# US 2019/0102395 A1 · Personalizing search and/or recommendation results based on member activity models

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

- Number: US 2019/0102395 A1
- Document ID: US20190102395A1
- Status: Published application
- Kind: A1
- Application number: 15/721,420
- Filed: 2017-09-29
- Published: 2019-04-04
- Earliest claimed: 2017-09-29
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Sanjay Kshetramade
- Web page: https://patentgrep.com/patent/US20190102395A1

## CPC

- G06F 16/9535: Search customisation based on user profiles and personalisation
- G06F 16/24578: {using ranking}
- G06F 16/248: Presentation of query results
- G06Q 10/42: Determination of affinities or common interests between users
- G06Q 30/0631: {Recommending goods or services}
- 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

Methods, systems, and computer programs are presented for analyzing profiles and building profile models that can be used to personalize search results for a member on a social network. In example embodiments, a system aggregates data about members on the social network including member profile data, customer relation data, and member communication data. The system further extracts attribute values from the aggregated data and maps the attribute values onto attribute vectors on a social data map. Based on the mapping, the system determines a model member profile for the member. The system further generates candidate attribute vectors for search results from a search for the member and determines a similarity score between the model member profile and each candidate attribute vector. The system further ranks the search results based on the similarity score and presents a ranked display of the search results to the user.

## Claims

### Claim 1

A computer-implemented method using at least one computer processor, the method comprising:
aggregating member data about members on a social network, the member data including attribute values that represent historical activity by the members of the social network and relationships between members;
mapping a first plurality of attribute values related to a first member onto a social data map, the social data map including attribute vectors that are matchable to the attribute values;
generating a model search result from the mapping of the first plurality of attribute values, the model search result including model attribute vectors and representing a model search result for a first member;
receiving, from a client system, a search request for a first member;
transmitting the search request to a search system;
retrieving a ranked list of candidate search results from the search system, the ranking based on a relevance of the search results to the first member;
generating a candidate attribute vector for each candidate search result;
re-ranking the list of search results based on similarity scores between the candidate search results and the model search result; and
sending the re-ranked search results to the client system for display.

### Claim 2 (depends on 1)

The method of claim 1, wherein the ranked list of candidate search results is a ranked list of member profiles representing prospective members for the first member to contact.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
comparing the attribute values to a threshold attribute value, wherein only attribute values that exceed the threshold attribute value are included in the model member profile.

### Claim 4 (depends on 1)

The method of claim 1, wherein the member data includes customer relation data that comprises information about historical transactions between members on the social network.

### Claim 5 (depends on 1)

The method of claim 1, wherein the member data includes profile data that comprises data added to member profiles by the members, such as by inputting data or uploading data.

### Claim 6 (depends on 1)

The method of claim 1, wherein the member data includes interactions between members on the social network such as interactions between the first member and other members.

### Claim 7 (depends on 6)

The method of claim 6, wherein interactions with other members of the social networking system include the first member saving a member profile of another member of the social networking system.

### Claim 8 (depends on 6)

The method of claim 6, wherein interactions between members on the social network include the first member sending or receiving a communication from another member of the social networking system.

### Claim 9 (depends on 6)

The method of claim 6, wherein interactions with other members of the social networking system include the first member making a sales connection with another member of the social networking system.

### Claim 10 (depends on 1)

The method of claim 1, wherein a similarity score is calculated based on a similarity value between the model search result and a candidate search result, the similarity value determined by a machine-learning program.

### Claim 11

A system comprising
at least one processor of a machine; and
a memory storing instructions that, when executed by the at least one processor, cause the machine to perform operations comprising:
aggregating member data about members on a social network, the member data including attribute values that represent historical activity by the members of the social network and relationships between members;
mapping a first plurality of attribute values related to a first member onto a social data map, the social data map including attribute vectors that are matchable to the attribute values;
generating a model search result from the mapping of the first plurality of attribute values, the model search result including model attribute vectors and representing a model search result for a first member;
receiving, from a client system, a search request for a first member;
transmitting the search request to a search system;
retrieving a ranked list of candidate search results from the search system, the ranking based on a relevance of the search results to the first member;
generating a candidate attribute vector for each candidate search result;
re-ranking the list of search results based on similarity scores between the candidate search results and the model search result; and
sending the re-ranked search results to the client system for display.

### Claim 12 (depends on 11)

The system of claim 11, wherein the ranked list of candidate search results is a ranked list of member profiles representing prospective members for the first member to contact.

### Claim 13 (depends on 11)

The system of claim 11, wherein operations further comprise:
comparing the attribute values to a threshold attribute value, wherein only attribute values that exceed the threshold attribute value are included in the model member profile.

### Claim 14 (depends on 11)

The system of claim 11, wherein the member data includes customer relation data that comprises information about historical transactions between members on the social network.

### Claim 15 (depends on 11)

The system of claim 11, wherein the member data includes profile data that comprises data added to member profiles by the members, such as by inputting data or uploading data.

### Claim 16 (depends on 11)

The system of claim 11, wherein the member data includes interactions between members on the social network such as interactions between the first member and other members.

### Claim 17 (depends on 16)

The system of claim 16, wherein interactions with other members of the social networking system include the first member saving a member profile of another member of the social networking system.

### Claim 18 (depends on 16)

The system of claim 16, wherein interactions between members on the social network include the first member sending or receiving a communication from another member of the social networking system.

### Claim 19 (depends on 11)

The system of claim 11, wherein a similarity score is calculated based on a similarity value between the model search result and a candidate search result, the similarity value determined by a machine-learning program.

### Claim 20

A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
aggregating member data about members on a social network, the member data including attribute values that represent historical activity by the members of the social network and relationships between members;
mapping a first plurality of attribute values related to a first member onto a social data map, the social data map including attribute vectors that are matchable to the attribute values;
generating a model search result from the mapping of the first plurality of attribute values, the model search result including model attribute vectors and representing a model search result for a first member;
receiving, from a client system, a search request for a first member;
transmitting the search request to a search system;
retrieving a ranked list of candidate search results from the search system, the ranking based on a relevance of the search results to the first member;
generating a candidate attribute vector for each candidate search result;
re-ranking the list of search results based on similarity scores between the candidate search results and the model search result; and
sending the re-ranked search results to the client system for display.
