# US 2021/0241309 A1 · Predicting Outcomes Via Marketing Asset Analytics > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241309 A1 - Document ID: US20210241309A1 - Status: Published application - Kind: A1 - Application number: 17/167,178 - Filed: 2021-02-04 - Published: 2021-08-05 - Earliest claimed: 2020-02-04 - Assignees: The Rocket Science Group LLC - Applicants: The Rocket Science Group LLC - Inventors: John J. Wolf, JR. - Web page: https://patentgrep.com/patent/US20210241309A1 ## CPC - G06Q 30/0244: {Optimization} - G06F 9/541: {via adapters, e.g. between incompatible applications} - G06F 40/131: Fragmentation of text files, e.g. creating reusable text-blocks; Linking to fragments, e.g. using XInclude; Namespaces - G06F 40/137: Hierarchical processing, e.g. outlines - G06F 40/216: using statistical methods - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/30: Semantic analysis - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 5/027: {Frames} - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06Q 10/40: Business processes related to social networking or social networking services - G06Q 30/0204: Market segmentation - G06F 40/205: Parsing - G10L 15/26: Speech to text systems (G10L15/08 takes precedence) - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING ## Abstract Systems and methods for predicting an outcome for a marketing asset. The systems and methods comprise first determining by a computing device, for a marketing asset received by the computing device, at least one asset type of the marketing asset. The marketing asset is parsed, by the computing device, into a plurality of segmented components, based on the determined at least one asset type. For at least one of the plurality of segmented components, at least one discrete marketing message conveyed by the marketing asset is determined, by applying at least one of a predictive model or rules to the at least one segmented component, where the at least one predictive model or rules are stored in a memory associated with the computing device. The method further includes determining, for each of the at least one discrete marketing message, at least one associated score. The method yet further includes inputting the determined at least one associated score to a trained predictive model to obtain a predicted marketing outcome, where the trained predictive model was trained using training scores associated with a multitude of training discrete marketing messages as independent variables and corresponding training marketing outcome data as dependent variables. ## Claims ### Claim 1 A method for predicting an outcome for a marketing asset, comprising: determining by a computing device, for a marketing asset received by the computing device, at least one asset type of the marketing asset; parsing, by the computing device, the marketing asset into a plurality of segmented components, based on the determined at least one asset type; determining, for at least one of the plurality of segmented components, at least one discrete marketing message by applying at least one of a predictive model or rules to the at least one segmented component, wherein the at least one predictive model or rules are stored in a memory associated with the computing device; determining, for each of the at least one discrete marketing message, at least one associated score; and inputting the determined at least one associated score to a trained predictive model to obtain a predicted marketing outcome, wherein the trained predictive model was trained using training scores associated with a multitude of training discrete marketing messages as independent variables and corresponding training marketing outcome data as dependent variables, and wherein the trained predictive model is stored in the memory associated with the computing device. ### Claim 2 (depends on 1) The method of claim 1, further comprising providing via a graphical interface, an output related to the predicted marketing outcome. ### Claim 3 (depends on 1) The method of claim 1, further comprising storing, in the memory associated with the computing device, data relating to the predicted marketing outcome. ### Claim 4 (depends on 1) The method of claim 1, wherein the at least one associated score is based on at least one of the following: (a) how many times a particular discrete marketing message is communicated in the marketing asset or (b) where, in the marketing asset, the particular discrete marketing message is located. ### Claim 5 (depends on 1) The method of claim 1, wherein the plurality of segmented components comprises at least one of the following: text, image, audio, or video. ### Claim 6 (depends on 5) The method of claim 5, wherein, if one of the plurality of segmented components comprises audio, the method further comprises transcribing the audio into text. ### Claim 7 (depends on 5) The method of claim 5, wherein, if one of the plurality of segmented components comprises video, the method further comprises: splitting the video component into a plurality of image components and an audio component; and transcribing the audio component. ### Claim 8 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes a web page: crawling the web page; identifying html code in the web page; storing the identified html code in the memory associated with the computing device; and parsing the stored identified html code by identifying at least one html tag, wherein the at least one html tag identifies at least one of an image, headline text, sub-headline text, paragraph text, video, or other component. ### Claim 9 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes a social media post, using an Application Program Interface (API) for a social media app associated with the social media post to parse the social media post into at least one of image, text, audio, or video. ### Claim 10 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes a portable document format (pdf) file, using a pdf parser to parse the social media post into at least one of image, text, audio, or video. ### Claim 11 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes a web-based word-processing application file, using an Application Program Interface (API) to parse the web-based word-processing application file into at least one of image, text, audio, or video. ### Claim 12 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes a plain-text email, parsing a text block in the plain-text email. ### Claim 13 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes an html email, identifying at least one html tag in the html email, wherein the at least one html tag identifies at least one of an image, headline text, sub-headline text, paragraph text, video, or other component. ### Claim 14 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes a video: segmenting the video into temporal blocks; parsing each temporal block into audio and images; and transcribing the audio for each temporal block into text, wherein the transcribing includes using an audio transcription service. ### Claim 15 (depends on 1) The method of claim 1, wherein parsing the marketing asset into the plurality of segmented components comprises, if the marketing asset includes an audio sales call: segmenting the audio sales call into temporal blocks each having audio; transcribing the audio for each temporal block into text, wherein the transcribing includes using an audio transcription service. ### Claim 16 (depends on 1) The method of claim 1, wherein determining the at least one discrete marketing message comprises applying natural-language rules to the at least one segmented component of the marketing asset to determine at least one of a word root or syntax pattern, and wherein the natural-language rules are stored in the memory associated with the computing device. ### Claim 17 (depends on 1) The method of claim 1, wherein the at least one discrete marketing message is from a discrete marketing message category selected from the following: value propositions, statements of differentiation, product experiences, product features, brand archetypes, brand promises, brand visions, brand missions, brand positionings, brand purposes, brand values, brand reputations, brand archetypes, calls to action, audience demographics, audience pastimes, audience habitats, audience values, audience personality traits, audience lifestyles, or audience professions. ### Claim 18 (depends on 1) The method of claim 1, wherein determining the at least one discrete marketing message comprises accessing at least one industry-specific dictionary for at least one segmented component of the marketing asset, and wherein the at least one industry-specific dictionary is stored in the memory associated with the computing device. ### Claim 19 (depends on 1) The method of claim 1, wherein the predicted marketing outcome is selected from the group consisting of a predicted engagement score, a web page bounce rate, a clickthrough rate, an occurrence of a sale, an occurrence of an engagement, or a specified conversion rate. ### Claim 20 (depends on 1) The method of claim 1, further comprising: determining a subset of discrete marketing messages, wherein the subset comprises only those determined discrete marketing messages having more than a threshold correlation to an associated marketing outcome; and providing a recommendation associated with the predicted marketing outcome, wherein the recommendation relates to the determined subset of discrete marketing messages. ### Claim 21 A system for predicting an outcome for a marketing asset, comprising: at least one computing device to perform tasks comprising: determining, for a marketing asset, at least one asset type of the marketing asset; parsing the marketing asset into a plurality of segmented components, based on the determined at least one asset type; determining, for at least one of the plurality of segmented components, at least one discrete marketing message conveyed by the marketing asset, wherein the determining includes applying at least one of a predictive model or rules to the at least one segmented component; determining, for each of the at least one discrete marketing message, at least one associated score; and inputting the determined at least one associated score to a trained predictive model to obtain a predicted marketing outcome, wherein the trained predictive model was trained using training scores associated with a multitude of training discrete marketing messages as independent variables and corresponding training marketing outcome data as dependent variables. ### Claim 22 (depends on 21) The system of claim 21, wherein the tasks performed by the at least one computing device further comprise providing via a graphical interface, an output related to the predicted marketing outcome. ### Claim 23 (depends on 21) The system of claim 21, wherein the at least one associated score is based on at least one of the following: (a) how many times a particular discrete marketing message is communicated in the marketing asset or (b) where, in the marketing asset, the particular discrete marketing message is located. ### Claim 24 (depends on 21) The system of claim 21, wherein the plurality of segmented components comprises at least one of the following: text, image, audio, or video. ### Claim 25 An article of manufacture including a non-transitory computer-readable medium, having stored thereon program instructions that, upon execution by one or more processors, cause the one or more processors to perform tasks comprising: determining, for a marketing asset, at least one asset type of the marketing asset; parsing the marketing asset into a plurality of segmented components, based on the determined at least one asset type; determining, for at least one of the plurality of segmented components, at least one discrete marketing message conveyed by the marketing asset, wherein the determining includes applying at least one of a predictive model or rules to the at least one segmented component; determining, for each of the at least one discrete marketing message, at least one associated score; and inputting the determined at least one score to a trained predictive model to obtain a predicted marketing outcome, wherein the trained predictive model was trained using training scores associated with a multitude of training discrete marketing messages as independent variables and corresponding training marketing outcome data as dependent variables. ### Claim 26 (depends on 25) The article of manufacture of claim 25, wherein the tasks performed by the one or more processors further comprise providing via a graphical interface, an output related to the predicted marketing outcome. ### Claim 27 (depends on 25) The article of manufacture of claim 25, wherein the at least one associated score is based on at least one of the following: (a) how many times a particular discrete marketing message is communicated in the marketing asset or (b) where, in the marketing asset, the particular discrete marketing message is located. ### Claim 28 (depends on 25) The article of manufacture of claim 25, wherein the plurality of segmented components comprises at least one of the following: text, image, audio, or video.