Information processing device
US-12118585-B2 · Oct 15, 2024 · US
US2025069127A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2025069127-A1 |
| Application number | US-202418947934-A |
| Country | US |
| Kind code | A1 |
| Filing date | Nov 14, 2024 |
| Priority date | Aug 24, 2020 |
| Publication date | Feb 27, 2025 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Systems and methods are provided for dynamically generating a product description personalized for a target user account. Product description data and/or product comment data associated with the product are obtained from a server via a communication network. Based on the product description data and/or product comment data, a product description template, comprising fields to be populated, is generated and stored in memory. Comment data associated with a product of interest is obtained from a server via the network. The comment data originates from a set of user accounts each having a similarity score with a target user account that is above a similarity threshold. Based on the set of comment data, comment-based description data are generated and stored in memory. Based on the product description template and the comment-based description data, a product description is generated for presentation for the target user account.
Opening claim text (preview).
What is claimed is: 1 . A method comprising: receiving, using input/output circuitry, from at least one device, a plurality of comments associated with a product listing; generating, by a processor, a tagged version of each comment of the plurality of comments by associating a tag from a plurality of tags with words or phrases of the plurality of comments, wherein the associating is performed using at least one of: (a) a part-of-speech tagging technique, (b) a dependency parsing technique, or (c) a domain knowledge analysis technique; storing, in a comment database, tagged versions of the plurality of comments; receiving, by input/output circuitry, a request to access a page for viewing the product listing; generating, by the processor, a description for the product listing by: accessing, from a memory, a description template that comprises a plurality of modifiable fields, wherein each modifiable field of the plurality of fields is linked to a respective tag from the plurality of tags; and populating each respective modifiable field of the plurality of fields with a respective word or phrase from the comment database based on determining that a tag linked to the respective modifiable field matches a respective tag associated with the respective word or phrase in the comment database; and generating, by input/output circuitry, for display the description for the product listing. 2 . The method of claim 1 , wherein each tag of the plurality of tags comprises information related to a type of word or phrase to be used in populating a modifiable field. 3 . The method of claim 1 , wherein the description template comprises at least one complete sentence formed by the plurality of modifiable fields combined with a series of connecting words or phrases. 4 . The method of claim 1 , wherein the accessing, from the memory, the description template that comprises a plurality of modifiable fields further comprises: accessing, from the memory, a plurality of description templates corresponding to the product listing; and selecting the description template from the plurality of description templates based on an importance score associated with the description template. 5 . The method of claim 1 , wherein the generating, by the processor, the description for the product listing further comprises: accessing, from the memory, multiple description templates associated with the product listing; and concatenating the multiple description templates associated with the product listing into a singular description for the product listing which comprises one or more paragraphs related to the product listing. 6 . The method of claim 5 , wherein the concatenating the multiple description templates associated with the product listing into the singular description for the product listing which comprises one or more paragraphs related to the product listing further comprises: accessing, from the memory, importance scores associated with each respective description template of the multiple description templates; and concatenating the multiple description templates associated with the product listing into the singular description such that the ordering of the multiple description templates within the singular description for the product listing is based on the importance scores associated with each respective description template. 7 . The method of claim 1 , wherein the description template corresponds to the product listing, and wherein the description template is generated by processing descriptions associated with a plurality of similar product listings. 8 . The method of claim 1 , further comprising: identifying metadata associated with the plurality of comments, wherein the identified metadata includes identification of a device that each comment was received from and a date specifying when each comment was received; and storing, in the comment database, the plurality of comments and the identified metadata associated with the plurality of comments. 9 . A system comprising: a memory; input/output circuitry configured to: receive, from at least one device, a plurality of comments associated with a product listing; control circuitry configured to: generate a tagged version of each comment of the plurality of comments by associating a tag from a plurality of tags with words or phrases of the plurality of comments, wherein the associating is performed using at least one of: (a) a part-of-speech tagging technique, (b) a dependency parsing technique, or (c) a domain knowledge analysis technique; store, in a comment database, tagged versions of the plurality of comments; receive, by input/output circuitry, a request to access a page for viewing the product listing; generate a description for the product listing by: accessing, from the memory, a description template that comprises a plurality of modifiable fields, wherein each modifiable field of the plurality of fields is linked to a respective tag from the plurality of tags; and populating each respective modifiable field of the plurality of fields with a respective word or phrase from the comment database based on determining that a tag linked to the respective modifiable field matches a respective tag associated with the respective word or phrase in the comment database; and wherein the input/output circuitry is further configured to: generate for display the description for the product listing. 10 . The system of claim 9 , wherein each tag of the plurality of tags comprises information related to a type of word or phrase to be used in populating a modifiable field. 11 . The system of claim 9 , wherein the description template comprises at least one complete sentence formed by the plurality of modifiable fields combined with a series of connecting words or phrases. 12 . The system of claim 9 , wherein the control circuitry is configured to access, from the memory, the description template that comprises a plurality of modifiable fields by: accessing, from the memory, a plurality of description templates corresponding to the product listing; and selecting the description template from the plurality of description templates based on an importance score associated with the description template. 13 . The system of claim 9 , wherein the control circuitry is configured to generate the description for the product listing by: accessing, from the memory, multiple description templates associated with the product listing; and concatenating the multiple description templates associated with the product listing into a singular description for the product listing which comprises one or more paragraphs related to the product listing. 14 . The system of claim 13 , wherein the control circuitry is configured to concatenate the multiple description templates associated with the product listing into the singular description for the product listing which comprises one or more paragraphs related to the product listing by: accessing, from the memory, importance scores associated with each respective description template of the multiple description templates; and concatenating the multiple description templates associated with the product listing into the singular description such that the ordering of the multiple description templates within the singular description for the product listing is based on the importance scores associated with each respective description template. 15 . The system of claim 9 , wherein the description template corresponds to the product listing, and wherein the description template is generated by processing des
utilising user interfaces specially adapted for shopping · CPC title
Recommending goods or services · CPC title
Rating or review of business operators or products · CPC title
Market modelling; Market analysis; Collecting market data · CPC title
Office automation; Time management · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.