US20230325943A1 - Interaction recommendation engine - Google Patents
Interaction recommendation engine Download PDFInfo
- Publication number
- US20230325943A1 US20230325943A1 US17/978,711 US202217978711A US2023325943A1 US 20230325943 A1 US20230325943 A1 US 20230325943A1 US 202217978711 A US202217978711 A US 202217978711A US 2023325943 A1 US2023325943 A1 US 2023325943A1
- Authority
- US
- United States
- Prior art keywords
- user
- interaction
- profile
- event
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000003993 interaction Effects 0.000 title claims abstract description 184
- 238000000034 method Methods 0.000 claims abstract description 59
- 230000007613 environmental effect Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 description 27
- 230000006399 behavior Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 230000003997 social interaction Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
Definitions
- communication plays a vital role in either developing the relationship or degrading the relationship.
- the communication between two individuals or a group of individuals can be positive and developing if the communication involves such topics in which the individuals or the group of individuals are interested.
- the communication between the individual may be non-interactive if the communication involves topics which are not of mutual interest.
- the system provides a method and apparatus for generating a profile of a first user, where the profile comprises interaction parameters associated with the user.
- the system can generate a profile of a second user, also comprising interaction parameters of the second user.
- the system can then provide suggestions to either or both the first and second user for interacting with each other.
- FIG. 1 illustrates a network environment implementing an interaction recommendation system, in accordance with an example implementation of the present subject matter
- FIG. 2 illustrates an interaction recommendation system, in accordance with an example implementation of the present subject matter
- FIG. 3 illustrates an architecture for a system which retrieves data form databases, according to an example of the present subject matter
- FIG. 4 shows a graph form of a stored data according to an example of the present subject matter
- FIG. 5 illustrates a method 500 for providing suggestions for an interaction, according to an example of the present subject matter.
- FIG. 6 illustrates another method 600 for providing suggestions for an interaction, in accordance with an example of the present subject matter.
- FIG. 7 illustrates yet another method 700 for providing suggestions for an interaction, according to an example of the present subject matter.
- FIG. 8 illustrates yet another method 800 for providing suggestions for an interaction, in accordance with an example of the present subject matter.
- a relationship between two individuals depends on the various factors, such as their interests, behavior, nature, and attitude. It is sometime difficult for a user to decide how he should interact with other user for an efficient and fruitful communication. For example, it is difficult for the individuals to decide a topic of discussion, a place of meeting, choice of food, etc. Similarly, it maybe sometimes difficult for parents to efficiently communicate with their teenage children such that the communication is engaging and interactive. Therefore, various factors are to be considered during any interaction between individuals. Wrong choices of such parameters may lead to unsuccessful meetings and inefficient communication between the individuals. For example, during a first date, it may be difficult for two individuals to decide a topic of discussion or a mutual point of interest.
- an interaction recommendation system determines various profile parameters, along with different interaction parameters corresponding to an individual.
- the profile parameters may indicate the behavior, likes and dislikes of an individual, while the interaction parameters may indicate different interactional aspects associated with the individual.
- the profile parameters may be based on the phycology, sociology, and environmental factors of the user.
- the interaction recommendation system based on the determination of the profile parameters and interaction parameters, may suggest actions/recommendations to the individuals for interaction.
- a digital coach implemented by the system may use various behavioral factors included in the profile parameters, such as personality type, body type, body built, favorite genre of movies, type of music, hobbies, favorite cuisine and restaurants, favorite places, environmental condition, political favorites, favorite sports etc., to suggest various interaction possibilities to an individual. Further, the digital coach may also use past interaction experience, such as events attended by the individual, status on social media platforms, frequency of meeting with other individuals, past experience of interactions, etc., to suggest various interaction possibilities to the individual.
- the interaction recommendation system may analyze the profile parameters of the two individuals along with the interaction parameters associated with the two individuals.
- the interaction recommendation system may, based on the assessment of the profile parameters and the interaction parameters, generate an interaction profile for each of the two individuals.
- the interaction recommendation system provides suggestions, such as topic of discussion, place of meetings, etc., to both of the individuals.
- the detail such as the interaction profile, the interaction parameters. All the calculations, processing, data analysis happens at the database by backend servers.
- a plurality of micro software services allows parallel execution and processing of the data.
- the data is processed using graphical processor unit (GPU) processors at these databases which are significantly faster than the central processing units of the user’s mobile device. Also, as the processing is done at backend servers, the battery power of the user’s device is saved.
- the mobile phone and tablet are equipped with 99% ARM processors.
- the backend servers are equipped with x86 processors (Intel or advanced micro devices (AMD)) and GPU (Nvidia or AMD). According to the set of benchmarks, the ARM architecture is about 8 times less efficient than the x86 architecture when it comes to complex calculation.
- FIG. 1 shows an interaction recommendation system 102 implementing a recommendation module 104 to provide suggestions to a user 110 , according to an example implementation of the present subject matter.
- the interaction recommendation system 102 may be coupled with a plurality of databases, such as database 106 - 1 , 106 - 2 , ..., 106 - n , via a network 108 .
- the network 108 may be a single network or a combination of multiple networks and may use a variety of different communication protocols.
- the network 108 may be a wireless or a wired network, or a combination thereof. Examples of such individual networks include, but are not limited to, Global System for Mobile Communication (GSM) network, Universal Mobile Telecommunications System (UMTS) network, Personal Communications Service (PCS) network, Time Division Multiple Access (TDMA) network, Code Division Multiple Access (CDMA) network, Next Generation Network (NON), and Public Switched Telephone Network (PSTN).
- GSM Global System for Mobile Communication
- UMTS Universal Mobile Telecommunications System
- PCS Personal Communications Service
- TDMA Time Division Multiple Access
- CDMA Code Division Multiple Access
- NON Next Generation Network
- PSTN Public Switched Telephone Network
- the communication network 108 includes various network entities, such as gateways, routers; however, such details have been omitted for the sake of brevity of the present description.
- the interaction recommendation system 102 may be implemented as any of a variety of conventional computing devices, including, a mobile phone, a tablet, a pager, desktop, and a laptop. Further, the databases 106 - 1 , 106 - 2 , ....,106-n may be a hierarchical database, a network database, an object-oriented database, a relational database etc.
- the interaction recommendation system 102 may determine profile parameters for the user 110 .
- the profile parameters may be likes, dislikes, personal choices, hobbies of the user 110 .
- the profile parameters may also be based on phycological, sociological, and environmental factors of the user 110 .
- the profile parameters based on phycological factors may be, introvert nature, extrovert nature etc.
- the profile parameters based sociological factors may be social status of the user 110 or the income level of the user 110 .
- the interaction recommendation system 102 determines interaction parameters associated with the user 110 .
- the interaction parameters may be based on the interactional habits of the user 110 , such as events in which the user may be interested in, frequency of meeting with other users etc.
- the interaction recommendation system 102 may generate interaction profile for the user 110 . Further, based on the interaction profile, a recommendation module 104 of the interaction recommendation system 102 provides suggestions to the user 100 for interaction with the other user. In an example, the suggestions may be place of meeting with other users, topic of discussion, restaurant to visit etc.
- a user 110 of the interaction recommendation system 102 may add a second user (not shown) with which the user 110 desires to have a communication.
- the user 110 may add the second user from an address book stored on the user’s device, a social media account of the user 110 , email of the user 110 and alike.
- the interaction recommendation system 102 may determine profile parameters for the second user.
- the profile parameters may be likes, dislikes, personal choices, hobbies of the second user. Further, the profile parameters may also be based on psychological, sociological, and environmental factors of the second user. Further, the interaction recommendation system 102 determines interaction parameters for second user. Based on the profile parameters and the interaction parameters, the interaction recommendation system 102 generates an interaction profile for the second user. Based on the interaction profile of the user 110 and the second user, the recommendation module 104 may provide suggestions to the user 110 and the second user for mutual communication.
- the interaction recommendation system 102 may access the databases 106 - 1 , 106 - 2 , ....,106-n to determine the profile parameters and interaction parameters for the user 110 and the second user. For example, for determining a profile parameter, such as based on sociological parameter of contacts, the interaction recommendation system 102 may access, via the network 108 , a database, say database 106 - 2 , to retrieve the information related to the social activities of the contact. In another example, for determining an interaction parameter, such as frequency of meeting with the other users, the interaction recommendation system 102 may access a calendar data of the user 110 to determine the frequency of meeting with other users.
- the databases 106 - 1 , 160 - 2 , 106 - 3 may correspond to the databases of Facebook, LinkedIn, twitter, google places etc.
- the interaction recommendation system 102 may access the databases of the social networking website to determine profile parameters and the interaction parameters for the user 110 and the second user.
- the database corresponding to the Facebook, twitter, LinkedIn, google places may be accessed through a GraphQL server.
- a collector may be coupled with the databases of the Facebook, twitter, LinkedIn, google places and the all the collectors may in turn be coupled with the GrpahQL server.
- the interaction recommendation system 102 may communicate over HyperText Transfer Protocol (HTTPS) with a graph QL server to retrieve the details from the databases of the Facebook, twitter, LinkedIn, google places.
- HTTPS HyperText Transfer Protocol
- the interaction recommendation system 102 may require a permission from the user to access his social account data. For example, a user may be provided a prompt ‘collect my data from Facebook’ and when the user allows the prompt, the user is directed to the Facebook page where the user authenticates the interaction recommendation system 102 to collected data from Facebook.
- the interaction recommendation system sends a message to GraphQL server which may in turn initiate a collector of the Facebook to collect data from the Facebook.
- the collector will collect the data and will provide the data to the GraphQL server and thereafter from the GraphQl server, the interaction recommendation system 102 may access the Facebook data.
- the retrieving of the data from various sources has been explained in with reference to FIG. 3 and FIG. 4 .
- the interaction recommendation system 102 may generate an interaction profile of the user 110 and the second user.
- the interaction profile of the user 110 and the second user reflect the interaction parameters and the profile parameters of the user 110 and the second user.
- the recommendation module 104 may, thereafter provide suggestions to the user 110 based on the interactional profile of the user and the second user. For example, considering that the user 110 and the second user are going for a date and the interaction profile indicates that the user 110 and the second user are both interested in football and cosmology. In this case, the recommendation module 104 may recommend to the user 110 to discuss football and cosmology during the date.
- the interaction recommendation system 102 may also be used to provide suggestions to a user 110 to improve his/her relationship with his/her children.
- the interaction recommendation system 102 would analyze the activities of the teenage children on various social media and may also analyze the details provided by Michelle about the teenage children. Based on these details and social media activity, the interaction recommendation system 102 may create an interaction profile for the teenage children and based on the interaction profile of the teenage children, may provide suggestions to Michelle to interact with her teenage children.
- FIG. 2 illustrates the interaction recommendation system 102 , in accordance with an example implementation of the present subject matter.
- the interaction recommendation system 102 includes processor(s) 200 and memory 202 and interface(s) 204 coupled to the processor(s) 200 .
- the processor(s) 200 may be implemented as microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions.
- the processor(s) 200 is configured to fetch and execute computer-readable instructions stored in the memory 202 of the interaction recommendation system 102 .
- the memory 202 may include any computer-readable medium including, for example, volatile memory (e.g., RAM), and/or non-volatile memory (e.g., EPROM, flash memory, etc.).
- processor(s) may be provided through the use of dedicated hardware as well as hardware capable of executing software.
- the functions may be provided by a single dedicated processor, by a single shared processor, or by a plurality of individual processors, some of which may be shared.
- explicit use of the term “processor” should not be construed to refer exclusively to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), read only memory (ROM) for storing software, random access memory (RAM), non-volatile storage. Other hardware, conventional and/or custom, may also be included.
- DSP digital signal processor
- ASIC application specific integrated circuit
- FPGA field programmable gate array
- ROM read only memory
- RAM random access memory
- non-volatile storage Other hardware, conventional and/or custom, may also be included.
- the processor(s) 200 is responsible for managing the operations of the interaction recommendation system 102 .
- the interface(s) 204 may include a variety of software and hardware interfaces, for example, interface for connected peripheral device(s) such as an external memory. Further, the interface(s) 204 may enable the interaction recommendation system 102 to communicate with other devices. The interface(s) 204 may facilitate multiple communications within a wide variety of protocols and networks, such as the network 108 , including wired networks, e.g., LAN, cable, etc., and wireless networks, e.g., WLAN, cellular, satellite, etc. The interface 204 may be used to provide inputs to interaction recommendation system 102 . In an example, the inputs may be provided by a user.
- Modules 206 and data 214 may reside in the memory 202 .
- the modules 206 include routines, programs, objects, components, data structures, and the like, which perform particular tasks or implement particular abstract data types.
- the modules 206 include a parameter module 208 and a recommendation module 210 , similar to the recommendation module 104 .
- the modules 206 may also comprise other modules 212 that supplement functions of the interaction recommendation system 102 .
- the data 214 serves, amongst other things, as a repository for storing data that may be fetched, processed, received, or generated by the modules 206 .
- the data 214 comprises other data 216 corresponding to the other modules 212 .
- the data 214 of the interaction recommendation system 102 also include parameters data 218 and profile data 220 .
- a user of the interaction recommendation system 102 may add an individual or another user with whom the user needs to communicate.
- the user may provide an input to the interaction recommendation system 102 to add a second user.
- the second user can be a family member, a friend, relative etc.
- the user may add the second user to the interaction recommendation system 102 .
- the user may add the second user from the address book of his device.
- the user may add, other individuals, a group of individuals, a community of individuals, an association of the individuals to the interaction recommendation system 102 .
- the term ‘individuals’ hereafter will include a single user, a group of users, a community of users, an association of users to which the user wises to communicate.
- the user may add details about the individuals, such as sex/gender of user, hobby of user, age of individuals and any other information of which the user is aware of. These details may constitute profile parameters for the user and the individuals. In an example, if the user is not aware of the details about the individuals, the user may not add any details of the individuals.
- the profile parameters for the user and the individuals may be determined by the interaction recommendation system 102 and may be updated against the user and the individuals.
- the parameter module 208 of the interaction recommendation system 102 may determine a psychological parameter, sociological parameter, environmental parameter associated with the user and the individuals.
- the parameter module 208 may determine a parameter for the user and the individuals based on the social media activity of the user and the individuals.
- a plurality of profile parameters may be stored against user and the individuals.
- the profile parameters may be based on a personal character, an emotional state, objective of life, business objective, behaviors, attitude, professional objective, love objective of the user and the individuals.
- the parameter module 208 may access social media profiles, status, social media accounts, posts of the user and the individuals in order to determine the profile parameters of the users.
- the social media posts, status, events may depict a mood, personality, and social connections of the user and the individuals.
- the parameters module 208 may also analyze the user’s database, such as image gallery of the user’s device, to determine profile parameters, such as body type, personality type etc.
- the profile parameters may be stored in the parameters data 218 .
- the parameter module 208 may also monitor a history of interactions between the user and the individuals to determine interaction parameters of the user and the individuals. For example, the parameter module 208 may analyze the applications the user and the individuals use in their communication, the frequency and duration of calls. In an example, the parameter module 208 allots a value to each of the profile parameters. For example, a set of profile parameters are shown below in table 1;
- the parameter module 208 may assign values to each of the profile parameters. For example, based on the social media activity and other physiological factors the parameters module 208 may analyze a personal character of the user and may determine that the user is helpful and may assign a value to the profile parameter helpfulness. In an example, the helpfulness may have a minimum value of 1 and a maximum value of 10. In an example, the helpfulness of the user may be determined by analyzing his day to day activities, such as receiving of donation receipts on the user’s mail may employ that the user is helpful. Further, values may be assigned to each of the profile parameters.
- a recommendation module 210 may generate an interaction profile based on the determined profile parameters and the interaction parameters associated with the user.
- the interaction profile may comprise details, such as behavior, attitude, goal, personality, of the user and the individuals.
- the recommendation module may create an interaction profile based on the values assigned to each of the profile parameters.
- a data relating to the interaction profile may be stored in the profile data 220 .
- the recommendation module 210 provides suggestions to the user for interaction with the individuals. In an example, the suggestions may be provided by comparing the values allotted to the profile parameters of the user and the other individual.
- the recommendation module 210 may recommend to the user to initiate a discuss on topics, such as social welfare programs, compassion etc. Further, in an example, the recommendation module 210 may suggest an activity to the user A and user B. Further, in another example, if the recommendation system 210 also considers the geographical location of the users and individuals to suggest activities. In an example, the recommendation module 210 suggest a nearest place based on the location of the user and the individuals.
- the interaction recommendation system 102 may, based on the interaction profile of Williams, may provide push notification to know how to communicate with his peer group.
- the recommendation module may identify an event associated with the user and may provide suggestions for the event, for example, topic of discussion, place of event. Further, in an example, recommendation module may determine another user/individual associated with the event and may generate an interaction profile for the user. As understood, the interaction profile for the user is already generated, the recommendation module 208 , based on the interaction profile of user and the interaction profile of the individual, may generate suggestions for the user and the individual. The suggestions may be a place of event, a topic of discussion of event, a special requirement for the event.
- the recommendation module 210 may provide recommendation for the date.
- the recommendation module 210 may analyze the interaction profile of Daniel and the woman and may recommend a gift that Daniel should give to the woman.
- the recommendation module 210 may recommend a place of meeting for the date.
- the place of dating may be based on the profile parameter of the Daniel and the woman.
- the recommendation module 210 may provide suggestions to the user based on the group, sex, professional goal, business goal, objective of life of the individual and the user. For example, if the user and the group of the user is having an age group of 20-25 years, the recommendation module 210 may provide suggestions for shopping, movie, trekking etc. In another example, if the age group of the user and the individuals is 50-60, the recommendation module 210 may provide suggestions indulging in a spiritual activity. In another example, if the user and the individuals have a common interest in the sport, the suggestions may be provided based on the sports.
- the recommendation module 210 may provide recommendation based on the historical interactions of the user.
- the recommendation module 210 may analyze social media status, events, or posts to determine suggestion for the user.
- FIG. 3 describes an architecture 300 for a system for retrieving data, such as interaction parameters from databases, such as databases of social media accounts of the user.
- the interaction recommendation system 102 may access the databases of the social networking website to determine selection parameters.
- FIG. 3 shows a database 302 - 1 , a database 302 - 2 , ...., a database 302 -N coupled to an interactional recommendation system 304 via a graphQL server 306 .
- a collector 302 - 1 ′, a collector 302 - 2 ′, and a collector 302 -N′ may be coupled with each of the database 302 - 1 , the database 302 - 2 , and the database 302 -N, respectively.
- the collector 302 - 1 ′, the collector 302 - 2 ′, and the collector 302 -N′ may be also coupled with the graphQL server 306 .
- the interactional recommendation system 304 may communicate over HTTPS with the graphQL server 306 to retrieve the details from the database 302 - 1 , the database 302 - 2 , and the database 302 -N.
- the database 302 - 1 , the database 302 - 2 , and the database 302 -N may corresponds to the databases of social media accounts of user, such as Facebook, LinkedIn, google places, twitter etc. the In an example, the interactional recommendation system 304 may require a permission from a user to access his social account data.
- a user may be provided a prompt ‘collect my data from Twitter’ and when the user allows the prompt, the user is directed to the Twitter page where the user authenticates the interaction recommendation system 304 to collect data from Facebook.
- the interaction recommendation system 304 sends a message to GraphQL server 306 which may in turn initiate the collector 302 - 1 ′ of the database 302 - 1 to collect data from the database 302 - 1 .
- the graphQL server 306 may send a message indication the data that is required.
- the message may comprise keywords, like ‘contacts of last ten video calls’, ‘contacts of last ten chat conversations’ etc.
- the collector 302 - 1 ′ will collect the data and will provide the data to the GraphQL server 306 and the graphQL server 306 may store the data in a system database 308 . Similarly, data from all the other databases are collected and stored in the system database 308 .
- the graphQL server 306 may provide the required data, such as interaction parameters to the interaction recommendation system 304 , when required.
- the database 302 - 1 , 302 - 3 , ...., 302 -N may be implemented on mongoDB and the graphQL server may utilize mongoDb protocol for communication with the collector 302 - 1 ′, 302 - 2 ′, ..., 302 -N′.
- apache spark may be employed to manage clusters of computing systems and clusters of databases.
- the data in the system database 308 may be stored in an encrypted form.
- the encryption of the data may be done using NTRU algorithm. Due to strong protection mechanism, such as NTRU algorithm, it is very difficult for a malicious user to access sensitive personal data. Thus, changes of privacy breach are very minimal in the current system as compared to the conventional system.
- the data may be stored in the system database 308 in a graph form 400 as shown in FIG. 4 .
- a data of a user 402 is linked with each other for better analysis and utilization of the data. For example, if the user 402 it is determined that the user is interested in football and further it is determined that another user 404 , which is a contact in the address book of the user, is also interested in football, a connection 406 is created for the user 402 . In another example, a user 408 knows the user 404 but do not knows the user 402 , an indirect connection 410 is created between the user 402 and the user 408 .
- an interest, likes, dislikes, preferences, of the user 402 , the user 404 , and the user 408 is also reflected on the graph form 400 .
- the user 404 and the user 408 has a common interest, i.e., cricket.
- the user 402 , the user 404 , and the user 408 has a common interest politics.
- FIG. 5 illustrates a method 500 for providing suggestions for an interaction, in accordance with an example of the present subject matter.
- the method 500 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of the example method 500 to provide suggestions is provided in reference to the above-described interaction recommendation system 102 .
- profile parameters associated with a user is determined.
- the profile parameters are indicative of behavior, likes and dislikes of the user.
- the profile parameters may include details, such as favorite sports, favorite food, favorite restaurant etc., of the user
- interaction parameters associated with the user is determined.
- the interaction parameters are indicative of interactional aspects of the user.
- the interaction parameters may indicate which application a user used for communication.
- interaction profile for the user is determined based on the determined profile parameters and the interaction parameters associated with the user.
- suggestions to the user are provided based on the interaction profile of the user.
- the suggestions are provided for interaction with the other users. For example, the suggestions may recommend a topic of discussion, a place of meeting, a food to have with the other users.
- FIG. 6 illustrates another method 600 for providing suggestions for an interaction, in accordance with an example of the present subject matter.
- the method 600 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of the example method 600 to provide suggestions is provided in reference to the above-described interaction recommendation system 102 .
- the method starts at block 602 .
- profile parameters associated with a user are determined.
- the profile parameters are indicative of behavior, likes, dislikes, attitude, personality, phycology, and behavior of the user. For example, if a user is an introvert, the profile parameter may be ‘introvert’.
- interaction parameters associated with the user is determined.
- interaction parameter depends on the interactional habit of the users and the historical interaction of the uses.
- the interaction parameter may be determined by accessing social media account of the user.
- an interaction profile of the user is generated based on the profile parameters and the interaction parameters and the method proceed to block 608 .
- an event associated with the user is identified.
- the event may be a date, a business meeting, a professional meeting.
- the event may be identified by accessing a calendar of the user’s device.
- At block 610 at least one individual associated with the event is identified.
- the at least one individual may be a woman if the event is date, a partner, if the meeting is a business meeting.
- an interaction profile of the at least one individual is generated.
- the interaction profile may be generated in the same manner as of the interaction profile of the user is generated in block 304-308.
- suggestions are provided to the user and the at least one individual, based on the interaction profile of the user and the individual.
- the suggestion may provide recommendation for holding the event. For example, if the identified event is a date, a place, restaurant, resort, may be suggested, based on the profile parameter of the user and the woman, for attending the date.
- the suggesting place can be a hotel, auditorium, meeting halls etc.
- the suggestions may also be provided for a topic of discussion, type of food to be ordered etc.
- FIG. 7 illustrates a method 700 for providing suggestions for an interaction, in accordance with an example of the present subject matter.
- the method 700 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of the example method 700 to provide suggestions is provided in reference to the above-described interaction recommendation system 102 .
- profile parameters for users are accessed from the profile parameters of the users.
- the profile parameters may indicate choices, likes, preferences of users. The method then proceeds to block 704 .
- values are allotted to the profile parameters of the users.
- the values are allotted to the profile parameters based on various factors, such as social media activity of the users, social interaction of the user.
- the allotted values are compared.
- the values of the plurality of profile parameters are compared.
- the suggestions are provided to the user based on the comparison. For example, if it is determined that two users have same allotted value in a profile parameter, say, sports, the interaction recommendation system may recommend the both users to discuss topics related to sports.
- FIG. 8 illustrates yet another method 800 for providing suggestions for an interaction, in accordance with an example of the present subject matter.
- the method 800 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of the example method 800 to provide suggestions is provided in reference to the above-described interaction recommendation system 102 .
- profile parameters associated with a user are determined.
- the profile parameters may be determined by any of the techniques recited previously.
- the method thereafter proceeds to block 804 where a plurality of contacts is generated based on the profile parameters of the user.
- the profile parameters may comprise details, such as birthday of the user or any special occasion of the user. Further, it is natural for a person to talk to his family on his birthday.
- a plurality of contacts, from an address book of the user may selected and provided to the user wherein the plurality of the contacts may comprise the contacts of family members of the user.
- interaction parameters associated with the user is determined and the method proceeds to block 808 where profile parameters and interaction parameters associated with plurality of contacts is determined.
- interaction profiles for the user and the plurality of the contacts are generated and the method proceeds to block 812 where a list of communication platforms is generated based on interaction profiles.
- the list of the communication platforms may indicate applications which the user can for communication. For example, if it is indicated, based on the interaction profiles, that the user and the plurality of the contact uses skype, WhatsApp, emails frequently for communication, the list of communication platform may comprise skype, WhatsApp, and email platform as recommended means for communication.
- suggestions may be provided to the user for the communication based on the interaction profiles. The suggestions may be about a topic of discussion, event, place of event etc.
- the methods and devices of the present subject matter provide techniques to provide suggestions for an interaction.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Tourism & Hospitality (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The system provides a method and apparatus for generating a profile of a first user, where the profile comprises interaction parameters associated with the user. The system can generate a profile of a second user, also comprising interaction parameters of the second user. The system can then provide suggestions to either or both the first and second user for interacting with each other.
Description
- In any relationship, communication plays a vital role in either developing the relationship or degrading the relationship. The communication between two individuals or a group of individuals can be positive and developing if the communication involves such topics in which the individuals or the group of individuals are interested. Similarly, the communication between the individual may be non-interactive if the communication involves topics which are not of mutual interest.
- The system provides a method and apparatus for generating a profile of a first user, where the profile comprises interaction parameters associated with the user. The system can generate a profile of a second user, also comprising interaction parameters of the second user. The system can then provide suggestions to either or both the first and second user for interacting with each other.
- The following detailed description references the drawings, wherein:
-
FIG. 1 illustrates a network environment implementing an interaction recommendation system, in accordance with an example implementation of the present subject matter; -
FIG. 2 illustrates an interaction recommendation system, in accordance with an example implementation of the present subject matter; -
FIG. 3 illustrates an architecture for a system which retrieves data form databases, according to an example of the present subject matter; -
FIG. 4 shows a graph form of a stored data according to an example of the present subject matter; -
FIG. 5 illustrates amethod 500 for providing suggestions for an interaction, according to an example of the present subject matter. -
FIG. 6 illustrates anothermethod 600 for providing suggestions for an interaction, in accordance with an example of the present subject matter. -
FIG. 7 illustrates yet anothermethod 700 for providing suggestions for an interaction, according to an example of the present subject matter. -
FIG. 8 illustrates yet anothermethod 800 for providing suggestions for an interaction, in accordance with an example of the present subject matter. - The description of the present subject matter herein incorporates the specification of the U.S. Granted Pat. US 6980870, by reference. The U.S. Pat. 6980870 discloses techniques for managing, optimizing, and scheduling personal relationship with a contact.
- A relationship between two individuals depends on the various factors, such as their interests, behavior, nature, and attitude. It is sometime difficult for a user to decide how he should interact with other user for an efficient and fruitful communication. For example, it is difficult for the individuals to decide a topic of discussion, a place of meeting, choice of food, etc. Similarly, it maybe sometimes difficult for parents to efficiently communicate with their teenage children such that the communication is engaging and interactive. Therefore, various factors are to be considered during any interaction between individuals. Wrong choices of such parameters may lead to unsuccessful meetings and inefficient communication between the individuals. For example, during a first date, it may be difficult for two individuals to decide a topic of discussion or a mutual point of interest. Similarly, in situations when two individuals are meeting after a long time, it may sometimes be difficult for them to determine mutual interests. Therefore, to effectively interact with others, an individual should be aware of his own behavior, likes and dislikes, along with the behavior, likes and dislikes of others. However, it is difficult for any individual to be fully aware of his/her own behavior, along with the behavior of others. This may lead to ineffective communication between individuals and may lead to unfruitful social interactions.
- According to the present subject matter, techniques for providing suggestions for interaction between individuals are provided. In an example of the present subject matter, an interaction recommendation system determines various profile parameters, along with different interaction parameters corresponding to an individual. The profile parameters may indicate the behavior, likes and dislikes of an individual, while the interaction parameters may indicate different interactional aspects associated with the individual. The profile parameters may be based on the phycology, sociology, and environmental factors of the user. In an example of the present subject matter, the interaction recommendation system, based on the determination of the profile parameters and interaction parameters, may suggest actions/recommendations to the individuals for interaction. According to the system, a digital coach implemented by the system may use various behavioral factors included in the profile parameters, such as personality type, body type, body built, favorite genre of movies, type of music, hobbies, favorite cuisine and restaurants, favorite places, environmental condition, political favorites, favorite sports etc., to suggest various interaction possibilities to an individual. Further, the digital coach may also use past interaction experience, such as events attended by the individual, status on social media platforms, frequency of meeting with other individuals, past experience of interactions, etc., to suggest various interaction possibilities to the individual.
- In an example, if a meeting/date has been scheduled between two individuals, the interaction recommendation system may analyze the profile parameters of the two individuals along with the interaction parameters associated with the two individuals. The interaction recommendation system may, based on the assessment of the profile parameters and the interaction parameters, generate an interaction profile for each of the two individuals. Based on the generated interaction profile of the two individuals, the interaction recommendation system, provides suggestions, such as topic of discussion, place of meetings, etc., to both of the individuals. According to the present subject matter, the detail, such as the interaction profile, the interaction parameters. All the calculations, processing, data analysis happens at the database by backend servers. A plurality of micro software services allows parallel execution and processing of the data. The data is processed using graphical processor unit (GPU) processors at these databases which are significantly faster than the central processing units of the user’s mobile device. Also, as the processing is done at backend servers, the battery power of the user’s device is saved. In general, the mobile phone and tablet are equipped with 99% ARM processors. The backend servers are equipped with x86 processors (Intel or advanced micro devices (AMD)) and GPU (Nvidia or AMD). According to the set of benchmarks, the ARM architecture is about 8 times less efficient than the x86 architecture when it comes to complex calculation.
- The above techniques are further described with reference to
FIG. 1 toFIG. 7 . It should be noted that the description and the Figures merely illustrate the principles of the present subject matter along with examples described herein and should not be construed as a limitation to the present subject matter. It is thus understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present subject matter. Moreover, all statements herein reciting principles, aspects, and implementations of the present subject matter, as well as specific examples thereof, are intended to encompass equivalents thereof. -
FIG. 1 shows aninteraction recommendation system 102 implementing a recommendation module 104 to provide suggestions to auser 110, according to an example implementation of the present subject matter. Theinteraction recommendation system 102 may be coupled with a plurality of databases, such as database 106-1, 106-2, ..., 106-n, via anetwork 108. - The
network 108 may be a single network or a combination of multiple networks and may use a variety of different communication protocols. Thenetwork 108 may be a wireless or a wired network, or a combination thereof. Examples of such individual networks include, but are not limited to, Global System for Mobile Communication (GSM) network, Universal Mobile Telecommunications System (UMTS) network, Personal Communications Service (PCS) network, Time Division Multiple Access (TDMA) network, Code Division Multiple Access (CDMA) network, Next Generation Network (NON), and Public Switched Telephone Network (PSTN). Depending on the technology, thecommunication network 108 includes various network entities, such as gateways, routers; however, such details have been omitted for the sake of brevity of the present description. - The
interaction recommendation system 102 may be implemented as any of a variety of conventional computing devices, including, a mobile phone, a tablet, a pager, desktop, and a laptop. Further, the databases 106-1, 106-2, ....,106-n may be a hierarchical database, a network database, an object-oriented database, a relational database etc. - In an example, the
interaction recommendation system 102 may determine profile parameters for theuser 110. The profile parameters may be likes, dislikes, personal choices, hobbies of theuser 110. Further, the profile parameters may also be based on phycological, sociological, and environmental factors of theuser 110. For example, the profile parameters based on phycological factors may be, introvert nature, extrovert nature etc., the profile parameters based sociological factors may be social status of theuser 110 or the income level of theuser 110. Further, theinteraction recommendation system 102 determines interaction parameters associated with theuser 110. The interaction parameters may be based on the interactional habits of theuser 110, such as events in which the user may be interested in, frequency of meeting with other users etc. Based on the profile parameters and the interaction parameters, theinteraction recommendation system 102 may generate interaction profile for theuser 110. Further, based on the interaction profile, a recommendation module 104 of theinteraction recommendation system 102 provides suggestions to the user 100 for interaction with the other user. In an example, the suggestions may be place of meeting with other users, topic of discussion, restaurant to visit etc. - According to another example implementation of the present subject matter, a
user 110 of theinteraction recommendation system 102 may add a second user (not shown) with which theuser 110 desires to have a communication. In an example, theuser 110 may add the second user from an address book stored on the user’s device, a social media account of theuser 110, email of theuser 110 and alike. - In an example, the
interaction recommendation system 102 may determine profile parameters for the second user. The profile parameters may be likes, dislikes, personal choices, hobbies of the second user. Further, the profile parameters may also be based on psychological, sociological, and environmental factors of the second user. Further, theinteraction recommendation system 102 determines interaction parameters for second user. Based on the profile parameters and the interaction parameters, theinteraction recommendation system 102 generates an interaction profile for the second user. Based on the interaction profile of theuser 110 and the second user, the recommendation module 104 may provide suggestions to theuser 110 and the second user for mutual communication. - In an example, the
interaction recommendation system 102 may access the databases 106-1, 106-2, ....,106-n to determine the profile parameters and interaction parameters for theuser 110 and the second user. For example, for determining a profile parameter, such as based on sociological parameter of contacts, theinteraction recommendation system 102 may access, via thenetwork 108, a database, say database 106-2, to retrieve the information related to the social activities of the contact. In another example, for determining an interaction parameter, such as frequency of meeting with the other users, theinteraction recommendation system 102 may access a calendar data of theuser 110 to determine the frequency of meeting with other users. - The databases 106-1, 160-2, 106-3 may correspond to the databases of Facebook, LinkedIn, twitter, google places etc. The
interaction recommendation system 102 may access the databases of the social networking website to determine profile parameters and the interaction parameters for theuser 110 and the second user. In an example, the database corresponding to the Facebook, twitter, LinkedIn, google places may be accessed through a GraphQL server. In an example, a collector may be coupled with the databases of the Facebook, twitter, LinkedIn, google places and the all the collectors may in turn be coupled with the GrpahQL server. Theinteraction recommendation system 102 may communicate over HyperText Transfer Protocol (HTTPS) with a graph QL server to retrieve the details from the databases of the Facebook, twitter, LinkedIn, google places. In an example, theinteraction recommendation system 102 may require a permission from the user to access his social account data. For example, a user may be provided a prompt ‘collect my data from Facebook’ and when the user allows the prompt, the user is directed to the Facebook page where the user authenticates theinteraction recommendation system 102 to collected data from Facebook. The interaction recommendation system sends a message to GraphQL server which may in turn initiate a collector of the Facebook to collect data from the Facebook. The collector will collect the data and will provide the data to the GraphQL server and thereafter from the GraphQl server, theinteraction recommendation system 102 may access the Facebook data. The retrieving of the data from various sources, has been explained in with reference toFIG. 3 andFIG. 4 . - Based on the profile parameters and the interaction parameters, the
interaction recommendation system 102 may generate an interaction profile of theuser 110 and the second user. The interaction profile of theuser 110 and the second user reflect the interaction parameters and the profile parameters of theuser 110 and the second user. The recommendation module 104, may, thereafter provide suggestions to theuser 110 based on the interactional profile of the user and the second user. For example, considering that theuser 110 and the second user are going for a date and the interaction profile indicates that theuser 110 and the second user are both interested in football and cosmology. In this case, the recommendation module 104 may recommend to theuser 110 to discuss football and cosmology during the date. - In another example, the
interaction recommendation system 102 may also be used to provide suggestions to auser 110 to improve his/her relationship with his/her children. Considering an example where Michelle is a single mother who lives alone with two teenage children. Michelle wants to improve her communication with her teenage children. In such cases, theinteraction recommendation system 102 would analyze the activities of the teenage children on various social media and may also analyze the details provided by Michelle about the teenage children. Based on these details and social media activity, theinteraction recommendation system 102 may create an interaction profile for the teenage children and based on the interaction profile of the teenage children, may provide suggestions to Michelle to interact with her teenage children. -
FIG. 2 illustrates theinteraction recommendation system 102, in accordance with an example implementation of the present subject matter. Theinteraction recommendation system 102, among other things, includes processor(s) 200 andmemory 202 and interface(s) 204 coupled to the processor(s) 200. The processor(s) 200 may be implemented as microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor(s) 200 is configured to fetch and execute computer-readable instructions stored in thememory 202 of theinteraction recommendation system 102. Thememory 202 may include any computer-readable medium including, for example, volatile memory (e.g., RAM), and/or non-volatile memory (e.g., EPROM, flash memory, etc.). - The functions of the various elements shown in the Figures, including any functional blocks labelled as “processor(s)”, may be provided through the use of dedicated hardware as well as hardware capable of executing software. When provided by a processor, the functions may be provided by a single dedicated processor, by a single shared processor, or by a plurality of individual processors, some of which may be shared. Moreover, explicit use of the term “processor” should not be construed to refer exclusively to hardware capable of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), read only memory (ROM) for storing software, random access memory (RAM), non-volatile storage. Other hardware, conventional and/or custom, may also be included. The processor(s) 200 is responsible for managing the operations of the
interaction recommendation system 102. - The interface(s) 204 may include a variety of software and hardware interfaces, for example, interface for connected peripheral device(s) such as an external memory. Further, the interface(s) 204 may enable the
interaction recommendation system 102 to communicate with other devices. The interface(s) 204 may facilitate multiple communications within a wide variety of protocols and networks, such as thenetwork 108, including wired networks, e.g., LAN, cable, etc., and wireless networks, e.g., WLAN, cellular, satellite, etc. Theinterface 204 may be used to provide inputs tointeraction recommendation system 102. In an example, the inputs may be provided by a user. -
Modules 206 anddata 214 may reside in thememory 202. Themodules 206 include routines, programs, objects, components, data structures, and the like, which perform particular tasks or implement particular abstract data types. In an example, themodules 206 include aparameter module 208 and arecommendation module 210, similar to the recommendation module 104. Themodules 206 may also compriseother modules 212 that supplement functions of theinteraction recommendation system 102. - The
data 214 serves, amongst other things, as a repository for storing data that may be fetched, processed, received, or generated by themodules 206. Thedata 214 comprisesother data 216 corresponding to theother modules 212. In the illustrated example implementation, thedata 214 of theinteraction recommendation system 102 also includeparameters data 218 and profile data 220. - In an example, a user of the
interaction recommendation system 102 may add an individual or another user with whom the user needs to communicate. In an example, the user may provide an input to theinteraction recommendation system 102 to add a second user. The second user can be a family member, a friend, relative etc. The user may add the second user to theinteraction recommendation system 102. In an example, the user may add the second user from the address book of his device. In another example, the user may add, other individuals, a group of individuals, a community of individuals, an association of the individuals to theinteraction recommendation system 102. The term ‘individuals’ hereafter will include a single user, a group of users, a community of users, an association of users to which the user wises to communicate. - In an example, while adding individuals, the user may add details about the individuals, such as sex/gender of user, hobby of user, age of individuals and any other information of which the user is aware of. These details may constitute profile parameters for the user and the individuals. In an example, if the user is not aware of the details about the individuals, the user may not add any details of the individuals.
- Further, in an example, the profile parameters for the user and the individuals may be determined by the
interaction recommendation system 102 and may be updated against the user and the individuals. For example, theparameter module 208 of theinteraction recommendation system 102 may determine a psychological parameter, sociological parameter, environmental parameter associated with the user and the individuals. In an example, theparameter module 208 may determine a parameter for the user and the individuals based on the social media activity of the user and the individuals. Thus, a plurality of profile parameters may be stored against user and the individuals. In an example, the profile parameters may be based on a personal character, an emotional state, objective of life, business objective, behaviors, attitude, professional objective, love objective of the user and the individuals. To determine the profile parameters, theparameter module 208 may access social media profiles, status, social media accounts, posts of the user and the individuals in order to determine the profile parameters of the users. In an example, the social media posts, status, events, may depict a mood, personality, and social connections of the user and the individuals. Further, theparameters module 208 may also analyze the user’s database, such as image gallery of the user’s device, to determine profile parameters, such as body type, personality type etc. The profile parameters may be stored in theparameters data 218. - In an example, the
parameter module 208 may also monitor a history of interactions between the user and the individuals to determine interaction parameters of the user and the individuals. For example, theparameter module 208 may analyze the applications the user and the individuals use in their communication, the frequency and duration of calls. In an example, theparameter module 208 allots a value to each of the profile parameters. For example, a set of profile parameters are shown below in table 1; -
Profile Parameters Maximum Value Minimum Value Helpfulnesss 1 10 Objective of life 1 5 Extroversion/ sociability 1 7 Independence 1 6 Frequency of contact 1 5 - In an example, the
parameter module 208 may assign values to each of the profile parameters. For example, based on the social media activity and other physiological factors theparameters module 208 may analyze a personal character of the user and may determine that the user is helpful and may assign a value to the profile parameter helpfulness. In an example, the helpfulness may have a minimum value of 1 and a maximum value of 10. In an example, the helpfulness of the user may be determined by analyzing his day to day activities, such as receiving of donation receipts on the user’s mail may employ that the user is helpful. Further, values may be assigned to each of the profile parameters. - A
recommendation module 210 may generate an interaction profile based on the determined profile parameters and the interaction parameters associated with the user. The interaction profile may comprise details, such as behavior, attitude, goal, personality, of the user and the individuals. In an example, the recommendation module may create an interaction profile based on the values assigned to each of the profile parameters. A data relating to the interaction profile may be stored in the profile data 220. Based on the interaction profile, therecommendation module 210 provides suggestions to the user for interaction with the individuals. In an example, the suggestions may be provided by comparing the values allotted to the profile parameters of the user and the other individual. For example, for a user A if the value allotted to the helpfulness matches with the value of helpfulness allotted to a user B, therecommendation module 210 may recommend to the user to initiate a discuss on topics, such as social welfare programs, compassion etc. Further, in an example, therecommendation module 210 may suggest an activity to the user A and user B. Further, in another example, if therecommendation system 210 also considers the geographical location of the users and individuals to suggest activities. In an example, therecommendation module 210 suggest a nearest place based on the location of the user and the individuals. - Considering an example, where a user, Williams, is very shy in communication. Sometimes he is not sure how to communicate with his peer group. The
interaction recommendation system 102 may, based on the interaction profile of Williams, may provide push notification to know how to communicate with his peer group. - In an example, the recommendation module may identify an event associated with the user and may provide suggestions for the event, for example, topic of discussion, place of event. Further, in an example, recommendation module may determine another user/individual associated with the event and may generate an interaction profile for the user. As understood, the interaction profile for the user is already generated, the
recommendation module 208, based on the interaction profile of user and the interaction profile of the individual, may generate suggestions for the user and the individual. The suggestions may be a place of event, a topic of discussion of event, a special requirement for the event. - For example, if a user, Daniel, has a date with a woman, the
recommendation module 210 may provide recommendation for the date. Therecommendation module 210 may analyze the interaction profile of Daniel and the woman and may recommend a gift that Daniel should give to the woman. In another example, therecommendation module 210 may recommend a place of meeting for the date. The place of dating may be based on the profile parameter of the Daniel and the woman. - In an example, the
recommendation module 210 may provide suggestions to the user based on the group, sex, professional goal, business goal, objective of life of the individual and the user. For example, if the user and the group of the user is having an age group of 20-25 years, therecommendation module 210 may provide suggestions for shopping, movie, trekking etc. In another example, if the age group of the user and the individuals is 50-60, therecommendation module 210 may provide suggestions indulging in a spiritual activity. In another example, if the user and the individuals have a common interest in the sport, the suggestions may be provided based on the sports. - Further, in an example, the
recommendation module 210 may provide recommendation based on the historical interactions of the user. In an example, therecommendation module 210 may analyze social media status, events, or posts to determine suggestion for the user. -
FIG. 3 describes an architecture 300 for a system for retrieving data, such as interaction parameters from databases, such as databases of social media accounts of the user. As explained earlier, theinteraction recommendation system 102 may access the databases of the social networking website to determine selection parameters.FIG. 3 shows a database 302-1, a database 302-2, ...., a database 302-N coupled to aninteractional recommendation system 304 via agraphQL server 306. In an example, a collector 302-1′, a collector 302-2′, and a collector 302-N′ may be coupled with each of the database 302-1, the database 302-2, and the database 302-N, respectively. The collector 302-1′, the collector 302-2′, and the collector 302-N′ may be also coupled with thegraphQL server 306. Theinteractional recommendation system 304 may communicate over HTTPS with thegraphQL server 306 to retrieve the details from the database 302-1, the database 302-2, and the database 302-N. In an example, the database 302-1, the database 302-2, and the database 302-N may corresponds to the databases of social media accounts of user, such as Facebook, LinkedIn, google places, twitter etc. the In an example, theinteractional recommendation system 304 may require a permission from a user to access his social account data. For example, a user may be provided a prompt ‘collect my data from Twitter’ and when the user allows the prompt, the user is directed to the Twitter page where the user authenticates theinteraction recommendation system 304 to collect data from Facebook. In an example, consider that the database 302-1 corresponds to Facebook. Theinteraction recommendation system 304 sends a message toGraphQL server 306 which may in turn initiate the collector 302-1′ of the database 302-1 to collect data from the database 302-1. In an example, thegraphQL server 306 may send a message indication the data that is required. In an example, the message may comprise keywords, like ‘contacts of last ten video calls’, ‘contacts of last ten chat conversations’ etc. The collector 302-1′ will collect the data and will provide the data to theGraphQL server 306 and thegraphQL server 306 may store the data in asystem database 308. Similarly, data from all the other databases are collected and stored in thesystem database 308. ThegraphQL server 306 may provide the required data, such as interaction parameters to theinteraction recommendation system 304, when required. In an example, the database 302-1, 302-3, ...., 302-N may be implemented on mongoDB and the graphQL server may utilize mongoDb protocol for communication with the collector 302-1′, 302-2′, ..., 302-N′. In an example, apache spark may be employed to manage clusters of computing systems and clusters of databases. - In an example, the data in the
system database 308 may be stored in an encrypted form. The encryption of the data may be done using NTRU algorithm. Due to strong protection mechanism, such as NTRU algorithm, it is very difficult for a malicious user to access sensitive personal data. Thus, changes of privacy breach are very minimal in the current system as compared to the conventional system. - Further, in an example, the data may be stored in the
system database 308 in agraph form 400 as shown inFIG. 4 . In an example, in the graph form 400 a data of a user 402 is linked with each other for better analysis and utilization of the data. For example, if the user 402 it is determined that the user is interested in football and further it is determined that another user 404, which is a contact in the address book of the user, is also interested in football, aconnection 406 is created for the user 402. In another example, a user 408 knows the user 404 but do not knows the user 402, anindirect connection 410 is created between the user 402 and the user 408. In an example, an interest, likes, dislikes, preferences, of the user 402, the user 404, and the user 408 is also reflected on thegraph form 400. For example, the user 404 and the user 408 has a common interest, i.e., cricket. In another example, the user 402, the user 404, and the user 408 has a common interest politics. -
FIG. 5 illustrates amethod 500 for providing suggestions for an interaction, in accordance with an example of the present subject matter. Although themethod 500 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of theexample method 500 to provide suggestions is provided in reference to the above-describedinteraction recommendation system 102. - The order in which the
method 500 is described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement themethod 500, or an alternative method. - At
block 502, profile parameters associated with a user is determined. The profile parameters are indicative of behavior, likes and dislikes of the user. For example, the profile parameters may include details, such as favorite sports, favorite food, favorite restaurant etc., of the user - At
block 504, interaction parameters associated with the user is determined. The interaction parameters are indicative of interactional aspects of the user. In an example, the interaction parameters may indicate which application a user used for communication. - At
block 506, interaction profile for the user is determined based on the determined profile parameters and the interaction parameters associated with the user. Finally, atblock 508, suggestions to the user are provided based on the interaction profile of the user. The suggestions are provided for interaction with the other users. For example, the suggestions may recommend a topic of discussion, a place of meeting, a food to have with the other users. -
FIG. 6 illustrates anothermethod 600 for providing suggestions for an interaction, in accordance with an example of the present subject matter. Although themethod 600 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of theexample method 600 to provide suggestions is provided in reference to the above-describedinteraction recommendation system 102. - The order in which the
method 600 is described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement themethod 600, or an alternative method. - The method starts at
block 602. Atblock 602, profile parameters associated with a user are determined. The profile parameters are indicative of behavior, likes, dislikes, attitude, personality, phycology, and behavior of the user. For example, if a user is an introvert, the profile parameter may be ‘introvert’. - At
block 604, interaction parameters associated with the user is determined. As described previously, interaction parameter depends on the interactional habit of the users and the historical interaction of the uses. In an example, the interaction parameter may be determined by accessing social media account of the user. - At
block 606 an interaction profile of the user is generated based on the profile parameters and the interaction parameters and the method proceed to block 608. Atblock 608, an event associated with the user is identified. In an example, the event may be a date, a business meeting, a professional meeting. In an example, the event may be identified by accessing a calendar of the user’s device. - At
block 610, at least one individual associated with the event is identified. In an example, the at least one individual may be a woman if the event is date, a partner, if the meeting is a business meeting. - At
block 612, an interaction profile of the at least one individual is generated. In an example, the interaction profile may be generated in the same manner as of the interaction profile of the user is generated in block 304-308. - At
block 614, suggestions are provided to the user and the at least one individual, based on the interaction profile of the user and the individual. In an example, the suggestion may provide recommendation for holding the event. For example, if the identified event is a date, a place, restaurant, resort, may be suggested, based on the profile parameter of the user and the woman, for attending the date. In another example, if the event is a business meeting, the suggesting place can be a hotel, auditorium, meeting halls etc. In another example, the suggestions may also be provided for a topic of discussion, type of food to be ordered etc. Finally, at block 618, the method terminates -
FIG. 7 illustrates amethod 700 for providing suggestions for an interaction, in accordance with an example of the present subject matter. Although themethod 700 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of theexample method 700 to provide suggestions is provided in reference to the above-describedinteraction recommendation system 102. - The order in which the
method 700 is described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement themethod 700, or an alternative method. - At
block 702, profile parameters for users are accessed from the profile parameters of the users. In an example, the profile parameters may indicate choices, likes, preferences of users. The method then proceeds to block 704. - At
block 704, values are allotted to the profile parameters of the users. The values are allotted to the profile parameters based on various factors, such as social media activity of the users, social interaction of the user. - At
block 706, the allotted values are compared. As explained in para 32, the values of the plurality of profile parameters are compared. Finally, atblock 708, the suggestions are provided to the user based on the comparison. For example, if it is determined that two users have same allotted value in a profile parameter, say, sports, the interaction recommendation system may recommend the both users to discuss topics related to sports. -
FIG. 8 illustrates yet anothermethod 800 for providing suggestions for an interaction, in accordance with an example of the present subject matter. Although themethod 800 may be implemented in a variety of interaction recommendation systems, but for the ease of explanation, the present description of theexample method 800 to provide suggestions is provided in reference to the above-describedinteraction recommendation system 102. - The order in which the
method 800 is described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement themethod 800, or an alternative method. - At
block 802, profile parameters associated with a user are determined. The profile parameters may be determined by any of the techniques recited previously. The method thereafter proceeds to block 804 where a plurality of contacts is generated based on the profile parameters of the user. In an example, the profile parameters may comprise details, such as birthday of the user or any special occasion of the user. Further, it is natural for a person to talk to his family on his birthday. Thus, in the example, a plurality of contacts, from an address book of the user may selected and provided to the user wherein the plurality of the contacts may comprise the contacts of family members of the user. - At
block 806, interaction parameters associated with the user is determined and the method proceeds to block 808 where profile parameters and interaction parameters associated with plurality of contacts is determined. - At
block 810, interaction profiles for the user and the plurality of the contacts are generated and the method proceeds to block 812 where a list of communication platforms is generated based on interaction profiles. The list of the communication platforms may indicate applications which the user can for communication. For example, if it is indicated, based on the interaction profiles, that the user and the plurality of the contact uses skype, WhatsApp, emails frequently for communication, the list of communication platform may comprise skype, WhatsApp, and email platform as recommended means for communication. Finally, atblock 814, suggestions may be provided to the user for the communication based on the interaction profiles. The suggestions may be about a topic of discussion, event, place of event etc. Thus, the methods and devices of the present subject matter provide techniques to provide suggestions for an interaction. Although examples of providing suggestions for an interaction as described, have been described in a language, specific to structural features and/or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as example for providing suggestions for an interaction.
Claims (15)
1. A method comprising:
determining profile parameters associated with a user, wherein the profile parameters are indicative of behavior, likes and dislikes of the user;
determining interaction parameters associated with the user, wherein the interaction parameters are indicative of interactional aspects of the user;
generating an interaction profile for the user based on the determined profile parameters and the interaction parameters associated with the user; and
providing suggestions to the user, for interaction with other users, based on the interaction profile of the user.
2. The method as claimed in claim 1 , wherein the method further comprises:
identifying an event associated with the user;
providing suggestions to the user for the event.
3. The method as claimed in claim 2 further comprising:
identifying at least one other individual associated with the event;
generating an interaction profile for the at least one other individual based on profile parameters and interaction parameters associated with at least one other individual; and
providing suggestions to the user for the event based on interaction profile of the user and the interaction profile of the at least one other individual.
4. The method as claimed in claim 1 , wherein the profile parameters comprises at least one of personality type, favorite genre of movies, type of music, hobbies, favorite places, favorite cuisine, phycology, sociology, and environmental condition, political favorites, sports favorites.
5. The method as claimed in claim 1 , wherein the interaction parameters comprises at least past interaction experiences.
6. The method as claimed in claim 1 , wherein the providing suggestions comprises at least one of location for an event, topics of discussion during the event, attire for the event and special requirement for the event.
7. The method as claimed in claim 1 , wherein the suggestions to the user is provided based on a group of the user and the other individuals, and wherein the group is based on at least one of age, sex, professional goal, business goal, objective of life.
8. The method as claimed in claim 1 , wherein the suggestions are provided based on historical interactions of the user and the other individuals.
9. An interaction recommendation system comprising:
a parameter module to:
determine profile parameters associated with a user, wherein the profile parameters are indicative of behavior, likes and dislikes of the user;
determine interaction parameters associated with the user, wherein the interaction parameters are indicative of interactional aspects of the user;
a recommendation module to:
generate an interaction profile for the user based on the determined profile parameters and the interaction parameters associated with the user; and
provide suggestions to the user, for interaction with other individuals, based on the interaction profile of the user.
10. The interaction recommendation system as claimed in claim 9 , wherein the providing suggestions comprises at least one of location for the event, topics of discussion during an event, attire for the event and special requirement for the event.
11. The interaction recommendation system as claimed in claim 9 , wherein the suggestions to the user is provided based on a group of the user and the other individuals, and wherein the group is based on at least one of age, sex, professional goal, business goal, objective of life.
12. The interaction recommendation system as claimed in claim 9 , wherein the recommendation module is to:
identifying an event associated with the user; and
providing suggestions to the user for the event.
13. The interaction recommendation system as claimed in claim 12 further comprising:
identifying at least another individual associated with the event;
generating an interaction profile for the another individual based on profile parameters and interaction parameters associated with the another individual; and
providing suggestions to the user for the event based on interaction profile of the user and the interaction profile of the another individual.
14. The interaction recommendation system as claimed in claim 9 , wherein the recommendation module is to provide suggestion based on historical interactions of the user and the other individuals.
15. The interaction recommendation system as claimed in claim 14 , wherein the historical interactions include a social media post, a social media status, last attended event, frequency of contact with other individuals.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/978,711 US20230325943A1 (en) | 2018-09-14 | 2022-11-01 | Interaction recommendation engine |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/086,281 US11488264B2 (en) | 2018-09-14 | 2018-09-14 | Interaction recommendation engine |
PCT/IB2018/057066 WO2020053631A1 (en) | 2018-09-14 | 2018-09-14 | Interaction recommendation system |
US17/978,711 US20230325943A1 (en) | 2018-09-14 | 2022-11-01 | Interaction recommendation engine |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/086,281 Continuation US11488264B2 (en) | 2018-09-14 | 2018-09-14 | Interaction recommendation engine |
Publications (1)
Publication Number | Publication Date |
---|---|
US20230325943A1 true US20230325943A1 (en) | 2023-10-12 |
Family
ID=63832451
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/086,281 Active US11488264B2 (en) | 2018-09-14 | 2018-09-14 | Interaction recommendation engine |
US17/978,711 Pending US20230325943A1 (en) | 2018-09-14 | 2022-11-01 | Interaction recommendation engine |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/086,281 Active US11488264B2 (en) | 2018-09-14 | 2018-09-14 | Interaction recommendation engine |
Country Status (6)
Country | Link |
---|---|
US (2) | US11488264B2 (en) |
EP (1) | EP3850573A1 (en) |
JP (1) | JP7278213B2 (en) |
CA (1) | CA3019019A1 (en) |
IL (1) | IL281365A (en) |
WO (1) | WO2020053631A1 (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11727284B2 (en) | 2019-12-12 | 2023-08-15 | Business Objects Software Ltd | Interpretation of machine learning results using feature analysis |
US20210342738A1 (en) * | 2020-05-01 | 2021-11-04 | Sap Se | Machine learning-facilitated data entry |
JP7495842B2 (en) | 2020-07-31 | 2024-06-05 | 株式会社Nttドコモ | Recommendation device |
Citations (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080086318A1 (en) * | 2006-09-21 | 2008-04-10 | Apple Inc. | Lifestyle companion system |
US20090106040A1 (en) * | 2007-10-23 | 2009-04-23 | New Jersey Institute Of Technology | System And Method For Synchronous Recommendations of Social Interaction Spaces to Individuals |
US20100082357A1 (en) * | 2008-09-30 | 2010-04-01 | Nokia Corporation | Methods, apparatuses, and computer program products for providing activity coordination services |
US20110107232A1 (en) * | 2009-10-29 | 2011-05-05 | BBE Partners LLC | Directory and notification system for college students based on individual user profiles |
US20120054666A1 (en) * | 2010-08-31 | 2012-03-01 | Baird-Smith Anselm P | Networked system with supporting media access and social networking |
US20120246302A1 (en) * | 2011-03-22 | 2012-09-27 | Milestone Project Inc. | System and methodology for creating and using contextual user profiles |
US20120266258A1 (en) * | 2011-04-12 | 2012-10-18 | Teletech Holdings, Inc. | Methods for providing cross-vendor support services |
US20130191372A1 (en) * | 2010-04-19 | 2013-07-25 | Yofay Kari Lee | Personalized Structured Search Queries for Online Social Networks |
US20130311324A1 (en) * | 2012-05-17 | 2013-11-21 | Luvocracy Inc. | Zero Click Commerce Systems |
US20140012918A1 (en) * | 2011-03-29 | 2014-01-09 | Nokia Corporation | Method and apparatus for creating an ephemeral social network |
US20140075385A1 (en) * | 2012-09-13 | 2014-03-13 | Chieh-Yih Wan | Methods and apparatus for improving user experience |
US20140136323A1 (en) * | 2012-08-11 | 2014-05-15 | Guangsheng Zhang | System and methods for advertising based on user intention detection |
US20140229487A1 (en) * | 2011-06-13 | 2014-08-14 | The Research Foundation Of State University Of New York | System and method for user preference augmentation through social network inner-circle knowledge discovery |
US8825658B1 (en) * | 2012-03-27 | 2014-09-02 | Google Inc. | Organizing indications of approval for collections |
US20140257890A1 (en) * | 2013-03-05 | 2014-09-11 | Gartner, Inc. | Methods and systems for improving engagement with a recommendation engine that recommends items, peers, and services |
US20150032814A1 (en) * | 2013-07-23 | 2015-01-29 | Rabt App Limited | Selecting and serving content to users from several sources |
US20150100570A1 (en) * | 2013-10-09 | 2015-04-09 | Foxwordy, Inc. | Excerpted Content |
US20150248721A1 (en) * | 2014-03-03 | 2015-09-03 | Invent.ly LLC | Recommendation engine with profile analysis |
US20150262219A1 (en) * | 2013-03-15 | 2015-09-17 | Thermodynamic Design, Llc | Customizable data management system |
US9177291B2 (en) * | 2012-01-11 | 2015-11-03 | Facebook, Inc. | Chaining connection requests |
US20160171588A1 (en) * | 2014-12-11 | 2016-06-16 | Facebook, Inc. | Providing product advice recommendation |
US20160171582A1 (en) * | 2014-12-11 | 2016-06-16 | Facebook, Inc. | Providing product advice recommendation |
US20160180403A1 (en) * | 2014-12-23 | 2016-06-23 | Cognizant Technology Solutions India Pvt. Ltd. | System and method for creating comprehensive profile of one or more customers of an organization |
US20170011445A1 (en) * | 2015-03-03 | 2017-01-12 | Go Daddy Operating Company, LLC | Business asset search for recommending legal service providers |
US20170011446A1 (en) * | 2015-03-03 | 2017-01-12 | Go Daddy Operating Company, LLC | Legal service provider recommendations for product ideas |
US20170083962A1 (en) * | 2015-09-18 | 2017-03-23 | Rovi Guides, Inc. | Methods and systems for recommending gifts using a supplemental profile |
US20170083963A1 (en) * | 2015-09-18 | 2017-03-23 | Rovi Guides, Inc. | Methods and systems for providing gift recommendations |
US20170177589A1 (en) * | 2015-12-17 | 2017-06-22 | Facebook, Inc. | Suggesting Tags on Online Social Networks |
US9704202B1 (en) * | 2008-02-18 | 2017-07-11 | Sprint Communications Company L.P. | Blending device-based recommendations |
US9947036B2 (en) * | 2014-09-24 | 2018-04-17 | Paypal, Inc. | Gift suggestion system |
US20180315116A1 (en) * | 2017-05-01 | 2018-11-01 | Walmart Apollo, Llc | System for autonomous configuration of product displays |
US20190005547A1 (en) * | 2017-06-30 | 2019-01-03 | Facebook, Inc. | Advertiser prediction system |
US10191937B2 (en) * | 2013-10-11 | 2019-01-29 | Samsung Electronics Co., Ltd. | System and method for sharing profile image card |
US20190050774A1 (en) * | 2017-08-08 | 2019-02-14 | General Electric Company | Methods and apparatus to enhance emotional intelligence using digital technology |
US20190080425A1 (en) * | 2017-09-12 | 2019-03-14 | TrendGrab, Inc | Method and Systems for Providing On-demand Real Estate Related Products and Services |
US10275404B2 (en) * | 2001-04-19 | 2019-04-30 | Amazon Technologies, Inc. | Play history based detection of similar digital works or work creators |
US20190244308A1 (en) * | 2018-02-07 | 2019-08-08 | BlackBook Media Inc. | Managing event databases using histogram-based analysis |
US10666921B2 (en) * | 2013-08-21 | 2020-05-26 | Verizon Patent And Licensing Inc. | Generating content for a virtual reality system |
US11010436B1 (en) * | 2018-04-20 | 2021-05-18 | Facebook, Inc. | Engaging users by personalized composing-content recommendation |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6980870B1 (en) | 2000-08-28 | 2005-12-27 | Mok Mimi T | Method and apparatus for optimizing, managing and scheduling personal relationships |
US6865538B2 (en) * | 2002-08-20 | 2005-03-08 | Autodesk, Inc. | Meeting location determination using spatio-semantic modeling |
JP2010033484A (en) * | 2008-07-31 | 2010-02-12 | Fujitsu Ltd | Banquet place recommendation device and banquet place recommendation program |
JP5730741B2 (en) * | 2011-10-19 | 2015-06-10 | 日本電信電話株式会社 | Topic recommendation device, method and program |
US9299060B2 (en) * | 2012-10-12 | 2016-03-29 | Google Inc. | Automatically suggesting groups based on past user interaction |
US9037578B2 (en) | 2012-12-03 | 2015-05-19 | Wellclub, Llc | Content suggestion engine |
US9948689B2 (en) * | 2013-05-31 | 2018-04-17 | Intel Corporation | Online social persona management |
US20150248651A1 (en) * | 2014-02-28 | 2015-09-03 | Christine E. Akutagawa | Social networking event planning |
CN107209019B (en) * | 2015-01-30 | 2021-01-15 | 索尼公司 | Information processing system and control method |
JP6682191B2 (en) * | 2015-04-24 | 2020-04-15 | 株式会社Nttドコモ | Search device, search system and program |
US10665229B2 (en) * | 2015-06-12 | 2020-05-26 | Sony Corporation | Information processing device, information processing method, and program |
JP6565886B2 (en) * | 2016-12-07 | 2019-08-28 | トヨタ自動車株式会社 | Information providing apparatus and information providing program |
US10565229B2 (en) * | 2018-05-24 | 2020-02-18 | People.ai, Inc. | Systems and methods for matching electronic activities directly to record objects of systems of record |
-
2018
- 2018-09-14 WO PCT/IB2018/057066 patent/WO2020053631A1/en unknown
- 2018-09-14 EP EP18785437.7A patent/EP3850573A1/en active Pending
- 2018-09-14 CA CA3019019A patent/CA3019019A1/en active Pending
- 2018-09-14 US US16/086,281 patent/US11488264B2/en active Active
- 2018-09-14 JP JP2019538686A patent/JP7278213B2/en active Active
-
2021
- 2021-03-09 IL IL281365A patent/IL281365A/en unknown
-
2022
- 2022-11-01 US US17/978,711 patent/US20230325943A1/en active Pending
Patent Citations (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10275404B2 (en) * | 2001-04-19 | 2019-04-30 | Amazon Technologies, Inc. | Play history based detection of similar digital works or work creators |
US20080086318A1 (en) * | 2006-09-21 | 2008-04-10 | Apple Inc. | Lifestyle companion system |
US20090106040A1 (en) * | 2007-10-23 | 2009-04-23 | New Jersey Institute Of Technology | System And Method For Synchronous Recommendations of Social Interaction Spaces to Individuals |
US9704202B1 (en) * | 2008-02-18 | 2017-07-11 | Sprint Communications Company L.P. | Blending device-based recommendations |
US20100082357A1 (en) * | 2008-09-30 | 2010-04-01 | Nokia Corporation | Methods, apparatuses, and computer program products for providing activity coordination services |
US20110107232A1 (en) * | 2009-10-29 | 2011-05-05 | BBE Partners LLC | Directory and notification system for college students based on individual user profiles |
US20130191372A1 (en) * | 2010-04-19 | 2013-07-25 | Yofay Kari Lee | Personalized Structured Search Queries for Online Social Networks |
US20120054666A1 (en) * | 2010-08-31 | 2012-03-01 | Baird-Smith Anselm P | Networked system with supporting media access and social networking |
US20120246302A1 (en) * | 2011-03-22 | 2012-09-27 | Milestone Project Inc. | System and methodology for creating and using contextual user profiles |
US20140012918A1 (en) * | 2011-03-29 | 2014-01-09 | Nokia Corporation | Method and apparatus for creating an ephemeral social network |
US20120266258A1 (en) * | 2011-04-12 | 2012-10-18 | Teletech Holdings, Inc. | Methods for providing cross-vendor support services |
US20140229487A1 (en) * | 2011-06-13 | 2014-08-14 | The Research Foundation Of State University Of New York | System and method for user preference augmentation through social network inner-circle knowledge discovery |
US9177291B2 (en) * | 2012-01-11 | 2015-11-03 | Facebook, Inc. | Chaining connection requests |
US8825658B1 (en) * | 2012-03-27 | 2014-09-02 | Google Inc. | Organizing indications of approval for collections |
US20130311324A1 (en) * | 2012-05-17 | 2013-11-21 | Luvocracy Inc. | Zero Click Commerce Systems |
US20140136323A1 (en) * | 2012-08-11 | 2014-05-15 | Guangsheng Zhang | System and methods for advertising based on user intention detection |
US20140075385A1 (en) * | 2012-09-13 | 2014-03-13 | Chieh-Yih Wan | Methods and apparatus for improving user experience |
US20140257890A1 (en) * | 2013-03-05 | 2014-09-11 | Gartner, Inc. | Methods and systems for improving engagement with a recommendation engine that recommends items, peers, and services |
US20150262219A1 (en) * | 2013-03-15 | 2015-09-17 | Thermodynamic Design, Llc | Customizable data management system |
US20150032814A1 (en) * | 2013-07-23 | 2015-01-29 | Rabt App Limited | Selecting and serving content to users from several sources |
US10666921B2 (en) * | 2013-08-21 | 2020-05-26 | Verizon Patent And Licensing Inc. | Generating content for a virtual reality system |
US20150100570A1 (en) * | 2013-10-09 | 2015-04-09 | Foxwordy, Inc. | Excerpted Content |
US10191937B2 (en) * | 2013-10-11 | 2019-01-29 | Samsung Electronics Co., Ltd. | System and method for sharing profile image card |
US20150248721A1 (en) * | 2014-03-03 | 2015-09-03 | Invent.ly LLC | Recommendation engine with profile analysis |
US9947036B2 (en) * | 2014-09-24 | 2018-04-17 | Paypal, Inc. | Gift suggestion system |
US20160171588A1 (en) * | 2014-12-11 | 2016-06-16 | Facebook, Inc. | Providing product advice recommendation |
US20160171582A1 (en) * | 2014-12-11 | 2016-06-16 | Facebook, Inc. | Providing product advice recommendation |
US20160180403A1 (en) * | 2014-12-23 | 2016-06-23 | Cognizant Technology Solutions India Pvt. Ltd. | System and method for creating comprehensive profile of one or more customers of an organization |
US20170011446A1 (en) * | 2015-03-03 | 2017-01-12 | Go Daddy Operating Company, LLC | Legal service provider recommendations for product ideas |
US20170011445A1 (en) * | 2015-03-03 | 2017-01-12 | Go Daddy Operating Company, LLC | Business asset search for recommending legal service providers |
US20170083963A1 (en) * | 2015-09-18 | 2017-03-23 | Rovi Guides, Inc. | Methods and systems for providing gift recommendations |
US20170083962A1 (en) * | 2015-09-18 | 2017-03-23 | Rovi Guides, Inc. | Methods and systems for recommending gifts using a supplemental profile |
US20170177589A1 (en) * | 2015-12-17 | 2017-06-22 | Facebook, Inc. | Suggesting Tags on Online Social Networks |
US20180315116A1 (en) * | 2017-05-01 | 2018-11-01 | Walmart Apollo, Llc | System for autonomous configuration of product displays |
US20190005547A1 (en) * | 2017-06-30 | 2019-01-03 | Facebook, Inc. | Advertiser prediction system |
US20190050774A1 (en) * | 2017-08-08 | 2019-02-14 | General Electric Company | Methods and apparatus to enhance emotional intelligence using digital technology |
US20190080425A1 (en) * | 2017-09-12 | 2019-03-14 | TrendGrab, Inc | Method and Systems for Providing On-demand Real Estate Related Products and Services |
US20190244308A1 (en) * | 2018-02-07 | 2019-08-08 | BlackBook Media Inc. | Managing event databases using histogram-based analysis |
US11010436B1 (en) * | 2018-04-20 | 2021-05-18 | Facebook, Inc. | Engaging users by personalized composing-content recommendation |
Also Published As
Publication number | Publication date |
---|---|
JP2022528021A (en) | 2022-06-08 |
CA3019019A1 (en) | 2020-03-14 |
IL281365A (en) | 2021-04-29 |
US20210233182A1 (en) | 2021-07-29 |
WO2020053631A1 (en) | 2020-03-19 |
JP7278213B2 (en) | 2023-05-19 |
US11488264B2 (en) | 2022-11-01 |
EP3850573A1 (en) | 2021-07-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230325943A1 (en) | Interaction recommendation engine | |
US9432326B2 (en) | Question server to facilitate communication between participants | |
US9749233B2 (en) | Techniques for smart data routing | |
US9767218B2 (en) | Indexing edge-ranked based partitions | |
US9569529B2 (en) | Personalizing an online service based on data collected for a user of a computing device | |
US10375242B2 (en) | System and method for user notification regarding detected events | |
US20140040377A1 (en) | Dynamic information streams in a social network platform | |
US20130317828A1 (en) | Content ranking and serving on a multi-user device or interface | |
US20220103787A1 (en) | Dynamically modifying live video streams for participant devices in digital video rooms | |
US20140280629A1 (en) | Method and system for optimizing composer prompts for posting in a social networking system | |
WO2016134359A1 (en) | Automated user profile matching and communication | |
US20190050945A1 (en) | Auto-suggestion for group activities based on combined user data sets | |
US20160277538A1 (en) | Method and system for matching profile records | |
US10659299B1 (en) | Managing privacy settings for content on online social networks | |
US9241015B1 (en) | System and method for suggesting discussion topics in a social network | |
US20220075826A1 (en) | Contact generatio device | |
US10135773B2 (en) | Communications system | |
JP7278214B2 (en) | alternating current generator | |
WO2016187338A1 (en) | Multi-component data object | |
CN112513911A (en) | Location prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |