# US 2025/0148754 A1 · Systems and methods for automating benchmark generation using neural networks for image or video selection > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2025/0148754 A1 - Document ID: US20250148754A1 - Status: Published application - Kind: A1 - Application number: 19/019,081 - Filed: 2025-01-13 - Published: 2025-05-08 - Earliest claimed: 2017-07-26 - Assignees: Vizit Labs, Inc. - Applicants: Vizit Labs, Inc. - Inventors: Jehan Hamedi; Elham Saraee; Zachary Halloran - Web page: https://patentgrep.com/patent/US20250148754A1 ## CPC - G06V 10/761: {Proximity, similarity or dissimilarity measures} - G06F 16/438: Presentation of query results - G06N 3/045: Combinations of networks - G06N 3/08: Learning methods - G06V 10/40: Extraction of image or video features - G06V 10/82: using neural networks - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method includes accessing a web-based property over a network; storing a plurality of images or videos from the web-based property and associations between the plurality of images or videos and a target audience identifier responsive to the web-based property having a stored association with the target audience identifier; retrieving the plurality of images or videos from the database responsive to each of the plurality of images or videos having stored associations with the target audience identifier; executing a neural network to generate a performance score for each of the plurality of images or videos; calculating a target audience benchmark; executing the neural network to generate a first performance score for a first image or video and a second performance score for a second image or video; comparing the first performance score and the second performance score to the benchmark; and generating a record identifying the first image or video. ## Claims ### Claim 1 A system comprising: one or more processors configured by machine-readable instructions to: extract one or more features from an image or video; select a set of rules from a plurality of sets of rules based on a source of the image or video, the set of rules indicating a set of expected features; compare the one or more extracted features to the set of rules to generate a performance score for the image or video based on a difference between the one or more features and the set of expected features; and store an association between the performance score and the image or video. ### Claim 2 (depends on 1) The system of claim 1, wherein the one or more processors are further configured to: select the set of rules from the plurality of sets of rules responsive to the set of rules having a stored association with an identifier of the source. ### Claim 3 (depends on 1) The system of claim 1, wherein the one or more processors are further configured to: select the set of rules from the plurality of sets of rules responsive to the set of rules having a stored association with an identifier of a website, computing network, or database. ### Claim 4 (depends on 1) The system of claim 1, wherein the one or more processors are configured to compare the one or more extracted features to the set of rules by: determining a number of defined rules that the extracted one or more features satisfy and a number of defined rules that the extracted one or more features do not satisfy; and determining the performance score based on the number of defined rules that the extracted one or more features satisfy and the number of defined rules that the extracted one or more features do not satisfy. ### Claim 5 (depends on 1) The system of claim 1, wherein the one or more processors are configured to compare the one or more extracted features to the set of rules by: determining a number of the set of expected features that match the at least one of the set of expected features; and determining the performance score based on the number of the set of expected features that match the at least one of the set of expected features. ### Claim 6 (depends on 5) The system of claim 5, wherein the one or more processors are configured to determine the number of the set of expected features that match the at least one of the set of expected features by: determining a plurality of features that match a defined pattern of features in the set of expected features. ### Claim 7 (depends on 1) The system of claim 1, wherein the one or more processors are further configured to: configure a web page to include the image or video responsive to the performance exceeding a threshold. ### Claim 8 (depends on 1) The system of claim 1, wherein the one or more processors are configured to: receive a request comprising the image or video; and execute a neural network to extract the one or more features from the image or video responsive to receiving the request. ### Claim 9 (depends on 1) The system of claim 1, wherein the one or more processors is further configured to generate a recommendation to upload the image or video to a website. ### Claim 10 A system, comprising: one or more processors configured by machine-readable instructions to: extract one or more features from an image or video; select a set of rules from a plurality of sets of rules based on a category corresponding to the set of rules, the set of rules generated based on a plurality of images or videos each corresponding to the category; compare the one or more extracted features to the set of rules to generate a performance score for the image or video based on a difference between the one or more features and the set of rules; and store an association between the performance score and the image or video. ### Claim 11 (depends on 10) The system of claim 10, wherein the one or more processors are further configured to: selecting the set of rules from the plurality of sets of rules responsive to the set of rules having a stored association with an identifier of a source of each of the plurality of images or videos. ### Claim 12 (depends on 10) The system of claim 10, wherein the one or more processors are further configured to: selecting the set of rules from the plurality of sets of rules responsive to the set of rules having a stored association with an identifier of a website, computing network, or database. ### Claim 13 (depends on 10) The system of claim 10, wherein the one or more processors are further configured to generate the set of rules by: extracting a set of features from each of the plurality of images or videos corresponding to the category; executing a second neural network to generate a second performance score for each of the plurality of images or videos; and generating one or more distributions for each of the set of features. ### Claim 14 (depends on 13) The system of claim 13, wherein the one or more processors are configured to compare the one or more extracted features to the set of rules by comparing the one or more extracted features of the image or video to the one or more distributions. ### Claim 15 (depends on 10) The system of claim 10, wherein the one or more processors is further configured to generate a recommendation to upload the image or video to a website. ### Claim 16 A system, comprising: one or more processors configured by machine-readable instructions to: extract one or more features from an image or video; generate a set of rules from one or more images or videos selected based on a similarity between the one or more features of the image or video and features of the one or more images or videos; compare the one or more extracted features to the set of rules to generate a performance score for the image or video based on a difference between the one or more features and the set of rules; and store an association between the performance score and the image or video. ### Claim 17 (depends on 16) The system of claim 16, wherein the one or more processors are further configured to: select the one or more images or videos based on the one or more images or videos each having a stored association with an identifier of a website, computing network, or database. ### Claim 18 (depends on 16) The system of claim 16, wherein the one or more processors are configured to generate the set of rules by: extracting a set of features from each of the one or more images or videos; executing a neural network to generate a second performance score for each of the one or more images or videos; and generating one or more distributions for each of the set of features. ### Claim 19 (depends on 18) The system of claim 18, wherein the one or more processors are configured to compare the one or more extracted features to the set of rules by comparing the one or more extracted features of the image or video to the one or more distributions. ### Claim 20 (depends on 19) The system of claim 19, wherein the one or more processors are further configured to update the set of rules based on a new image or video by: extracting a new set of features from the new image or video; executing the neural network to generate a new performance score for the new image or video; and updating the one or more distributions for each feature of the new set of features based on the new performance score for the new image or video. ### Claim 21 (depends on 18) The system of claim 18, wherein the one or more processors are configured to compare the one or more extracted features to the set of rules by: comparing the one or more extracted features to the one or more distributions; and generating the performance score for the image or video based on weights assigned to the one or more extracted features.