# US 11,113,738 B2 · Presenting endorsements using analytics and insights

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

- Number: US 11,113,738 B2
- Document ID: US11113738B2
- Status: Granted
- Kind: B2
- Application number: 15/711,884
- Filed: 2017-09-21
- Published: 2018-03-29
- Granted: 2021-09-07
- Earliest claimed: 2016-09-29
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Maria Iu; Joey Bai; Jie Zhang; Richard Ramirez; Victor Louis Kabdebon; Hari Srinivasan; Yo-Tzu Yeh
- Web page: https://patentgrep.com/patent/US11113738B2

## CPC

- G06Q 30/0613: {using intermediate agents}
- G06F 16/24578: {using ranking}
- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/9536: Search customisation based on social or collaborative filtering
- G06Q 10/063112: {Skill-based matching of a person or a group to a task}
- G06Q 10/06395: {Quality analysis or management}
- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06Q 10/1053: Employment or hiring
- G06Q 10/46: Determination of level of influence of users within social networking services
- H04L 67/306: User profiles
- 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)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Techniques for presenting a featured skill of a first member of a social network system are described. An example system presents the featured skill on a profile page of the first member. The system can receive a request to view the profile page from a device of a second member. Additionally, profile data of the first and second members can be accessed, the profile data including skills associated with the first member. An endorser value can be determined for the first member based on a reputation score, the endorser value being associated with the first member having a specific skill. Moreover, a quality score for each skill in the skills can be calculated using the endorser value and the profile data. Furthermore, the featured skill can be selected based on the quality score. Subsequently, a user interface can present the featured skill on the profile page of the first member.

## Claims

### Claim 1

A computer system comprising:
a processor;
a storage device;
a memory device holding an instruction set executable by the processor to cause the computer system to perform operations comprising:
training a machine learned model using a machine learning algorithm, wherein the training includes calculating a plurality of coefficients using an optimization function;
responsive to receiving, via a computing device of a first member of a social networking service, a request to view a member profile of a second member of the social networking service:
accessing member profile data of the second member to identify a set of skills, each skill in the set of skills a skill for which the second member has received an endorsement from one or more endorsers;
deriving an endorsement quality score for each endorsement of a skill in the set of skills by the one or more endorsers, the endorsement quality score for each endorsement derived as a combination of sub-scores including an endorser value based on characteristics of the endorser and a recipient value based on characteristics of the second member, the combination calculated by passing one or more features of the endorser and one or more features of the second member to the trained machine learned model and applying the calculated coefficients to the subscores;
selecting from the set of skills a particular skill, shared in common between the first member profile and the second member profile, according to member profiles of the first member and the second member, and associated with an endorsement having an endorsement quality score that exceeds a predetermined threshold;
presenting in a user interface, via the computing device of the first member of the social networking service, the member profile of the second member and member information identifying the particular skill and the endorser associated with the endorsement of the particular skill; and
retraining the machine learning model based on input received from the first member in response to the presenting.

### Claim 2 (depends on 1)

The computer system of claim 1, further comprising:
for each endorsement of a skill in the set of skills by the one or more endorsers, deriving an endorsement value for the endorser associated with the endorsement of the skill as a weighted combination of characteristics of the endorser including the number of other endorsements of the skill made by the endorser for other members of the social networking service, and the number of endorsements of the skill received by the endorser from other members of the social networking service.

### Claim 3 (depends on 1)

The computer system of claim 1, further comprising:
for each endorsement of a skill in the set of skills by the one or more endorsers, deriving an endorsement value for the endorser associated with the endorsement as a weighted combination of characteristics of the endorser, the characteristics of the endorser selected from the set of characteristics consisting of: number of endorsements made by the endorser; the number of endorsements received by the endorser; the number of skills possessed by the endorser, according to a member profile of the endorser; the number of years the endorser has been employed, according to a member profile of the endorser; the number of direct connections the endorser has with other members of the social networking service; and, the number of endorsements per direct connection for those direct connections the endorser has with other members of the social networking service.

### Claim 4 (depends on 1)

The computer system of claim 1, further comprising:
for each skill in the set of skills, deriving for the second member a recipient value as a weighted combination of characteristics of the second member, the characteristics of the second member including the number of endorsements given by the second member to other members of the social networking service for the skill, and the number of endorsements received by the second member from other members of the social networking service for the skill.

### Claim 5 (depends on 4)

The computer system of claim 4, wherein the endorser value, the recipient value and the overlap value are computed and stored in a database prior to receiving the request to view the member profile of the second member; and,
subsequent to receiving the request to view the member profile of the second member, the endorser value, the recipient value and the overlap value are obtained from the database.

### Claim 6 (depends on 1)

The computer system of claim 1, further comprising:
for each skill in the set of skills, deriving for the second member a recipient value as a weighted combination of characteristics of the second member, the characteristics of the second member selected from the set of characteristics consisting of: the number of endorsements of other members of the social networking service given by the second member; the number of endorsements received by the second member from other members of the social networking service; the number of skills possessed by the second member, according to a member profile of the second member; the number of years the second member has been employed, according to a member profile of the second member; the number of direct connections the endorser has with other members of the social networking service; and, the number of endorsements per direct connection for those direct connections the endorser has with other members of the social networking service.

### Claim 7 (depends on 1)

The computer system of claim 1, further comprising:
for each endorser associated with an endorsement, deriving an overlap value based on characteristics shared in common between the endorser and the second member, the characteristics shared in common selected from the set of characteristics consisting of: employment with a common employer; employment with an employer or employers in a common industry; attendance at or matriculation from a common educational institution; academic degrees with a common major or common discipline of study; and, geographical location of residence;
wherein the endorsement quality score for each endorsement is derived as a combination of sub-scores including the endorser value, the recipient value, and the overlap value.

### Claim 8 (depends on 1)

The computer system of claim 1, further comprising:
presenting in the user interface, via the computing device of the first member of the social networking service, the member profile of the second member and member information identifying a plurality of skills for which the second member has been endorsed by other members of the social networking service, wherein the particular skill is designated as a featured skill in the plurality of skills as a result of an endorser associated with the endorsement for the particular skill having the endorsement quality score that exceeds the predetermined threshold.

### Claim 9 (depends on 1)

The computer system of claim 1, further comprising:
presenting in the user interface, via the computing device of the first member of the social networking service, the member profile of the second member and including with the member profile of the second member information identifying the particular skill, the endorser associated with the endorsement having the endorsement quality score that exceeds the predetermined threshold, and the number of endorsers who have endorsed the second member for the particular skill.

### Claim 10 (depends on 1)

The computer system of claim 1, further comprising:
presenting in the user interface, via the computing device of the first member of the social networking service, a prompt requesting the first member to endorse the second member as possessing the particular skill.

### Claim 11

A computer-implemented method comprising:
responsive to receiving, via a computing device of a first member of a social networking service, a request to view a member profile of a second member of the social networking service:
training a machine learned model using a machine learning algorithm, wherein the training includes calculating a plurality of coefficients using an optimization function;
accessing member profile data of the second member to identify a set of skills, each skill in the set of skills a skill for which the second member has received an endorsement from one or more endorsers;
deriving an endorsement quality score for each endorsement of a skill in the set of skills by the one or more endorsers, the endorsement quality score for each endorsement derived as a combination of sub-scores including an endorser value based on characteristics of the endorser and a recipient value based on characteristics of the second member, the combination calculated by passing one or more features of the endorser and one or more features of the second member to the trained machine learned model and applying the calculated coefficients to the subscores;
selecting from the set of skills a particular skill, shared in common between the first member profile and the second member profile, according to member profiles of the first member and the second member, and associated with an endorsement having an endorsement quality score that exceeds a predetermined threshold;
presenting in a user interface, via the computing device of the first member of the social networking service, the member profile of the second member and information identifying i) the particular skill, and ii) the endorser associated with the endorsement of the particular skill; and retraining the machine learning model based on input received from the first member in response to the presenting.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11, further comprising:
for each endorsement of a skill in the set of skills by the one or more endorsers, deriving an endorsement value for the endorser associated with the endorsement of the skill as a weighted combination of characteristics of the endorser including the number of other endorsements of the skill made by the endorser for other members of the social networking service, and the number of endorsements of the skill received by the endorser from other members of the social networking service.

### Claim 13 (depends on 11)

The computer-implemented method of claim 11, further comprising:
for each endorsement of a skill in the set of skills by the one or more endorsers, deriving an endorsement value for the endorser associated with the endorsement as a weighted combination of characteristics of the endorser, the characteristics of the endorser selected from the set of characteristics consisting of: number of endorsements made by the endorser; the number of endorsements received by the endorser; the number of skills possessed by the endorser, according to a member profile of the endorser; the number of years the endorser has been employed, according to a member profile of the endorser; the number of direct connections the endorser has with other members of the social networking service; and, the number of endorsements per direct connection for those direct connections the endorser has with other members of the social networking service.

### Claim 14 (depends on 11)

The computer-implemented method of claim 11, further comprising:
for each skill in the set of skills, deriving for the second member a recipient value as a weighted combination of characteristics of the second member, the characteristics of the second member including the number of endorsements given by the second member to other members of the social networking service for the skill, and the number of endorsements received by the second member from other members of the social networking service for the skill.

### Claim 15 (depends on 11)

The computer-implemented method of claim 11, further comprising:
for each skill in the set of skills, deriving for the second member a recipient value as a weighted combination of characteristics of the second member, the characteristics of the second member selected from the set of characteristics consisting of: the number of endorsements of other members of the social networking service given by the second member; the number of endorsements received by the second member from other members of the social networking service; the number of skills possessed by the second member, according to a member profile of the second member; the number of years the second member has been employed, according to a member profile of the second member; the number of direct connections the endorser has with other members of the social networking service; and, the number of endorsements per direct connection for those direct connections the endorser has with other members of the social networking service.

### Claim 16 (depends on 11)

The computer-implemented method of claim 11, further comprising:
for each endorser associated with an endorsement, deriving an overlap value based on characteristics shared in common between the endorser and the second member, the characteristics shared in common selected from the set of characteristics consisting of: employment with a common employer; employment with an employer or employers in a common industry; attendance at or matriculation from a common educational institution; academic degrees with a common major or common discipline of study; and, geographical location of residence;
wherein the endorsement quality score for each endorsement is derived as a combination of sub-scores including the endorser value, the recipient value, and the overlap value.

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, wherein the endorser value, the recipient value and the overlap value are computed and stored in a database prior to receiving the request to view the member profile of the second member; and,
subsequent to receiving the request to view the member profile of the second member, the endorser value, the recipient value and the overlap value are obtained from the database.

### Claim 18 (depends on 11)

The computer-implemented method of claim 11, further comprising:
presenting in the user interface, via the computing device of the first member of the social networking service, the member profile of the second member and information identifying a plurality of skills for which the second member has been endorsed by other members of the social networking service, wherein the particular skill is designated as a featured skill in the plurality of skills as a result of an endorser associated with the endorsement for the particular skill having the endorsement quality score that exceeds the predetermined threshold.

### Claim 19 (depends on 11)

The computer-implemented method of claim 11, further comprising:
presenting in the user interface, via the computing device of the first member of the social networking service, the member profile of the second member and information identifying the particular skill, the endorser associated with the endorsement having the endorsement quality score that exceeds the predetermined threshold, and the number of endorsers who have endorsed the second member for the particular skill.

### Claim 20 (depends on 11)

The computer-implemented method of claim 11, further comprising:
multiplying the endorser value by a first of the plurality of coefficients and the recipient value by a second of the plurality of coefficients.