Dual web graph
View Patent ↗Scoring a document is disclosed. One or more metrics is determined in a forward direction. One or more backwards metrics is determined. The document is scored based at least in part on a combination of the metrics.
1. A method of scoring a document with respect to a distinguished node, the method comprising:
determining, using a computer system comprising a processor, one or more metrics in a forward direction for the document with respect to the distinguished node and a graph including the document and the distinguished node, the one or more metrics in the forward direction indicating relevance of the document to the distinguished node and being based on a proportion of random walks of the graph including the distinguished node preceding the document with in-links and out-links of the graph in an original direction;
determining, using the computer system comprising a processor, one or more backward metrics for the document with respect to the distinguished node and the graph, the one or more backward metrics indicating relevance of the document to the distinguished node and being based on a proportion of random walks of the graph including the document preceding the distinguished node with in-links and out-links of the graph being reversed in direction; and
scoring, using the computer system comprising a processor, the document based at least in part on a combination of the metrics.
2. The method of claim 1 wherein determining one or more metrics in a forward direction includes using reversible Markov chains.
3. The method of claim 1 wherein the document is represented in a dual graph.
4. The method of claim 1 wherein the combination is a product.
5. The method of claim 1 wherein the combination includes weighting at least one of the metrics.
6. The method of claim 1 wherein the combination includes weighting the one or more metrics determined in the forward direction differently from the one or more backward metrics.
7. The method of claim 1 wherein the combination includes normalizing at least one of the metrics.
8. A system for scoring a document with respect to a distinguished node, the method comprising:
a processor, configured to:
determine one or more metrics in a forward direction for the document with respect to the distinguished node and a graph including the document and the distinguished node, the one or more metrics in the forward direction being based on a proportion of random walks of the graph including the distinguished node preceding the document with in-links and out-links of the graph in an original direction;
determine one or more backward metrics for the document with respect to the distinguished node and the graph, the one or more backward metrics being based on a proportion of random walks of the graph including the document preceding the distinguished node with in-links and out-links of the graph being reversed in direction; and
score the document based at least in part on a combination of the metrics; and
a memory, coupled with the processor, wherein the memory is configured to provide the processor with instructions.
9. The system of claim 8 wherein determining one or more metrics in a forward direction includes using reversible Markov chains.
10. The system of claim 8 wherein the document is represented in a dual graph.
11. The system of claim 8 wherein the combination is a product.
12. The system of claim 8 wherein the combination includes weighting at least one of the metrics.
13. The system of claim 8 wherein the combination includes weighting the one or more metrics determined in the forward direction differently from the one or more backward metrics.
14. The system of claim 8 wherein the combination includes normalizing at least one of the metrics.
15. A computer program product for scoring a document with respect to a distinguished node, the computer program product being embodied as a non-transitory computer readable medium and comprising computer instructions for:
determining one or more metrics in a forward direction for the document with respect to the distinguished node and a graph including the document and the distinguished node, the one or more metrics in the forward direction being based on a proportion of random walks of the graph including the distinguished node preceding the document with in-links and out-links of the graph in an original direction;
determining one or more backward metrics for the document with respect to distinguished node, the one or more backward metrics being based on a proportion of random walks of the graph including the document preceding the distinguished node with in-links and out-links of the graph being reversed in direction; and
scoring the document based at least in part on a combination of the metrics.
16. The computer program product of claim 15 wherein determining one or more metrics in a forward direction includes using reversible Markov chains.
17. The computer program product of claim 15 wherein the document is represented in a dual graph.
18. The computer program product of claim 15 wherein the combination is a product.
19. The computer program product of claim 15 wherein the combination includes weighting at least one of the metrics.
20. The computer program product of claim 15 wherein the combination includes weighting the one or more metrics determined in the forward direction differently from the one or more backward metrics.