# US 2020/0004885 A1 · Risk-based comprehension intervention for important documents

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2020/0004885 A1
- Document ID: US20200004885A1
- Status: Published application
- Kind: A1
- Application number: 16/021,541
- Filed: 2018-06-28
- Published: 2020-01-02
- Earliest claimed: 2018-06-28
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Paul R. BASTIDE; Alexandra URMAN; Fang LU
- Web page: https://patentgrep.com/patent/US20200004885A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06Q 30/0201: Market modelling; Market analysis; Collecting market data
- G06F 16/24578: {using ranking}
- G06F 16/248: Presentation of query results
- G06F 16/93: Document management systems
- G06F 16/9538: Presentation of query results
- G06F 40/103: Formatting, i.e. changing of presentation of documents (automatic justification G06F40/189; automatic line break hyphenation G06F40/191)
- G06F 40/30: Semantic analysis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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

## Abstract

In providing visual cues in a document, a server captures search term(s) input by a user and detects a user selection of a document returned based on the search term(s). The server determines a dataset describing the user, where the dataset includes the search term(s), the document, and a set of demographic data of the user. The server maps the dataset to a user group, where the user group is associated with an expertise level for a domain associated with the document. The server assigns the expertise level associated with the user group to the user and maps the expertise level of a risk model for the domain. The risk model is applied to the document to identify the content segments that may pose a risk of harm to a reader with the user's expertise level. The document with the visual cues can then be displayed to the user.

## Claims

### Claim 1

A method for providing visual cues in a document by a server, comprising:
capturing, by the server, a set of one or more search terms input by a user;
detecting, by the server, a user selection of a document of a plurality of documents returned based on the set of one or more search terms;
determining, by the server, a dataset describing the user, the dataset comprising the set of one or more search terms, the selected document, and a set of demographic data of the user;
mapping, by the server, the dataset to a given user group of a plurality of user groups, the given user group being associated with an expertise level for a domain associated with the selected document;
assigning, by the server, the expertise level associated with the given user group to the user;
mapping, by the server, the expertise level of a given risk model for the domain of a plurality of risk models; and
applying, by the server, one or more visual cues to one or more content segments of the selected document based on the given risk model.

### Claim 2 (depends on 1)

The method of claim 1, wherein the mapping of the dataset to the given user group comprises:
determining, by the server, the domain associated with the selected document;
comparing, by the server, the dataset with parameters for one or more of the plurality of user groups, wherein each of the plurality of user groups is associated with a level of expertise in the domain;
calculating, by the server, a similarity score based on the comparing with the given user group of the plurality of user groups; and
when the similarity score exceeds a similarity score threshold, assigning, by the server, the level of expertise associated with the given user group to the user.

### Claim 3 (depends on 1)

The method of claim 1, wherein the assigning of the expertise level of the given user group to the user comprises:
comparing, by the server, the set of one or more search terms with a plurality of terms in an ontology database, wherein each term in the ontology database is associated with a set of domains, wherein each domain in the set is associated with a second expertise level;
when the set of one or more search terms matches a given term in the ontology database, comparing, by the server, the domain associated with the selected document with the set of domains associated with the given term; and
adjusting, by the server, the expertise level assigned to the user according to the second expertise level associated with the matching domain.

### Claim 4 (depends on 1)

The method of claim 1, wherein the dataset further comprises a referral source, wherein the assigning of the expertise level of the given user group to the user comprises:
comparing, by the server, the referral source with a plurality of referral sources in a referral source database, wherein each referral source in the referral source database is associated with a set of domains, wherein each domain in the set is associated with a second expertise level;
when the referral source matches a given referral source in the referral source database, comparing, by the server, the domain associated with the selected document with the set of domains associated with the given referral source; and
adjusting, by the server, the expertise level assigned to the user according to the label associated with the matching domain.

### Claim 5 (depends on 1)

The method of claim 1, wherein the risk model captures words, phrases, or concepts in the domain in which a lack of understanding that may pose a risk of harm to a reader, wherein the mapping of the expertise level to the given risk model for the domain comprises:
identifying, by the server, one or more content segments of the selected document that would pose the risk of harm to the reader with the expertise level assigned to the user using the risk model; and
applying, by the server, a visual cue to each content segment identified.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
tracking, by the server, the user's interaction with the selected document;
measuring, by the server, a dwell time of the user on a given content segment of the selected document;
when the dwell time exceeds a threshold dwell time, adjusting lower, by the server, the expertise level assigned to the user.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
calculating, by the server, an overall risk of understanding score representing an overall level of risk of harm to a reader with the expertise level assigned to the user with lack of understanding of the one or more content segments in the selected document; and
applying, by the server, a visual cue displaying the overall risk of understanding score to the selected document.

### Claim 8

A computer program product for providing visual cues in a document, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
capture a set of one or more search terms input by a user;
detect a user selection of a document of a plurality of documents returned based on the set of one or more search terms;
determine a dataset describing the user, the dataset comprising the set of one or more search terms, the selected document, and a set of demographic data of the user;
map the dataset to a given user group of a plurality of user groups, the given user group being associated with an expertise level for a domain associated with the selected document;
assign the expertise level associated with the given user group to the user;
map the expertise level of a given risk model for the domain of a plurality of risk models for the domain; and
apply one or more visual cues to one or more content segments of the selected document based on the given risk model.

### Claim 9 (depends on 8)

The computer program product of claim 8, wherein the mapping of the dataset to the given user group comprises:
determine the domain associated with the selected document;
compare the dataset with parameters for one or more of the plurality of user groups, wherein each of the plurality of user groups is associated with a level of expertise in the domain;
calculate a similarity score based on the comparing with the given user group of the plurality of user groups; and
when the similarity score exceeds a similarity score threshold, assign the level of expertise associated with the given user group to the user.

### Claim 10 (depends on 8)

The computer program product of claim 8, wherein the assigning of the expertise level of the given user group to the user comprises:
compare the set of one or more search terms with a plurality of terms in an ontology database, wherein each term in the ontology database is associated with a set of domains, wherein each domain in the set is associated with a second expertise level;
when the set of one or more search terms matches a given term in the ontology database, compare the domain associated with the selected document with the set of domains associated with the given term; and
adjust the expertise level assigned to the user according to the second expertise level associated with the matching domain.

### Claim 11 (depends on 8)

The computer program product of claim 8, wherein the dataset further comprises a referral source, wherein the assigning of the expertise level of the given user group to the user comprises:
compare the referral source with a plurality of referral sources in a referral source database, wherein each referral source in the referral source database is associated with a set of domains, wherein each domain in the set is associated with a second expertise level;
when the referral source matches a given referral source in the referral source database, compare the domain associated with the selected document with the set of domains associated with the given referral source; and
adjust the expertise level assigned to the user according to the label associated with the matching domain.

### Claim 12 (depends on 8)

The computer program product of claim 8, wherein the risk model captures words, phrases, or concepts in the domain in which a lack of understanding that may pose a risk of harm to a reader, wherein the mapping of the expertise level to the given risk model for the domain comprises:
identify one or more content segments of the selected document that would pose the risk of harm to the reader with the expertise level assigned to the user using the risk model; and
apply a visual cue to each content segment identified.

### Claim 13 (depends on 8)

The computer program product of claim 8, further comprising:
track the user's interaction with the selected document;
measure a dwell time of the user on a given content segment of the selected document;
when the dwell time exceeds a threshold dwell time, adjust lower the expertise level assigned to the user.

### Claim 14 (depends on 8)

The computer program product of claim 8, further comprising:
calculate an overall risk of understanding score representing an overall level of risk of harm to a reader with the expertise level assigned to the user with lack of understanding of the one or more content segments in the selected document; and
apply a visual cue displaying the overall risk of understanding score to the selected document.

### Claim 15

A system comprising:
a processor; and
a computer readable storage medium having program instructions embodied therewith, the program instructions executable by the processor to cause the processor to:
capture a set of one or more search terms input by a user;
detect a user selection of a document of a plurality of documents returned based on the set of one or more search terms;
determine a dataset describing the user, the dataset comprising the set of one or more search terms, the selected document, and a set of demographic data of the user;
map the dataset to a given user group of a plurality of user groups, the given user group being associated with an expertise level for a domain associated with the selected document;
assign the expertise level associated with the given user group to the user;
map the expertise level of a given risk model for the domain of a plurality of risk models for the domain; and
apply one or more visual cues to one or more content segments of the selected document based on the given risk model.

### Claim 16 (depends on 15)

The system of claim 15, wherein the mapping of the dataset to the given user group comprises:
determine the domain associated with the selected document;
compare the dataset with parameters for one or more of the plurality of user groups, wherein each of the plurality of user groups is associated with a level of expertise in the domain;
calculate a similarity score based on the comparing with the given user group of the plurality of user groups; and
when the similarity score exceeds a similarity score threshold, assign the level of expertise associated with the given user group to the user.

### Claim 17 (depends on 15)

The system of claim 15, wherein the assigning of the expertise level of the given user group to the user comprises:
compare the set of one or more search terms with a plurality of terms in an ontology database, wherein each term in the ontology database is associated with a set of domains, wherein each domain in the set is associated with a second expertise level;
when the set of one or more search terms matches a given term in the ontology database, compare the domain associated with the selected document with the set of domains associated with the given term; and
adjust the expertise level assigned to the user according to the second expertise level associated with the matching domain.

### Claim 18 (depends on 15)

The system of claim 15, wherein the dataset further comprises a referral source, wherein the assigning of the expertise level of the given user group to the user comprises:
compare the referral source with a plurality of referral sources in a referral source database, wherein each referral source in the referral source database is associated with a set of domains, wherein each domain in the set is associated with a second expertise level;
when the referral source matches a given referral source in the referral source database, compare the domain associated with the selected document with the set of domains associated with the given referral source; and
adjust the expertise level assigned to the user according to the label associated with the matching domain.

### Claim 19 (depends on 15)

The system of claim 15, wherein the risk model captures words, phrases, or concepts in the domain in which a lack of understanding that may pose a risk of harm to a reader, wherein the mapping of the expertise level to the given risk model for the domain comprises:
identify one or more content segments of the selected document that would pose the risk of harm to the reader with the expertise level assigned to the user using the risk model; and
apply a visual cue to each content segment identified.

### Claim 20 (depends on 15)

The system of claim 15, further comprising:
track the user's interaction with the selected document;
measure a dwell time of the user on a given content segment of the selected document;
when the dwell time exceeds a threshold dwell time, adjust lower the expertise level assigned to the user.
