# US 2021/0241310 A1 · Intelligent advertisement campaign effectiveness and impact evaluation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0241310 A1 - Document ID: US20210241310A1 - Status: Published application - Kind: A1 - Application number: 16/777,216 - Filed: 2020-01-30 - Published: 2021-08-05 - Earliest claimed: 2020-01-30 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Joao H BETTENCOURT-SILVIA; Stefano BRAGHIN; Michalis PACHILAKIS - Web page: https://patentgrep.com/patent/US20210241310A1 ## CPC - G06Q 30/0246: {Traffic} - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06Q 30/0251: Targeted advertisements - 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 - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Embodiments for implementing intelligent advertisement effectiveness and impact evaluation in a computing environment by a processor. A degree of impact and a degree of distribution of one or more communication campaigns upon a targeted entity may be identified according to a user persona, one or more communication rules, security factors, or a combination thereof. ## Claims ### Claim 1 A method, by a processor, for implementing intelligent advertisement effectiveness and impact evaluation in computing environment, comprising: monitoring user access patterns as a user accesses various webpages over a selected period of time, wherein the user access patterns are inclusive of advertisements accepted and rejected by the user while accessing the various webpages; training a machine learning component according to the user access patterns, wherein the training includes teaching the machine learning component to identify specific types of those of the advertisements accepted and rejected by the user using reinforced feedback learning; creating a user persona for the user based on the user access patterns, wherein the user persona includes a persona profile having characteristic and demographic information of the user; simulating the user persona by an automated web crawler, using the trained machine learning component, to reproduce the user access patterns of accessing the various webpages while automatically monitoring one or more communication campaigns promoted to the user persona during the accessing; and identifying a degree of impact and a degree of distribution of the one or more communication campaigns upon a targeted entity according to the user persona, one or more communication rules, security factors, or a combination thereof. ### Claim 2 (depends on 1) The method of claim 1, further including determining, as the degree of distribution, a number of times the one or more communication campaigns were delivered to the targeted entity according to one or more selected domains. ### Claim 3 (depends on 1) The method of claim 1, further including: monitoring and evaluating the one or more communication campaigns according to the one or more communication rules and security factors, wherein the one or more communication rules and security factors used to detect security breaches and inference attempts upon the one or more communication campaigns. ### Claim 4 (depends on 1) The method of claim 1, further including extracting one or more topics, sentiments, or a combination thereof based on the one or more communication campaigns. ### Claim 5 (depends on 1) The method of claim 1, wherein the user persona includes a description of a user obtained from a list of uniform resource locators (URLs), a frequency and probability of the user visiting one or more of a URLs from the list of the URLs, a list of interests relating to the user, activities and behaviors of the user associated with the list of the URLs, or a combination thereof. ### Claim 6 (depends on 1) The method of claim 1, further including: classifying the one or more communication campaigns as the advertisements or non-advertisements; and identifying an intent or type of the one or more communication campaigns. ### Claim 7 (depends on 1) The method of claim 1, wherein training the machine learning component further includes initializing a machine learning operation to: discern the one or more communication campaigns as an advertisement; learn or extract topics, semantics, categories, intent, or a combination thereof of the one or more communication campaigns; and identify a degree of polarity of the one or more communication campaigns in relation to the user persona. ### Claim 8 A system for implementing intelligent advertisement effectiveness and impact evaluation in a computing environment, comprising: one or more computers with executable instructions that when executed cause the system to: monitor user access patterns as a user accesses various webpages over a selected period of time, wherein the user access patterns are inclusive of advertisements accepted and rejected by the user while accessing the various webpages; train a machine learning component according to the user access patterns, wherein the training includes teaching the machine learning component to identify specific types of those of the advertisements accepted and rejected by the user using reinforced feedback learning; create a user persona for the user based on the user access patterns, wherein the user persona includes a persona profile having characteristic and demographic information of the user; simulate the user persona by an automated web crawler, using the trained machine learning component, to reproduce the user access patterns of accessing the various webpages while automatically monitoring one or more communication campaigns promoted to the user persona during the accessing; and identify a degree of impact and a degree of distribution of the one or more communication campaigns upon a targeted entity according to the user persona, one or more communication rules, security factors, or a combination thereof. ### Claim 9 (depends on 8) The system of claim 8, wherein the executable instructions further determine, as the degree of distribution, a number of times the one or more communication campaigns were delivered to the targeted entity according to one or more selected domains. ### Claim 10 (depends on 8) The system of claim 8, wherein the executable instructions further: monitor and evaluate the one or more communication campaigns according to the one or more communication rules and security factors, wherein the one or more communication rules and security factors used to detect security breaches and inference attempts upon the one or more communication campaigns. ### Claim 11 (depends on 8) The system of claim 8, wherein the executable instructions further extract one or more topics, sentiments, or a combination thereof based on the one or more communication campaigns. ### Claim 12 (depends on 8) The system of claim 8, wherein the user persona includes a description of a user obtained from a list of uniform resource locators (URLs), a frequency and probability of the user visiting one or more of a URLs from the list of the URLs, a list of interests relating to the user, activities and behaviors of the user associated with the list of the URLs, or a combination thereof. ### Claim 13 (depends on 8) The system of claim 8, wherein the executable instructions further: classifying the one or more communication campaigns as the advertisements or non-advertisements; and identify an intent or type of the one or more communication campaigns. ### Claim 14 (depends on 8) The system of claim 8, wherein wherein training the machine learning component further includes initializing a machine learning operation to: discern the one or more communication campaigns as an advertisement; learn or extract topics, semantics, categories, intent, or a combination thereof of the one or more communication campaigns; and identify a degree of polarity of the one or more communication campaigns in relation to the user persona. ### Claim 15 A computer program product for implementing intelligent advertisement effectiveness and impact evaluation in a computing environment by a processor, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising: an executable portion that monitors user access patterns as a user accesses various webpages over a selected period of time, wherein the user access patterns are inclusive of advertisements accepted and rejected by the user while accessing the various webpages; an executable portion that trains a machine learning component according to the user access patterns, wherein the training includes teaching the machine learning component to identify specific types of those of the advertisements accepted and rejected by the user using reinforced feedback learning; an executable portion that creates a user persona for the user based on the user access patterns, wherein the user persona includes a persona profile having characteristic and demographic information of the user; an executable portion that simulates the user persona by an automated web crawler, using the trained machine learning component, to reproduce the user access patterns of accessing the various webpages while automatically monitoring one or more communication campaigns promoted to the user persona during the accessing; and an executable portion that identifies a degree of impact and a degree of distribution of the one or more communication campaigns upon a targeted entity according to the user persona, one or more communication rules, security factors, or a combination thereof. ### Claim 16 (depends on 15) The computer program product of claim 15, further including an executable portion that determines, as the degree of distribution, a number of times the one or more communication campaigns were delivered to the targeted entity according to one or more selected domains. ### Claim 17 (depends on 15) The computer program product of claim 15, further including an executable portion that: monitors and evaluates the one or more communication campaigns according to the one or more communication rules and security factors, wherein the one or more communication rules and security factors used to detect security breaches and inference attempts upon the one or more communication campaigns. ### Claim 18 (depends on 15) The computer program product of claim 15, further including an executable portion that extracts one or more topics, sentiments, or a combination thereof based on the one or more communication campaigns. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the user persona includes a description of a user obtained from a list of uniform resource locators (URLs), a frequency and probability of the user visiting one or more of a URLs from the list of the URLs, a list of interests relating to the user, activities and behaviors of the user associated with the list of the URLs, or a combination thereof; and further including an executable portion that: classifies the one or more communication campaigns as the advertisements or non-advertisements; or identifies an intent or type of the one or more communication campaigns. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein training the machine learning component further includes initializing a machine learning operation to: discern the one or more communication campaigns as an advertisement; learn or extract topics, semantics, categories, intent, or a combination thereof of the one or more communication campaigns; and identify a degree of polarity of the one or more communication campaigns in relation to the user persona.