Metadata tag auto-application to posted entries
A system and a method are disclosed for receiving, from a source of a plurality of candidate sources, a payload comprising content and metadata. The system selects a destination to which to route the payload based on the source and the content, and generates an entry at the destination based on the content. The system inputs the metadata into a classification engine, and receives, as output from the classification engine, one or more classifications for the payload. The system applies a metadata tag to the entry, the metadata tag indicating the one or more classifications. The system receives a search request from a client device specifying at least one of the one or more classifications, and, in response to receiving the search request, provides the entry to the client device based on a matching classification.
1 . A non-transitory computer-readable medium comprising memory with instructions encoded thereon, the instructions, when executed, causing one or more processors to perform operations, the instructions comprising instructions to:
receive a search query, the search query comprising a classification;
search entries tagged with the classification, the classification reducing a search space to entries having a metadata tag indicating the classification; and
return a search result having data matching the search query, wherein data entries within the search space are generated by:
receiving, from a source of a plurality of candidate sources, a payload comprising content and metadata;
selecting a destination to which to route the payload based on the source and the content;
generating an entry at the destination based on the content;
inputting the metadata into a classification engine;
receiving, as output from the classification engine, one or more classifications for the payload; and
applying a metadata tag to the entry, the metadata tag indicating the one or more classifications.
2 . The non-transitory computer-readable medium of claim 1 , wherein each of the plurality of candidate sources generate payloads based on input into respective, different user interfaces.
3 . The non-transitory computer-readable medium of claim 1 , wherein selecting the destination to which to route the payload based on the source and the content comprises:
selecting a root of a plurality of candidate root based on the source, wherein each candidate root corresponds to a different one of the plurality of candidate sources;
selecting a leaf of the root, of a plurality of candidate leaves, based on the content, wherein the leaf corresponds to the destination.
4 . The non-transitory computer-readable medium of claim 1 , wherein the classification engine identifies the one or more classifications by comparing the metadata to entries of a database, the entries corresponding candidate metadata to corresponding classifications.
5 . The non-transitory computer-readable medium of claim 1 , wherein the classification engine is a machine learning model that takes the metadata as input and outputs probabilities corresponding to candidate classifications, and wherein receiving the one or more classifications for the payload comprises:
receiving the probabilities;
identifying one or more respective probabilities that meet or exceed a threshold; and
selecting the one or more candidate classifications based on their respective probabilities having met or exceeded the threshold.
6 . The non-transitory computer-readable medium of claim 5 , wherein the machine learning model is trained using training data comprising combinations of metadata paired with labels, the labels indicating a classification corresponding to the combinations of metadata.
7 . The non-transitory computer-readable medium of claim 1 , wherein generating the entry comprises determining a discrepancy between a value stored at the destination, and a corresponding value shown within the contents, and wherein the data entries are further generated by providing an identification of the discrepancy to a client device performing a search request that specifies the classification.
8 . A computer-implemented method comprising:
receiving a search query, the search query comprising a classification;
searching entries tagged with the classification, the classification reducing a search space to entries having a metadata tag indicating the classification; and
returning a search result having data matching the search query, wherein data entries within the search space are generated by:
receiving, from a source of a plurality of candidate sources, a payload comprising content and metadata;
selecting a destination to which to route the payload based on the source and the content;
generating an entry at the destination based on the content;
inputting the metadata into a classification engine;
receiving, as output from the classification engine, one or more classifications for the payload; and
applying a metadata tag to the entry, the metadata tag indicating the one or more classifications.
9 . The computer-implemented method of claim 8 , wherein each of the plurality of candidate sources generate payloads based on input into respective, different user interfaces.
10 . The computer-implemented method of claim 8 , wherein selecting the destination to which to route the payload based on the source and the content comprises:
selecting a root of a plurality of candidate root based on the source, wherein each candidate root corresponds to a different one of the plurality of candidate sources;
selecting a leaf of the root, of a plurality of candidate leaves, based on the content, wherein the leaf corresponds to the destination.
11 . The computer-implemented method of claim 8 , wherein the classification engine identifies the one or more classifications by comparing the metadata to entries of a database, the entries corresponding candidate metadata to corresponding classifications.
12 . The computer-implemented method of claim 8 , wherein the classification engine is a machine learning model that takes the metadata as input and outputs probabilities corresponding to candidate classifications, and wherein receiving the one or more classifications for the payload comprises:
receiving the probabilities;
identifying one or more respective probabilities that meet or exceed a threshold; and
selecting the one or more candidate classifications based on their respective probabilities having met or exceeded the threshold.
13 . The computer-implemented method of claim 12 , wherein the machine learning model is trained using training data comprising combinations of metadata paired with labels, the labels indicating a classification corresponding to the combinations of metadata.
14 . The computer-implemented method of claim 8 , wherein generating the entry comprises determining a discrepancy between a value stored at the destination, and a corresponding value shown within the contents, and wherein the method further comprises providing an identification of the discrepancy to a client device performing a search request that specifies the classification.
15 . A system comprising:
memory with instructions encoded thereon; and
one or more processors that, when executing the instructions, are caused to perform operations comprising:
receiving a search query, the search query comprising a classification;
searching entries tagged with the classification, the classification reducing a search space to entries having a metadata tag indicating the classification; and
returning a search result having data matching the search query, wherein data entries within the search space are generated by:
receiving, from a source of a plurality of candidate sources, a payload comprising content and metadata;
selecting a destination to which to route the payload based on the source and the content;
generating an entry at the destination based on the content;
inputting the metadata into a classification engine;
receiving, as output from the classification engine, one or more classifications for the payload; and
applying a metadata tag to the entry, the metadata tag indicating the one or more classifications.
16 . The system of claim 15 , wherein each of the plurality of candidate sources generate payloads based on input into respective, different user interfaces.
17 . The system of claim 15 , wherein selecting the destination to which to route the payload based on the source and the content comprises:
selecting a root of a plurality of candidate root based on the source, wherein each candidate root corresponds to a different one of the plurality of candidate sources;
selecting a leaf of the root, of a plurality of candidate leaves, based on the content, wherein the leaf corresponds to the destination.
18 . The system of claim 15 , wherein the classification engine identifies the one or more classifications by comparing the metadata to entries of a database, the entries corresponding candidate metadata to corresponding classifications.
19 . The system of claim 15 , wherein the classification engine is a machine learning model that takes the metadata as input and outputs probabilities corresponding to candidate classifications, and wherein receiving the one or more classifications for the payload comprises:
receiving the probabilities;
identifying one or more respective probabilities that meet or exceed a threshold; and
selecting the one or more candidate classifications based on their respective probabilities having met or exceeded the threshold.
20 . The system of claim 19 , wherein the machine learning model is trained using training data comprising combinations of metadata paired with labels, the labels indicating a classification corresponding to the combinations of metadata.