Social proximity networks for mobile phones

• US 10,015,770 B2
• Filed: 03/24/2014
• Issued: 07/03/2018
• Est. Priority Date: 03/24/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Ekambaram, Vijay, Joshi, Vikas, Nandakumar, Vikrant, Narayanam, Ramasuri
• Primary Examiner(s): Bibbee, Jared M
• Application Number:
  US14/223,499
• Publication Number:
  US 20150269267A1
• Time in Patent Office: 1,562 Days
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04W 64/003 locating network equipment

Abstract

Methods and arrangements for rendering social proximity networks for mobile phones. A contemplated method includes: obtaining communication data for a mobile phone; deriving from the communication data a social proximity score with respect to at least one individual associated with at least one device that has communicated with the mobile phone; and storing the social proximity score. Other variants and embodiments are broadly contemplated herein.

Claims

1. A method of rendering social proximity networks for mobile phones, said method comprising:

utilizing at least one processor to execute computer code configured to perform the steps of;

initiating obtaining of communication data for a mobile phone of a user in response to a call conversation between the user and at least one mobile phone contact, wherein the communication data comprises a speech signal of the call conversation and supplementary information comprising a duration of the call conversation and a social networking relationship status of the user and the at least one mobile phone contact;

said obtaining comprising mining text data from the speech signal of the call conversation and categorizing the call conversation into a sentiment category;

deriving from the communication data and the social networking relationship status, a social proximity score for the at least one mobile phone contact that has communicated with the mobile phone;

the social proximity score being based at least in part on sentiment analysis of one or more words of the communication data and the sentiment category of the call conversation and the social proximity score identifying a closeness a relationship of the at least one mobile phone contact to a user of the mobile phone;

storing the social proximity score;

dynamically creating a proximity graph that depicts relationship health between the user and the at least one mobile phone contact based on a metric comprising a quantitative relationship health index and a mood of the user at a time of the call conversation, said metric being derived from the duration of the call conversation, wherein the proximity graph includes a label for each of the relationships depicted in the proximity graph, wherein the label is derived from at least one of the social networking relationship and historical categorized call conversations; and

issuing a prompt from the mobile phone, based on the proximity score and the quantitative relationship health index, the prompt containing at least one of;

a reminder to contact the at least one mobile phone contact and a recommended activity other than a reminder to contact the at least one mobile device contact.

2. The method according to claim 1, wherein the at least one mobile phone contact comprises at least two mobile phone contacts.

3. The method according to claim 1, wherein said obtaining comprises analyzing non-social media content of a text message.

4. The method according to claim 3, wherein said analyzing comprises performing sentiment analysis on the text message.

5. The method according to claim 1, wherein said obtaining comprises entering data into a call data record.

6. The method according to claim 5, wherein said deriving comprises obtaining historical data with respect to non-social media content of at least one of:

the call conversation and a text message.

7. The method according to claim 6, wherein said analyzing comprises performing sentiment analysis on the non-social media content of at least one of:

the call and the text message.

8. The method according to claim 7, wherein said deriving comprises deriving a social proximity score as a function of the sentiment analysis data, data from the call data record, and the historical data.

9. The method according to claim 1, wherein said deriving comprises obtaining historical data with respect to non-social media content of at least one of:

the call conversation and a text message.

10. The method according to claim 1, comprising displaying the social proximity score.

11. The method according to claim 1, comprising plotting the social proximity score with respect to the at least one mobile phone contact on the proximity graph.

12. The method according to claim 10, comprising dynamically updating the proximity graph.

20. The method according to claim 1, wherein the prompt is designed to improve the social proximity score.

13. An apparatus for rendering social proximity networks for mobile phones, said apparatus comprising:

at least one processor; and

a computer readable storage medium having computer readable program code embodied therewith and executable by the at least one processor, the computer readable program code comprising;

computer readable program code configured to initiate obtaining of communication data for a mobile phone of a user in response to a call conversation between the user and at least one mobile phone contact, wherein the communication data comprises a speech signal of the call conversation and supplementary information comprising a duration of the call conversation and a social networking relationship status of the user and the at least one mobile phone contact;

said obtaining comprising mining text data from the speech signal of the call conversation and categorizing the call conversation into a sentiment category;

computer readable program code configured to derive from the communication data and the social networking relationship status a social proximity score for the at least one mobile phone contact that has communicated with the mobile phone;

the social proximity score being based at least in part on sentiment analysis of one or more words of the communication data and the sentiment category of the call conversation and the social proximity score identifying a closeness a relationship of the at least one mobile phone contact to a user of the mobile phone;

computer readable program code configured to store the social proximity score;

computer readable program code configured to dynamically create a proximity graph that depicts relationship health between the user and the at least one mobile phone contact based on a metric comprising a quantitative relationship health index and a mood of the user at a time of the call conversation, said metric being derived from the duration of the call conversation, wherein the proximity graph includes a label for each of the relationships depicted in the proximity graph, wherein the label is derived from at least one of the social networking relationship and historical categorized call conversations; and

computer readable program code configured to issue a prompt from the apparatus, based on the proximity score and the quantitative relationship health index, the prompt containing at least one of;

a reminder to contact the at least one mobile phone contact and recommended activity other than a reminder to contact the at least one mobile device contact.

14. A computer program product for rendering social proximity networks for mobile phones, said computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code comprising;

computer readable program code configured to initiate obtaining of communication data for a mobile phone of a user in response to a call conversation between the user and at least one mobile phone contact, wherein the communication data comprises a speech signal of the call conversation and supplementary information comprising a duration of the call conversation and a social networking relationship status of the user and the at least one mobile phone contact;

said obtaining comprising mining text data from the speech signal of the call conversation and categorizing the call conversation into a sentiment category;

computer readable program code configured to derive from the communication data and the social networking relationship status a social proximity score for the at least one mobile phone contact that has communicated with the mobile phone;

the social proximity score being based at least in part on sentiment analysis of one or more words of the communication data and the sentiment category of the call conversation and the social proximity score identifying a closeness a relationship of the at least one mobile phone contact to a user of the mobile phone;

computer readable program code configured to store the social proximity score;

computer readable program code configured to dynamically create a proximity graph that depicts relationship health between the user and the at least one mobile phone contact based on a metric comprising a quantitative relationship health index and a mood of the user at a time of the call conversation, said metric being derived from the duration of the call conversation, wherein the proximity graph includes a label for each of the relationships depicted in the proximity graph, wherein the label is derived from at least one of the social networking relationship and historical categorized call conversations; and

computer readable program code configured to issue a prompt from the apparatus, based on the proximity score, the prompt containing at least one of;

a reminder to contact the at least one mobile phone contact and recommended activity other than a reminder to contact the at least one mobile device contact.

15. The computer program product according to claim 14, wherein the at least one mobile phone contact comprises at least two mobile phone contacts.

16. The computer program product according to claim 14, wherein said computer readable program code is configured to analyze non-social media content of a text message.

17. The computer program product according to claim 16, wherein said computer readable program code is configured to perform sentiment analysis on the text message.

18. The computer program product according to claim 14, wherein said computer readable program code is configured to plot the social proximity score with respect to the at least one mobile phone contact on a proximity graph.

19. A method comprising:

initiating obtaining of communication data for a mobile phone of a user in response to a call conversation between the user and at least one mobile phone contact, the communication data including sentiment analysis data and data from a call data record comprising a duration of the call conversation and a social networking relationship status of the user and the at least one mobile phone contact;

said obtaining comprising obtaining at least part of the communication data from the speech signal of the call conversation, mining text data from the speech signal and categorizing the call conversations into a sentiment category;

deriving from the communication data and the social networking relationship status, a social proximity score for mobile phone contacts as a function of at least the sentiment analysis data and the data from the call data record;

the social proximity score being based at least in part on sentiment analysis of one or more words of the communication data and the sentiment category of the call conversation and the social proximity score identifying a closeness a relationship of the at least one mobile phone contact to a user of the mobile phone;

creating a proximity graph based on the social proximity score with respect to each of the at least two individuals, said proximity graph depicting relationship health based on a metric comprising a quantitative relationship health index and a mood of the user at a time of the call conversation, said metric being derived from a duration of the call conversation, wherein the proximity graph includes a label for each of the relationships depicted in the proximity graph, wherein the label is derived from at least one of the social networking relationship and historical categorized call conversations; and

issuing a prompt from the mobile phone, based on the proximity graph, the prompt containing at least one of;

a reminder to contact at least one mobile phone contact and a recommended activity other than a reminder to contact at least one mobile device contact.