a method selects first content and second content.
In some embodiments, a method selects first content and second content. The first content and the second content are configured to be delivered to clients. First labels are determined for categories for the first content. The first labels are based on an analysis of the first content. Second labels are determined for the categories for the second content. The second labels are based on an analysis of the second content. The method compares the first labels and the second labels to determine scores for the first labels. The scores is based on parameters of a matching tool that is configured to determine a match between instances of content. A weight of a category is used to adjust a score in the scores to generate an adjusted score. The score is for the label that is determined for the category. The method outputs information for the adjusted score and other scores.
BACKGROUND (1) A system may compare metadata for two instances of content to determine if the two instances match. For example, a company may have instances of catalog content, such as videos, that may be delivered to client devices. A system may be used to match instances of supplemental content with instances of catalog content. The system may use a manual selection of information about the instances of catalog content and the instances of supplemental content to perform the comparison. The manual selection may involve inputting keywords that describe the content, demographics (e.g., age ranges) for the content, etc. Using the manual selection may provide obvious matches between content, but these obvious matches may not always be the optimal matches. For example, an instance of catalog content may be manually tagged as with the age range of 21-30 and an instance of supplemental content that is matched with the instance of catalog content may also be manually tagged as being associated with the same age range. This is an obvious match between two general labels. However, there may be other instances of supplemental content that could be explored as being more optimal matches.
1. A method comprising: selecting an instance of first content and an instance of second content, wherein the instance of first content and the instance of second content are configured to be delivered to client devices; determining a plurality of first labels for a plurality of categories for the instance of first content, wherein the plurality of first labels are based on an analysis of content of the instance of first content; determining a plurality of second labels for the plurality of categories for the instance of second content, wherein the plurality of second labels are based on an analysis of content of the instance of second content; comparing the plurality of first labels and the plurality of second labels to determine a plurality of scores for the plurality of first labels, wherein the plurality of scores is based on parameters of a matching tool that is configured to determine a match between instances of content; using a weight of a category to adjust a score in the plurality of scores to generate an adjusted score, wherein the adjusted score is for the label that is determined for the category; outputting information for the adjusted score and scores in the plurality of scores; receiving feedback from delivering the instance of first content that is inserted into a break of the instance of second content, and using the feedback to adjust a parameter of the matching tool, wherein the parameter is used to determine scores for the plurality of categories. ||
17. A non-transitory computer-readable storage medium having stored thereon computer executable instructions, which when executed by a computing device, cause the computing device to be operable for: selecting an instance of first content and an instance of second content, wherein the instance of first content and the instance of second content are configured to be delivered to client devices; determining a plurality of first labels for a plurality of categories for the instance of first content, wherein the plurality of first labels are based on an analysis of content of the instance of first content; determining a plurality of second labels for the plurality of categories for the instance of second content, wherein the plurality of second labels are based on an analysis of content of the instance of second content; comparing the plurality of first labels and the plurality of second labels to determine a plurality of scores for the plurality of first labels, wherein the plurality of scores is based on parameters of a matching tool that is configured to determine a match between instances of content; using a weight of a category to adjust a score in the plurality of scores to generate an adjusted score, wherein the adjusted score is for the label that is determined for the category; outputting information for the adjusted score and scores in the plurality of scores; receiving feedback from delivering the instance of first content that is inserted into a break of the instance of second content; and using the feedback to adjust a parameter of the matching tool, wherein the parameter is used to determine scores for the plurality of categories. ||
19. An apparatus comprising: one or more computer processors; and a computer-readable storage medium comprising instructions for controlling the one or more computer processors to be operable for: selecting an instance of first content and an instance of second content, wherein the instance of first content and the instance of second content are configured to be delivered to client devices; determining a plurality of first labels for a plurality of categories for the instance of first content, wherein the plurality of first labels are based on an analysis of content of the instance of first content; determining a plurality of second labels for the plurality of categories for the instance of second content, wherein the plurality of second labels are based on an analysis of content of the instance of second content; comparing the plurality of first labels and the plurality of second labels to determine a plurality of scores for the plurality of first labels, wherein the plurality of scores is based on parameters of a matching tool that is configured to determine a match between instances of content; using a weight of a category to adjust a score in the plurality of scores to generate an adjusted score, wherein the adjusted score is for the label that is determined for the category; outputting information for the adjusted score and scores in the plurality of scores; receiving feedback from delivering the instance of first content that is inserted into a break of the instance of second content; and using the feedback to adjust a parameter of the matching tool, wherein the parameter is used to determine scores for the plurality of categories.