# US 2021/0081998 A1 · Automated product health risk assessment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0081998 A1 - Document ID: US20210081998A1 - Status: Published application - Kind: A1 - Application number: 16/568,697 - Filed: 2019-09-12 - Published: 2021-03-18 - Earliest claimed: 2019-09-12 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Carlos Andres Martinez Vazquez; Emmanuel Barajas Gonzalez; Irving Yukio Hayashi Leon; Mara Miranda Bautista - Web page: https://patentgrep.com/patent/US20210081998A1 ## CPC - G06Q 30/0271: {Personalized advertisement} - G06Q 30/0267: {Wireless devices} - G06Q 30/0627: {by specifying product or service characteristics, e.g. product dimensions} - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 40/67: for remote operation - G16H 50/30: for calculating health indices; for individual health risk assessment - G16H 70/40: relating to drugs, e.g. their side effects or intended usage - 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 - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A computer-implemented method comprises analyzing an advertisement presented to a user during a first time period to identify a plurality of ingredients; and analyzing documents related to a medical condition of the user to determine a respective first relevance rank for each ingredient. The method further comprises selecting a subset of the ingredients having a highest number of occurrences based on the respective first relevance rank for each of the ingredients; performing sentiment analysis of the documents for the selected subset; determining a respective second relevance rank for each of the ingredients in the selected subset based on the sentiment analysis; and computing a product risk score based on the respective second relevance rank for each of the ingredients in the subset. The method further comprises modifying a display on a device associated with the user such that the display indicates the product risk score during the first time period. ## Claims ### Claim 1 A computer-implemented method for product risk assessment, the method comprising: analyzing an advertisement presented to a user during a first time period to identify a plurality of ingredients in a product in the advertisement; analyzing one or more documents related to a medical condition of the user to determine a respective first relevance rank for each of the plurality of ingredients based, at least in part, on a number of occurrences of each ingredient in the one or more documents; selecting a subset of the plurality of ingredients having a highest number of occurrences based on the respective first relevance rank for each of the plurality of ingredients; performing sentiment analysis of the one or more documents for the selected subset of the plurality of ingredients having the highest number of occurrences; determining a respective second relevance rank for each of the ingredients in the selected subset of the plurality of ingredients based on the sentiment analysis; computing a product risk score for the product based on the respective second relevance rank for each of the ingredients in the subset of the plurality of ingredients, the product risk score indicating a risk for effects of the product on the medical condition of the user; and modifying a display on a device associated with the user such that the display indicates the product risk score for the product during the first time period in which the advertisement is presented to the user. ### Claim 2 (depends on 1) The method of claim 1, wherein the advertisement is presented to the user on a first device and wherein modifying the display on the device associated with the user comprises modifying a display on a second device different from the first device. ### Claim 3 (depends on 2) The method of claim 2, further comprising capturing, via one or more sensors, audio and images of the advertisement presented to the user on the first device, the one or more sensors located near the first device. ### Claim 4 (depends on 1) The method of claim 1, wherein modifying the display on the device associated with the user comprises overlaying a notification indicating the product risk score on top of at least a portion of the advertisement which is presented to the user on the display of the device associated with the user. ### Claim 5 (depends on 1) The method of claim 1, wherein analyzing the one or more documents related to the user's medical condition to determine a respective first relevance rank for each of the plurality of ingredients comprises performing term frequency-inverse document frequency analysis on the one or more documents for the plurality of ingredients. ### Claim 6 (depends on 1) The method of claim 1, further comprising determining a quantity of each of the plurality of ingredients in the product; and wherein computing the product risk score for the product further comprises computing the product risk score based on the determined quantity of each of the plurality of ingredients in the product. ### Claim 7 (depends on 5) The method of claim 5, wherein analyzing the advertisement presented to the user during the first time period to identify the plurality of ingredients in the product in the advertisement comprises: performing image analysis to identify a barcode of the product; identifying the product in a product database based on the identified barcode; and obtaining the plurality of ingredients and quantity of each of the ingredients in the product from the product database. ### Claim 8 An apparatus comprising: a display; a network interface; and a processor communicatively coupled with the display and the network interface, the processor configured to: analyze an advertisement presented to a user during a first time period to identify a plurality of ingredients in a product in the advertisement; retrieve, from one or more databases via the network interface, one or more documents related to a medical condition of a user viewing the advertisement; analyze the one or more documents to determine a respective relevance of each of the plurality of ingredients to the product based, at least in part, on a respective number of occurrences of each ingredient in the one or more documents; select a subset of the plurality of ingredients having a highest number of occurrences in the one or more documents; update the respective relevance of each ingredient in the subset of plurality of ingredients based on sentiment analysis of the one or more documents for the selected subset of the plurality of ingredients having the highest number of occurrences; compute a product risk score for the product based on the updated respective relevance for each of the ingredients in the subset of the plurality of ingredients, the product risk score indicating a risk for effects of the product on the medical condition of the user; and output instructions to the display to display information indicating the product risk score for the product during the first time period in which the advertisement is presented to the user. ### Claim 9 (depends on 8) The apparatus of claim 8, further comprising: one or more sensors configured to capture audio and images of the advertisement presented to the user on a separate device ### Claim 10 (depends on 8) The apparatus of claim 8, wherein the display is configured to display the advertisement presented to the user during the first time period. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein the processor is configured to output instructions to the display to overlay a notification indicating the product risk score on top of at least a portion of the advertisement which is presented to the user on the display. ### Claim 12 (depends on 8) The apparatus of claim 8, wherein the processor is configured to perform term frequency-inverse document frequency analysis on the one or more documents for the plurality of ingredients to determine the respective relevance of each of the plurality of ingredients to the product. ### Claim 13 (depends on 8) The apparatus of claim 8, wherein the processor is further configured to: determine a quantity of each of the plurality of ingredients in the product; and compute the product risk score for the product based on the determined quantity of each of the plurality of ingredients in the product. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein the processor is further configured to: perform image analysis on the advertisement to identify a barcode of the product; identify the product in a product database based on the identified barcode, the product database coupled to the processor via the network interface; and obtain the plurality of ingredients and quantity of each of the ingredients in the product from the product database. ### Claim 15 A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed by a processor, causes the processor to: analyze an advertisement presented to a user during a first time period to identify a plurality of ingredients in a product in the advertisement; retrieve, from one or more databases, one or more documents related to a medical condition of a user viewing the advertisement; analyze the one or more documents to determine a respective relevance of each of the plurality of ingredients to the product based, at least in part, on a respective number of occurrences of each ingredient in the one or more documents; select a subset of the plurality of ingredients having a highest number of occurrences in the one or more documents; update the respective relevance of each ingredient in the subset of plurality of ingredients based on sentiment analysis of the one or more documents for the selected subset of the plurality of ingredients having the highest number of occurrences; compute a product risk score for the product based on the updated respective relevance for each of the ingredients in the subset of the plurality of ingredients, the product risk score indicating a risk for effects of the product on the medical condition of the user; and output instructions to a display to display information indicating the product risk score for the product during the first time period in which the advertisement is presented to the user. ### Claim 16 (depends on 15) The computer program product of claim 15, wherein the program instructions are further configured to cause the processor to analyze audio and images of the advertisement captured by one or more sensors located near a first device configured to present the advertisement to the user and to output instructions to a display on a second device different from the first device to display the information indicating the product risk score for the product during the first time period. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the program instructions are further configured to cause the processor to output instructions to the display to overlay a notification indicating the product risk score on top of at least a portion of the advertisement which is presented to the user on the display. ### Claim 18 (depends on 15) The computer program product of claim 15, wherein the program instructions are further configured to cause the processor to perform term frequency-inverse document frequency analysis on the one or more documents for the plurality of ingredients to determine the respective relevance of each of the plurality of ingredients to the product. ### Claim 19 (depends on 15) The computer program product of claim 15, wherein the program instructions are further configured to cause the processor to: determine a quantity of each of the plurality of ingredients in the product; and compute the product risk score for the product based on the determined quantity of each of the plurality of ingredients in the product. ### Claim 20 (depends on 15) The computer program product of claim 15, wherein the program instructions are further configured to cause the processor to: perform image analysis on the advertisement to identify a barcode of the product; identify the product in a product database based on the identified barcode; and obtain the plurality of ingredients and quantity of each of the ingredients in the product from the product database.