with respect to two or more documents of the (i−1)′th collection of documents, wherein the implicit user action is an input of an interaction with the two or more documents of the (i−1)′th collection of documents indicating that the user (i) likes at least one of the two or more documents of the (i−1)′th collection of documents and (ii) dislikes at least one of the two or more documents of the (i−1)′th collection of documents,

assigning a weight to the implicit user actions in dependence on whether the user action indicates that the user likes or dislikes the two or more documents of the (i−1)′th collection of documents,

wherein the assigned weight is positive when a particular user action indicates that the user likes a document of the (i−1)′th collection of documents, and

wherein the assigned weight is negative when the particular user action indicates that the user dislikes the document of the (i−1)′th collection of documents,

identifying, using a computer system, an i′th collection of Ni>1 candidate documents from the embedding space such that, according to a predefined definition of collective closeness, the candidate documents in the i′th collection of Ni>1 candidate documents have a collective closeness in the embedding space to the document that is dependent upon the weight assigned to the implicit user action, and

identifying for dynamic display toward the user the i′th collection of Ni>1 candidate documents; and

taking action in response to user selection of a document, of the i′th collection of Ni>1 documents, dynamically identified toward the user, wherein the predefined definition of collective closeness is defined such that a candidate document X is considered closer to a document A than to a document B if in the embedding space, d(A,X)<d(B,X).

12. A non-transitory computer-readable recording medium having computer instructions recorded thereon, the computer instructions, when executed on one or more processors, causing the one or more processors to implement the method of claim 11 .

13. A system including one or more processors coupled to memory, the memory being loaded with computer instructions, the computer instructions, when executed on the one or more processors, causing the one or more processors to implement the method of claim 11 .