# US 2021/0281925 A1 · Dynamic viewer prediction system for advertisement scheduling > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0281925 A1 - Document ID: US20210281925A1 - Status: Published application - Kind: A1 - Application number: 17/252,420 - Filed: 2018-07-05 - Published: 2021-09-09 - Earliest claimed: 2018-07-05 - Assignees: Telefonaktiebolaget LM Ericsson (publ) - Applicants: Telefonaktiebolaget Lm Ericsson (Publ) - Inventors: Junaid SHAIKH; Farnaz MORADI; Valentin KULYK - Web page: https://patentgrep.com/patent/US20210281925A1 ## CPC - G06Q 30/0243: {Comparative campaigns} - H04N 21/812: {involving advertisement data (advertising per se G06Q30/02)} - H04N 21/44213: {Monitoring of end-user related data (arrangements for monitoring the users' behaviour or opinions in broadcast systems H04H60/33)} - H04N 21/458: Scheduling content for creating a personalised stream, e.g. by combining a locally stored advertisement with an incoming stream; Updating operations, e.g. for OS modules {; time-related management operations (arrangements for replacing or switching information during the broadcast or during the distribution H04H20/10)} - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION ## Abstract Systems and methods are provided for generating a predicted number of viewers in support of selecting an advertisement to be displayed during an advertisement break. The method includes: generating, by an advertisement break class identifier module, a plurality of advertisement break classes based on historical advertisement break information and prediction errors generated by a regression model analysis of advertisement break data samples; evaluating, by the advertisement break class identifier module, the plurality of advertisement break classes; redefining and rearranging, by the advertisement break class identifier module, advertisement break classes from the plurality of advertisement break classes based on the step of evaluating which results in an updated set of advertisement break classes; forwarding, by the advertisement break class identifier module, the updated set of advertisement break classes and trained model information to a prediction module; receiving, modifying and returning prediction model information to the prediction module by a training function in the advertisement break class identifier module; generating, by the prediction module, the prediction of a number of viewers for the advertisement break, wherein a regression model uses the updated set of advertisement break classes and data associated with a specific advertisement break to generate the prediction; and sending, by the prediction module, the prediction of a number of viewers for the advertisement break to a scheduler of advertisements. ## Claims ### Claim 1 A method for generating a predicted number of viewers in support of selecting an advertisement to be displayed during an advertisement break, the method comprising: generating, by an advertisement break class identifier module, a plurality of advertisement break classes based on historical advertisement break information and prediction errors generated by a regression model analysis of advertisement break data samples; evaluating, by the advertisement break class identifier module, the plurality of advertisement break classes; redefining and rearranging, by the advertisement break class identifier module, advertisement break classes from the plurality of advertisement break classes based on the step of evaluating which results in an updated set of advertisement break classes; forwarding, by the advertisement break class identifier module, the updated set of advertisement break classes and trained model information to a prediction module; receiving, modifying and returning prediction model information to the prediction module by a training function in the advertisement break class identifier module; generating, by the prediction module, the prediction of a number of viewers for the advertisement break, wherein a regression model uses the updated set of advertisement break classes and data associated with a specific advertisement break to generate the prediction; and sending, by the prediction module, the prediction of a number of viewers for the advertisement break to a scheduler of advertisements. ### Claim 2 (depends on 1) The method of claim 1, wherein the steps performed by the advertisement break class identifier module are continuously iterated. ### Claim 3 (depends on 1) The method of claim 1, wherein the historical advertisement break information includes at least one of a time period of historical viewer ratings, competitor historical ratings, weather information, program meta data for programs airing before and after the historical advertisement break and information from program content database ratings. ### Claim 4 (depends on 1) The method of claim 1, wherein the advertisement break data samples include advertisement break start and stop times, unique title of advertisement break, name of television channel displaying the advertisement break, population of an advertisement target group, names and metadata features of television programs displayed before and after the advertisement break, weather forecast metrics, ratings of programs displayed before and after from a program content database, a number of viewers of the programs displayed before and after the advertisement break and name and metadata of programs displayed in competitor channels during the advertisement break. ### Claim 5 (depends on 1) The method of claim 1, wherein the advertisement break classes are based on one or more advertisement classification features, further wherein the one or more advertisement classification features include television channel, population target group, prime time, non-prime time, season and level of popularity. ### Claim 6 (depends on 1) The method of claim 1, wherein the step of evaluating the plurality of advertisement break classes generates model evaluation metrics that include a difference between an actual number of viewers and a predicted number of viewers, an absolute percentage error, a weighted absolute percentage error and a square error. ### Claim 7 (depends on 1) The method of claim 1, being performed by one or more servers distributed in a cloud architecture. ### Claim 8 (depends on 1) The method of claim 1, being performed by one or more servers located in a network of a content provider. ### Claim 9 (depends on 1) The method of claim 1, further comprising: displaying the selected advertisement on at least one of a television and a user equipment (UE). ### Claim 10 (depends on 1) The method of claim 1, further comprising: applying different advertisement break classes to different advertisement time slots; and applying different advertisement break classes to different broadcasted television content types. ### Claim 11 (canceled) ### Claim 12 (depends on 22) The apparatus of claim 22, wherein the steps performed by the processor to perform advertisement break classes are continuously iterated. ### Claim 13 (depends on 22) The apparatus of claim 22, wherein the historical advertisement break information includes at least one of a time period of historical viewer ratings, competitor historical ratings, weather information, program meta data for programs airing before and after the historical advertisement break and program content database ratings. ### Claim 14 (depends on 22) The apparatus of claim 22, wherein the advertisement break data samples include advertisement break start and stop times, unique title of advertisement break, name of television channel displaying the advertisement break, population of an advertisement target group, names and metadata features of television programs displayed before and after the advertisement break, weather forecast metrics, ratings of programs displayed before and after from a program content database, and a number of viewers of the programs displayed before and after the advertisement break. ### Claim 15 (depends on 22) The apparatus of claim 22, wherein the advertisement break classes are based on one or more advertisement classification features, further wherein the one or more advertisement classification features include television channel, population target group, prime time, non-prime time, season and level of popularity. ### Claim 16 (depends on 22) The apparatus of claim 22, wherein the processor is configured to evaluate the plurality of advertisement break classes and generates model evaluation metrics which include a difference between an actual number of viewers and a predicted number of viewers, an absolute percentage error, a weighted absolute percentage error and a square error. ### Claim 17 (depends on 22) The apparatus of claim 22, wherein the processor is one or more processors located on one or more servers distributed in a cloud architecture. ### Claim 18 (depends on 22) The apparatus of claim 22, wherein the processor is one or more processors located on one or more servers located in a network of a content provider. ### Claim 19 (depends on 22) The apparatus of claim 22, wherein the selected advertisement is displayed on one of a television or a user equipment (UE). ### Claim 20 (depends on 22) The system of claim 22, wherein different advertisement break classes are applied to different advertisement time slots and further wherein different advertisement break classes are applied to different broadcasted television content types. ### Claim 21 (canceled) ### Claim 22 An apparatus including a processor adapted to generate a plurality of advertisement break classes based on historical advertisement break information and prediction errors generated by a regression model analysis of advertisement break data samples; evaluate the plurality of advertisement break classes; redefine and rearrange advertisement break classes from the plurality of advertisement break classes based on the step of evaluating which results in an updated set of advertisement break classes; forward the updated advertisement break classes and trained model information to a prediction model; receive, modify and return prediction model information to the prediction module; generate the prediction of a number of viewers for the advertisement break, wherein a regression model uses the updated advertisement break classes and data associated with a specific advertisement break to generate the prediction; and send the prediction of a number of viewers for the advertisement break to a scheduler of advertisements. ### Claim at position 23 23-25. (canceled)