Recommending a document for a user to access
Abstract
A user device can send, to a server, a request for a set of documents likely to be opened by a user, determine a client-suggested document to present to the user and a potential motive for the user to open the client-suggested document, receive a suggestion message from the server, the suggestion message including a set of documents likely to be opened by the user and potential motives for the user to open documents in the set of documents, and present, on a display of the user device, visual representations of the client-suggested document, the potential motive for the user to open the client-suggested document, multiple documents included in the set of documents, and the potential motives for the user to open the multiple documents in the set of documents.
Claims
exact text as granted — not AI-modifiedWhat is claimed is:
1 . A user device comprising:
at least one processor; and a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by the at least one processor, are configured to cause the user device to:
send, to a server, a request for a set of documents likely to be opened by a user;
determine a client-suggested document to present to the user and a potential motive for the user to open the client-suggested document;
receive a suggestion message from the server, the suggestion message including a set of documents likely to be opened by the user and potential motives for the user to open documents in the set of documents; and
present, on a display of the user device, visual representations of the client-suggested document, the potential motive for the user to open the client-suggested document, multiple documents included in the set of documents, and the potential motives for the user to open the multiple documents in the set of documents.
2 . The user device of claim 1 , wherein the instructions are configured to cause the user device to send the request for the set of documents likely to be opened by the user in response to the user launching a document access application on the user device.
3 . The user device of claim 1 , wherein the instructions are configured to cause the user device to determine the client-suggested document to present to the user based on a most recently accessed document.
4 . The user device of claim 1 , wherein the instructions are configured to cause the user device to determine the client-suggested document to present to the user based on a document that the user device has most recently accessed and synchronized with the server.
5 . The user device of claim 1 , wherein the instructions are configured to cause the user device to determine the client-suggested document to present to the user based on a most frequently accessed document over a predetermined time period.
6 . A method performed by a server, the method comprising:
receiving, from a user device, a request for a set of documents likely to be accessed in association with a user account; determining scores for each of multiple documents stored in association with the user account, the scores indicating likelihoods that the documents will be accessed in association with the user account at a time of receiving the request; selecting at least one document from the multiple documents based on the determined scores; selecting, from multiple potential motives, at least one potential motive for the user account to access the at least one document; and sending, to the user device, a suggestion message including the at least one document and the at least one potential motive, the suggestion message prompting the user device to present at least one icon representing the at least one selected document in association with the at least one potential motive.
7 . The method of claim 6 , wherein the selecting the potential motive is performed independently of determining the scores.
8 . The method of claim 6 , wherein the selecting the potential motive includes selecting a first potential motive for which one or more predetermined criteria are met.
9 . The method of claim 6 , wherein the selecting the potential motive includes selecting the potential motive that will maximize a likelihood that the user account will access the at least one selected document.
10 . The method of claim 6 , wherein:
the selecting the at least one document includes selecting at least a first document and a second document from the multiple documents based on the determined scores; the selecting the potential motive includes selecting, from multiple potential motives, a first potential motive for the user account to access the first document and a second potential motive for the user to access the second document; and the sending the potential motive includes sending, to the user device, the suggestion message including the first document, the first potential motive, the second document, and the second potential motive, the suggestion message prompting the user device to present icons representing the first document in association with the first potential motive and the second document in association with the second potential motive.
11 . The method of claim 6 , wherein the determining scores includes applying the multiple documents to a neural network.
12 . The method of claim 6 , wherein the determining scores includes generating multiple vectors representing the multiple documents and applying the multiple vectors to a neural network.
13 . A server comprising:
at least one processor; and a non-transitory computer-readable storage medium comprising instructions stored thereon that, when executed by the at least one processor, are configured to cause the server to:
receive, from a user device, a request for a set of documents likely to be accessed in association with a user account;
determine scores for each of multiple documents stored in association with the user account, the scores indicating likelihoods that the documents will be accessed in association with the user account at a time of receiving the request;
select at least one document from the multiple documents based on the determined scores;
select, from multiple potential motives, at least one potential motive for the user account to access the at least one document; and
send, to the user device, a suggestion message including the at least one document and the at least one potential motive, the suggestion message prompting the user device to present at least one icon representing the at least one selected document in association with the at least one potential motive.
14 . The server of claim 13 , wherein the selecting the potential motive is performed independently of determining the scores.
15 . The server of claim 13 , wherein the selecting the potential motive includes selecting a first potential motive for which one or more predetermined criteria are met.
16 . The server of claim 13 , wherein the selecting the potential motive includes selecting the potential motive that will maximize a likelihood that the user account will access the at least one selected document.
17 . The server of claim 13 , wherein:
the selecting the at least one document includes selecting at least a first document and a second document from the multiple documents based on the determined scores; the selecting the potential motive includes selecting, from multiple potential motives, a first potential motive for the user account to access the first document and a second potential motive for the user to access the second document; and the sending the potential motive includes sending, to the user device, the suggestion message including the first document, the first potential motive, the second document, and the second potential motive, the suggestion message prompting the user device to present icons representing the first document in association with the first potential motive and the second document in association with the second potential motive.
18 . The server of claim 13 , wherein the determining scores includes applying the multiple documents to a neural network.
19 . The server of claim 13 , wherein the determining scores includes generating multiple vectors representing the multiple documents and applying the multiple vectors to a neural network.Join the waitlist — get patent alerts
Track US2021019622A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.