WO2014074426A1 - Détermination d'un sentiment social à l'aide de données physiologiques - Google Patents

Détermination d'un sentiment social à l'aide de données physiologiques Download PDF

Info

Publication number
WO2014074426A1
WO2014074426A1 PCT/US2013/068205 US2013068205W WO2014074426A1 WO 2014074426 A1 WO2014074426 A1 WO 2014074426A1 US 2013068205 W US2013068205 W US 2013068205W WO 2014074426 A1 WO2014074426 A1 WO 2014074426A1
Authority
WO
WIPO (PCT)
Prior art keywords
physiological data
data
analyzing
persons
physiological
Prior art date
Application number
PCT/US2013/068205
Other languages
English (en)
Inventor
Daniel H. Lange
Original Assignee
Intel Corporation
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Intel Corporation filed Critical Intel Corporation
Priority to CN201380004601.3A priority Critical patent/CN104145272B/zh
Priority to JP2014549012A priority patent/JP2015502624A/ja
Priority to DE112013000324.4T priority patent/DE112013000324T5/de
Priority to GB1411008.4A priority patent/GB2511978A/en
Priority to KR1020147017646A priority patent/KR101617114B1/ko
Priority to RU2014126373A priority patent/RU2014126373A/ru
Publication of WO2014074426A1 publication Critical patent/WO2014074426A1/fr
Priority to IN4566CHN2014 priority patent/IN2014CN04566A/en

Links

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
    • G06Q30/0241—Advertisements
    • G06Q30/0242—Determining effectiveness of advertisements
    • 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
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass

Definitions

  • This relates to crowd sourced data collection.
  • social sentiment is constructed based on various data provided by users online, such as text strings and click streams. Even these rather limited forms of data provide valuable tools for businesses and other groups (e.g., governments) for marketing their products, identifying new opportunities and needs, managing their reputations, and soliciting public opinions.
  • FIG. 1 is a flowchart illustrating a method for predicting social sentiment of one or more persons using physiological data, in accordance with certain
  • FIG. 2 illustrates a network used for predicting social sentiment of one or more persons using physiological data, in accordance with certain embodiments.
  • FIG. 3 is a block diagram of an exemplary computing system that may be utilized to practice aspects of the present disclosure.
  • FIG. 4 shows a social sentiment map according to one embodiment.
  • Physiological data may be used for monitoring and predicting social sentiment of a plurality of persons.
  • the term "physiological data” will be understood to mean physiological data, psychophysiological data, or a combination thereof.
  • a method involves receiving physiological data at a computing device, analyzing the physiological data, determining indicator data relating to social sentiment, such that the indicator data is determined from the physiological data, and transmitting the indicator data.
  • the computing device may include a server or some other remote computing device.
  • the physiological data may be received over a network and transmitted over the same or different network.
  • the indicator data may include advance warning information and be transmitted, in certain embodiments, back to the users.
  • physiological data is received from a person using a single sensor. This may be done for a plurality of people, where a given person's data is received a single sensor.
  • multiple sensors may be used to receive data from a person.
  • a user device may be equipped with only a single sensor for obtaining physiological data from the user.
  • Even a single sensor implementation may be able to provide various types of physiological data, such as a body temperature and a heart rate.
  • a single sensor may serve as a multifunctional sensor. Operations of the sensor, and/or the sensor(s) itself, may be hidden from a user, such that physiological data is collected in a covert manner without any specific action from the user and possibly without knowledge of the user.
  • Analyzing physiological data may involve aggregating data from multiple persons to provide a more comprehensive analysis.
  • analyzing physiological data may involve accounting for current events, personal activities, and/or physical parameters of a person.
  • physical parameters may include a health condition, age, gender, weight, body fat percentage, genetics, biometric, and physical location. These parameters may be combined with the physiological data or used to interpret the physiological data.
  • Analyzing physiological data may involve predicting one or more connections between two or more persons. Connections may be genetic, familial, and/or social and may be based on the physiological data of all users or a subset of users. Furthermore, analyzing the physiological data may involve analyzing a change in the physiological data due to some external stimulus, such as visual stimulus, audio stimulus, and/or other sensory stimulus. In certain embodiments, a method may also involve determining a response differential between two or more persons based on the presence or absence of a variable.
  • a system for predicting social sentiment of one or more persons using physiological data may include a memory for storing data, a receiving module, an analyzing module, an indicator data determining module, and a transmitting module, as well as a processor for executing the receiving module, analyzing module, indicator data determining module, transmitting module, and a display module.
  • the processor may be adapted to receive physiological data from one or more persons at a computing device, analyze the physiological data, determine indicator data relating to social sentiment of the one or more persons, with the indicator data being determined from the physiological data, and display and/or transmit the indicator data.
  • the computing device may be a server, and the physiological data may be received by the receiving module and transmitted over a network by the transmitting module.
  • the physiological data may be received from one or more persons using a single sensor per person.
  • the physiological data may be received seamlessly from a person using a single or multiple sensors. When multiple persons are involved, they may have a relationship with one other.
  • Analyzing the physiological data may involve aggregating data from a plurality of persons.
  • analyzing the physiological data may include taking current events, personal activities, and/or physical parameters of a person into account. Physical parameters may include, for example, one or more of health condition, age, gender, weight, body fat percentage, genetics, biometrics, and physical location.
  • the indicator data includes advance warning information.
  • a computer-readable storage medium may have a program embodied thereon, executable by a processor to perform a method for monitoring and predicting social sentiment of one or more persons using physiological data.
  • the method may involve receiving the physiological data from one or more persons at a computing device, analyzing the physiological data, determining indicator data relating to social sentiment of the one or more persons, with the indicator data being determined from the physiological data, and displaying and/or transmitting the indicator data.
  • FIG. 1 is a flowchart illustrating a sequence 100 for predicting social sentiment of one or more persons (i.e., users) using physiological data, in accordance with certain embodiments.
  • the sequence may be implemented in software, firmware, and/or hardware.
  • software and firmware embodiments it may be implemented using computer executed instructions stored on one or more non- transitory computer readable media, such as optical, magnetic, or semiconductor storages.
  • Social sentiment typically contains information about these users, their social and/or geographic environments, and various groups that these persons naturally belong to or are assigned to by applications of this method. As further explained herein, this information may be provided back to the users or used to generate custom content for the users, such as target advertisements and information about various related services. Social sentiment may be shared with other parties, such as businesses and government agencies for example, in order to provide services to the users. Various security and privacy features may be provided to ensure controlled dissemination of the sensitive information to minimize privacy concerns.
  • Social sentiment has been gaining increased interest with the rise of Internet communication technologies and new forms of communications such as blogs and social networks.
  • Social sentiment may involve reviews, ratings, and recommendations of other users, business, policies, and other aspects of everyday life.
  • social sentiment is constructed based on various data provided by users online, such as text strings and click streams.
  • Even these rather limited forms of data provide valuable tools for businesses and other groups (e.g., governments) for marketing their products, identifying new opportunities and needs, managing their reputations, and soliciting public opinions.
  • While many techniques have been proposed to filter the noise created by random and unrelated information widely spread on the Internet, there are many limitations in the very nature of the available data.
  • Physiological data may be collected through user devices. This data may be transmitted to servers for aggregating and analyzing the data in more
  • physiological data examples include heart rate, body impedance, body temperature, and so forth.
  • Physiological data may be categorized as objective data since it corresponds to objective physical characteristics of the users' bodies. This type of data is easily distinguishable from subjective data types, such as verbal and written expressions in a form of blog posts and news feeds. The subjective data may be easily skewed by various other factors that may be impossible to separate analytically from each other. As such, physiological data may be generally much more valuable than other data traditionally used to construct social sentiment.
  • physiological data During analysis of physiological data (and even while obtaining such data), it may be supplemented with other data, such as users' geographic location, their demographic information, click-stream data, pre-filled and post-filled surveys, external data feeds, and many other types and forms of data. Collectively, all data feeds may be used to construct and refine social sentiment. It should be noted that in some embodiments, social sentiment may only be an intermediate product provided by the proposed methods and systems and may be used to develop and provide additional services and products to the users and users' communities.
  • Sequence 100 may commence with receiving physiological data from one or more persons at a computing device in operation 102.
  • the received information may be sent by one or more user devices. It should be noted that multiple users may share the same user device. These devices may be used to obtain
  • Some exemplary user devices may include personal computers, laptops, mobile telephones, etc.
  • the user devices may be equipped with one or more sensors for collecting such data as a part of a dedicated data collection operation (e.g., prompting a user to operate or interact with a sensor) or as a part of another operation (e.g., while obtaining biometric information for authentication purposes, which also may involve capturing one or more of EKG, body fat percentage, body temperature, pulse, any other physiological data, etc.).
  • Physiological data obtained at a user device level may be then transmitted to a server.
  • the transmission may be performed over one or more networks, further described with reference to FIG. 2.
  • the server is defined as a computer system that is separate from a user device used for collecting physiological data.
  • a server typically does not have the capability of obtaining physiological data directly from one or more persons (i.e., it may not be equipped with a sensor in some embodiments). Instead, the server is communicatively coupled with multiple user devices for collecting physiological data from these devices.
  • one of the user devices used for collecting physiological data may perform some or all server functions described herein.
  • FIG. 2 illustrates that there are two servers used; however any number of servers may be used. It is important to note that, in certain embodiments, a server is configured to collect and aggregate such data from multiple users. As described below, the data may reflect relationships between some users or be analyzed in light of some predefined relationships. Sometimes collection and analysis of physiological data is referred to as "physiological polling.”
  • the sequence 100 may proceed with analyzing physiological data.
  • this operation may be combined with determining indicator data relating to social sentiment of the one or more persons, which is presented below as operation 106.
  • the analyzing operation may involve grouping some physiological data, combining it with and/or, more generally, analyzing it in light of other data, and producing some form of an output.
  • Operation 104 may involve various optional embodiments, which will now be described in more detail. It should be noted that each of these additional sub-operations may be practiced by itself or combined with various other operations.
  • analyzing physiological data involves aggregating such data from multiple users (i.e., a plurality of persons (optional operation 104a)). Unlike analyzing data from a single user, collecting data from multiple users allows for a more comprehensive analysis of the physiological data of an entire group and even for individual users. For example, an indication that one user has a fever has limited value, while an indication that a large group of people in the same geographic location has such a condition may be indicative of an epidemic, for example. In addition to being warned about their own fever conditions, the users will also appreciate information about an epidemic. For example, such collective information may be used for dispatching medical services and warning all users to avoid possibly dangerous areas.
  • a specific example may provide a better understanding of some implementations of this optional operation.
  • a user device may capture a body temperature of its user, for example, during periodic contact of the user with one or more sensors.
  • the data is sent to a server, which has some additional information about the user, such as a specific geographic location of the user.
  • the server may search for and even request similar data corresponding to other users in this location.
  • the comprehensive analysis of the data may help to determine trends (e.g., epidemic trends etc.) and issue warning messages.
  • physiological data may be received from multiple users who have various relationships with one other.
  • Some examples of such relationships include family ties, social network, geographic locations, and certain demographic groupings (e.g., by gender, age, and so forth).
  • the data may be grouped, categorized, and analyzed to reflect these relationships.
  • physiological data is grouped according to personal space maps and/or geographic position maps.
  • Personal space maps are identified based on "emotional proximity" of the users, frequency of their interactions, claimed professional/social/family relationships, and other related factors. Personal space maps may help to analyze physiological data in a specific context provided by these factors and to draw appropriate conclusions, for example, about the social dynamics of a specific group.
  • physiological data itself is used in identifying personal space maps.
  • mapping in terms of interpersonal and geographical/physical relationships, other type of relationships may be mapped and analyzed. These types of relationship may include but are not limited to relationships to organizations or hierarchies (e.g., businesses, armies, religious organizations, and political parties, etc.) and so forth.
  • Geographic position maps group people based on their physical proximity to each other and/or some geographic boundaries, such as city limits for example.
  • Various geographic tracking systems such as a global positioning system (GPS) and cell phone usage or triangulation may be used to associate individuals with certain areas on these maps.
  • GPS global positioning system
  • GOOGLE LATITUDE® service available from Google in Menlo Park, CA may be used for such purposes.
  • geographic position maps are combined with personal space maps to perform a more encompassing analysis of physiological data.
  • geographic position maps may be used to revise personal space maps. Without being restricted to any particular theory, it is often believed that people who are in close physical proximity tend to influence each other more than people located far away from each other. Of course, this theory should account for availability and usage of communication tools by users that would further influence the proposed dependence of the two types of maps. It is envisioned that other types of maps may be used as well, such as maps built on demographic factors and certain
  • Grouping maps may be relatively static (e.g., city limits, family relationships) or dynamic (e.g., physical proximity of users).
  • Analyzing physiological data may also involve aggregating and examining/analyzing physiological data over periods of time. This may involve determining various time trends, since data tends to vary over time. Some statistical methods may be applied for such purposes.
  • the time dependence of physiological data is an important factor to consider in constructing algorithms for analyzing physiological data. For example, after experiencing a certain stimulation (e.g., seeing a visual image), a human body may go through various stages. The body may go through an initial reaction, which may be referred to as an initial "shock.” This may encompass either a strong or weak reaction, and a positive or negative reaction, such as panic, hate, pleasure, etc. During this initial period, the human body may generate more pronounced signals associated with the received stimulation, and physiological data collected tends to be the most relevant.
  • analyzing physiological data involves accounting for current events (optional operation 104b) or, more specifically, correlating physiological data to the current events to provide some understanding and meaning (which otherwise may be relatively abstract data).
  • Current events may be defined as various external data (usually presented in a form of some stimulus) that may influence physiological data or at least put physiological data into some context. Examples of such current events may involve global events, such as major political or financial news, disasters, wars and coups, as well as local events, such as a death or birth in the family and special events (e.g., birthdays, weddings, promotions, etc.).
  • Trial balloon is information shared with a specific purpose of observing the reaction of an audience (i.e., users of the system).
  • Trial balloons may be used by businesses to send out press releases to judge reaction by customers (e.g., anticipated product releases) or they can be used by politicians or other entities deliberately leaking information on a policy change that may be under consideration.
  • observing public reaction was difficult to accomplish, typically involving expensive and often inaccurate surveys.
  • Novel combinations of information and sensor technologies may be used to capture relevant data in an efficient and precise manner. Specifically, once information is "leaked" in the initial stages of the trial balloon process, users' physiological data may be immediately collected.
  • This information may be complemented by other data points, such as information reflecting how soon the information reached each user and levels of interest in the information by the users (e.g., click stream data).
  • physiological data is generally more reflective than other forms of users' responses (e.g., responses to survey questions etc.) and such data may be collected in a covert manner, which makes the entire process less intrusive and efficient. In other words, some or all users may not even be aware that they are being monitored.
  • analyzing physiological data includes analyzing changes in the physiological data to external stimuli (optional operation 104c).
  • Some examples of such stimuli include visual images, audio, and various other sensory stimuli (smell, touch, etc.). This type of operation may overlap with other similar operations.
  • External stimuli may be provided by a user device using its video and audio outputs.
  • the user device may also be equipped with a sensor.
  • users' physiological data may be collected and synchronized with an image of a computer or cell phone display.
  • a photo of a political candidate may be sent to user devices and, upon users' viewing of the photo, the data is collected and received on the server. This viewing/data collection may be performed over a period of time in comparison to more traditional mass media options. This, in turn, adds to the flexibility of this method.
  • a particular implementation of this optional operation 104c is soliciting donations for various causes. Different users may be receptive to different causes. These correlations may be established by providing various external stimuli associated with these different causes and selecting ones that generate the most pronounced emotions based on the received physiological data. The solicitation may then be tailored to the users based on their different reactions to the causes.
  • analyzing physiological data involves taking personal activities into account (optional operation 104d). Similar to current events described above with reference to optional operation 104b, personal activities may help to provide some reflection on physiological data and help to better understand this data. Some examples of personal activities include social network usage (e.g., postings, messages, status updates, etc.), click streams, search-streams from user devices, and other types of data collected by user devices (e.g., weight monitoring applications, physical activity applications, schedules, to-do lists, and so forth).
  • social network usage e.g., postings, messages, status updates, etc.
  • click streams e.g., click streams, search-streams from user devices
  • other types of data collected by user devices e.g., weight monitoring applications, physical activity applications, schedules, to-do lists, and so forth.
  • the operation may involve designing and providing to users specific surveys for supplementing and interpreting collected physiological data. For example, a user device may register that its user has a fever. The user device may then prompt the user to answer certain health related questions to help identifying and providing a precise diagnosis and/or prognosis. In some embodiments, the system may analyze other user activities (e.g., intense physical activity registered by another application etc.) to explain the data. Moreover, the system may detect the user typing a message on the device indicating some pointers to the user's heath status (e.g., asking for a sick day).
  • user activities e.g., intense physical activity registered by another application etc.
  • Modern social networks present ample sources of information about users and their environments. A large number of tech savvy people are active members of social networks. Methods and systems disclosed herein may be designed to continuously collect information about its users from such sources. For example, respective user accounts may be associated with a specifically designed web crawler to collect information pertaining to personal activities of that user.
  • analyzing physiological data involves accounting for physical parameters of a user (optional operation 104e).
  • physical parameters include health conditions, age, gender, weight, genetics, biometric, and physical location. There may be some overlap with other analyzing operations.
  • a user's physical location may be associated with current events, or personal activities such as jogging and the like.
  • users may object to the usage and sharing of such personal data.
  • Some proposed methods and systems provide for various security measures limiting access to this data, as set by the user or other criteria.
  • a user device is equipped with a GPS device or other types of location devices and/or systems (e.g., cell phone usage, cell phone triangulation system, Wi-Fi hubs, and Internet Protocol (IP) addresses).
  • This location information may be used to form groups for analyzing the data based on specific geographic locale. For example, a strong deviation in certain physiological parameters in a particular region may be indicative of an epidemic or allergy outbreak. People may be warned to avoid these areas.
  • Some physical parameters may be used to generate and update other parameters. For example, physical location may be used to determine local weather conditions (e.g., outside temperature, rain etc.) and then correlate this information with physiological data to determine the effects of one on another. In a specific example, a cold temperature may explain a local outbreak of a fever.
  • one or more heart beat authentication techniques are implemented to provide physical parameters of a user. These techniques can be implemented on a user device equipped with near-field communication (NFC) capabilities. For example, a process may include obtaining heart beat information that is then used to provide mood/sentiment feedback. This feedback can be shared with a service provider as an indication of the level of satisfaction (or lack thereof) from a particular transaction completed by the user (e.g., a purchase of a product, etc.). In some embodiments, coupons (or anything else) may be sent to one or more individuals based on mood or other data. This may be accomplished via e-mail, SMS, snail mail, or any other suitable method.
  • NFC near-field communication
  • analyzing physiological data involves predicting a connection or relationship between two or more persons (optional operation 104f).
  • connection/relationship types include a genetic connection, a familial connection, a social connection etc. Strong correlation of certain
  • physiological data may be indicative that two people have similar genetic make-up, which may further indicate that the two people are relatives. Furthermore, this information may be used to identify possible organ donors even though two people may not necessarily be related. Also, some physiological data may predict positive or negative relationships of two or more people in various social and professional settings, such as marriage, friendship, or other relationships or affiliations.
  • Embodiments herein may also be applied to flash mobs, protests, other gatherings, and so forth.
  • a method includes determining a response differential between two or more persons based on a presence or absence of one or more variables.
  • physiological data corresponding to one or more users are compared to the same type of data of one or more other users.
  • the same type of comparison may be implemented over time for the same group of one or more individuals.
  • method 100 may proceed with determining indicator data relating to social sentiment of one or more persons during operation 106.
  • physiological data may be a more advanced predictor of social sentiment than other types of user's input, such as blog postings and social network postings.
  • This indicator data may include some kind of advance warning information.
  • the indicator data may be then transmitted back to the user device for displaying on a user interface in operation 108.
  • the indicator data may include some interpretation of the physiological data, such as a preliminary medical diagnosis, a health tip, mental state, mood, etc.
  • a system may be configured to compile a health dashboard on a user device based on various data points collected over time.
  • indicator data will include some information that would encourage users to continue providing physiological data.
  • the indictor data may be also valuable to entities other than the users providing the data.
  • the data may be transmitted to marketing agencies, government agencies, military authorities, medical entities, and other types of entities interested in the data.
  • Various financial and security arrangements may be implemented in this system.
  • government agencies may be interested in the health or other status of various regions, and collecting physiological data may help such agencies in this regard.
  • the indictor data may be used to customize other content provided back to the user device, such as to target advertisements.
  • Various examples of a sequence 100 described above may be implemented for different applications. For example, similar to social network posts of status and relationship information, users may be interested in sharing their health and mental state information with their networks. For example, physiological data may be interpreted to determine a user's mood, which may be a useful and/or fun or entertaining fact to share with others. There could be clinical uses for broadcasting mood. Someone trying to stop smoking, stop overeating, or cure some other addiction or undesirable behavior, might be able to implement this aspect so that friends or a therapist can monitor their mood and provide moral support.
  • Other types of data may be also used for entertainment, social, professional, and medical reasons. For example, health conditions of an employee may prompt an employer to offer a day off, with the overall goal to increase the person's productivity. Indications that many people in a particular area, affiliation, or network are in a bad "mood" or poor health may prompt others to stay away from this area.
  • FIG. 2 illustrates an exemplary network segment 200 in which various embodiments of the method described above may be implemented.
  • multiple user devices or clients 202a-202d may be communicatively coupled with network 204 to provide various types of physiological data to servers 206 and 208 hosted by a service provider.
  • User devices 202a-202d may be equipped with one or more sensors for collecting information from their respective users. In certain embodiments, at least some of user devices 202a-202d includes only one sensor.
  • Network 204 may take any suitable form, such as a wide area network (WAN) or Internet and/or one or more local area networks (LANs).
  • the network 204 may include any suitable number and type of devices (e.g., routers, switches, etc.) for forwarding requests from respective clients to a particular server application, forwarding application results back to the requesting clients, or forwarding data between various servers.
  • Methods described above may be practiced in a wide variety of network environments (represented by network 204), telecommunications networks, wireless networks, mobile networks, and the like.
  • the computer program instructions may be stored in any type of computer-readable media, and may be executed according to a variety of computing models, including a client/server model, a peer-to-peer model, on a stand-alone computing device, or according to a distributed computing model in which various of the functionalities described herein may be affected or employed at different locations.
  • FIG. 3 illustrates a computer system 300 that, when appropriately configured or designed, can be used for receiving physiological data from one or more persons, analyzing the physiological data, determining indicator data relating to social sentiment of the one or more persons from the physiological data, and displaying and/or transmitting the indicator data.
  • Computer system 300 includes any number of processors 302 (also referred to as central processing units (CPUs)) that are coupled to storage devices, including primary storage 306 (typically a random access memory, (RAM)) and primary storage 304 (typically a read only memory (ROM)).
  • processors 302 also referred to as central processing units (CPUs)
  • primary storage 306 typically a random access memory, (RAM)
  • primary storage 304 typically a read only memory (ROM)
  • Processors 302 may be of various types, including microcontrollers and microprocessors, such as programmable devices (e.g., CPLDs and FPGAs), and non-programmable devices, such as gate array ASICs or general-purpose microprocessors.
  • Primary storage 304 acts to transfer data and instructions uni- directionally to the processor 302 and primary storage 306 is typically used to transfer data and instructions in a bi-directional manner. Both of these primary storage devices may include any suitable computer-readable media, such as those described herein.
  • a mass storage device 308 is also coupled bi-directionally to processor 302 and provides additional data storage capacity, and may include any of the computer-readable media described herein.
  • Mass storage device 308 may be used to store programs, data and the like and is typically a secondary storage medium (such as a hard disk). It will be appreciated that the information retained within the mass storage device 308, may, in appropriate cases, be incorporated in standard fashion as part of primary storage 306 as virtual memory. A specific mass storage device such as a CD-ROM 313 may also pass data uni-directionally to the processor 302.
  • Processor 302 is also communicatively coupled with an interface 310 that communicatively couples with one or more input/output devices, such as video monitors, track balls, mice, keyboards, microphones, touch-sensitive displays, transducer card readers, magnetic or paper tape readers, tablets, styluses, voice or handwriting recognizers, or other well-known input devices such as, of course, other computers.
  • processor 302 optionally may be coupled to an external device such as a database, a computer, or a telecommunications network using an external connection as shown generally at 312. With such a connection, it is contemplated that the processor 302 might receive information from the network, or might output information to the network in the course of performing the method steps described herein.
  • the physiological data may be collected by components integral with processor-based systems, such as computers, tablets, cellular telephones, medical test equipment, and input/output devices for such equipment, including remote controls for televisions, mice, and touchpads, to mention some examples.
  • processor-based systems such as computers, tablets, cellular telephones, medical test equipment, and input/output devices for such equipment, including remote controls for televisions, mice, and touchpads, to mention some examples.
  • a pair of contacts 324 may be provided on a button 322 of a mouse 320. Then when the user merely rests the user's finger on the mouse button 322, physiological data may be taken. This physiological data may be used to constantly collect information about the physiological states of users of large numbers of computing devices. If sufficient data can be collected, more meaningful trends can be developed.
  • the physiological data may be associated with position information. Specifically, the location with relatively fine granularity of the user whose physiological data may be taken, may be appended to that data in a way such that mapping software may be used to indicate changes in physiological data and thereby changes in social sentiment on a geographic basis.
  • a region of a map showing counties indicated as boxes 402, 404, 406, and 408 is indicated.
  • the region 402 may have a different social sentiment than the regions 404, 406, 408, as compiled and illustrated on the map. In this way, geographic differences and geographic based trends may be better understood.
  • the sensors may be connected to an interface, such as the interface depicted in Figure 3, which does filtering and signal processing using conventional techniques. Then this data, once it is analyzed, may be sent on over computer networks for aggregation with information from a wide variety of other users. In the embodiments in which that data is linked to particular geographic locations, social sentiment changes on a geographic basis may be identified and depicted visually in some embodiments.
  • the system may employ one or more memories or memory modules configured to store data, program instructions for the general-purpose processing operations and/or the inventive techniques described herein.
  • the program instructions may control the operation of an operating system and/or one or more applications, for example.
  • the memory or memories may also be configured to store representational information regarding one or more of the following: account or subscription information, messages, message semantic features, classification information, feature vectors, class lexicons, topic models, statistics regarding messages and classification, and the like.
  • modules and engines may be located in different places in various embodiments. Modules and engines mentioned herein can be stored as software, firmware, hardware, as a combination, or in various other ways. It is contemplated that various modules and engines can be removed or included in other suitable locations besides those locations specifically disclosed herein. In various embodiments, additional modules and engines can be included in the exemplary embodiments described herein.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Accounting & Taxation (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Primary Health Care (AREA)
  • Human Resources & Organizations (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computing Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

L'invention concerne des procédés et des systèmes permettant de prédire un sentiment social d'une ou de plusieurs personnes à l'aide de données physiologiques. Selon certains modes de réalisation, un procédé comprend les étapes consistant à recevoir les données en provenance d'une ou de plusieurs personnes dans un dispositif informatique, à analyser les données, à déterminer les données d'indicateur concernant le sentiment social d'une ou de plusieurs personnes de sorte que les données d'indicateur soient déterminée à partir des données, et à afficher et/ou transmettre les données d'indicateur. Le dispositif informatique peut comprendre un serveur ou un autre dispositif informatique distant. Les données physiologiques peuvent être reçues sur un réseau et/ou transmises sur ce dernier ou sur un réseau différent. Selon certains modes de réalisation, les données d'indicateur comprennent des informations d'avertissement à l'avance.
PCT/US2013/068205 2012-11-06 2013-11-04 Détermination d'un sentiment social à l'aide de données physiologiques WO2014074426A1 (fr)

Priority Applications (7)

Application Number Priority Date Filing Date Title
CN201380004601.3A CN104145272B (zh) 2012-11-06 2013-11-04 使用生理数据确定社会情绪
JP2014549012A JP2015502624A (ja) 2012-11-06 2013-11-04 生理データを利用した社会的感情の判定
DE112013000324.4T DE112013000324T5 (de) 2012-11-06 2013-11-04 Das gesellschaftliche Grundgefühl mithilfe physiologischer Daten bestimmen
GB1411008.4A GB2511978A (en) 2012-11-06 2013-11-04 Determining social sentiment using physiological data
KR1020147017646A KR101617114B1 (ko) 2012-11-06 2013-11-04 생리학적 데이터를 사용한 소셜 감성 결정
RU2014126373A RU2014126373A (ru) 2012-11-06 2013-11-04 Способ определения социальных настроений и структуры поведения с использованием физиологических данных
IN4566CHN2014 IN2014CN04566A (fr) 2012-11-06 2014-06-18

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201261722857P 2012-11-06 2012-11-06
US61/722,857 2012-11-06

Publications (1)

Publication Number Publication Date
WO2014074426A1 true WO2014074426A1 (fr) 2014-05-15

Family

ID=50685091

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2013/068205 WO2014074426A1 (fr) 2012-11-06 2013-11-04 Détermination d'un sentiment social à l'aide de données physiologiques

Country Status (8)

Country Link
JP (1) JP2015502624A (fr)
KR (1) KR101617114B1 (fr)
CN (1) CN104145272B (fr)
DE (1) DE112013000324T5 (fr)
GB (1) GB2511978A (fr)
IN (1) IN2014CN04566A (fr)
RU (1) RU2014126373A (fr)
WO (1) WO2014074426A1 (fr)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016009342A (ja) * 2014-06-25 2016-01-18 日本電信電話株式会社 エリアバースト推定提示装置、エリアバースト推定提示方法及びエリアバースト推定提示プログラム
CN106231996A (zh) * 2014-10-28 2016-12-14 林志成 用于提供对个体健康的指示的系统和方法
CN106339668A (zh) * 2016-08-16 2017-01-18 信利光电股份有限公司 一种虹膜识别方法及虹膜识别系统
US9805381B2 (en) 2014-08-21 2017-10-31 Affectomatics Ltd. Crowd-based scores for food from measurements of affective response
CN108538397A (zh) * 2017-12-23 2018-09-14 天津国科嘉业医疗科技发展有限公司 一种基于粒子滤波模型的流感趋势预测系统及方法
US10198505B2 (en) 2014-08-21 2019-02-05 Affectomatics Ltd. Personalized experience scores based on measurements of affective response
US10572679B2 (en) 2015-01-29 2020-02-25 Affectomatics Ltd. Privacy-guided disclosure of crowd-based scores computed based on measurements of affective response
US10769737B2 (en) * 2015-05-27 2020-09-08 Sony Corporation Information processing device, information processing method, and program
US11232466B2 (en) 2015-01-29 2022-01-25 Affectomatics Ltd. Recommendation for experiences based on measurements of affective response that are backed by assurances
US11269891B2 (en) 2014-08-21 2022-03-08 Affectomatics Ltd. Crowd-based scores for experiences from measurements of affective response
US11315088B1 (en) 2018-11-27 2022-04-26 Wells Fargo Bank, N.A. Geolocation and physiological signals for transaction initiation
EP4006751A1 (fr) 2020-11-27 2022-06-01 Prisma Analytics GmbH Procédure matérielle efficace automatisée pour représenter des mégadonnées
EP4006750A1 (fr) 2020-11-27 2022-06-01 Prisma Analytics GmbH Génération d'ensembles de paramètres multidimensionnels lisibles par machine
US11494390B2 (en) 2014-08-21 2022-11-08 Affectomatics Ltd. Crowd-based scores for hotels from measurements of affective response

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101685335B1 (ko) 2015-05-12 2016-12-12 대한민국 빅데이터 의미 기반 재난 감성분류방법
CN105554531A (zh) * 2015-12-16 2016-05-04 江苏惠通集团有限责任公司 媒体内容推送方法及系统
JP6474749B2 (ja) * 2016-03-10 2019-02-27 富士フイルム株式会社 情報提示方法、情報提示プログラム、及び情報提示装置
CN106202860B (zh) * 2016-06-23 2018-08-14 南京邮电大学 一种情绪调节业务推送方法
WO2018057544A1 (fr) * 2016-09-20 2018-03-29 Twiin, Inc. Systèmes et procédés de génération d'affects de conscience à l'aide d'une ou de plusieurs entrées non biologiques
JP6798353B2 (ja) * 2017-02-24 2020-12-09 沖電気工業株式会社 感情推定サーバ及び感情推定方法
JP6798383B2 (ja) * 2017-03-24 2020-12-09 沖電気工業株式会社 データ処理装置、データ処理方法およびプログラム
JP6872757B2 (ja) * 2018-06-21 2021-05-19 日本電信電話株式会社 集団状態推定装置、集団状態推定方法及び集団状態推定プログラム
US20200388364A1 (en) * 2019-06-07 2020-12-10 International Business Machines Corporation Sentiment Detection Using Medical Clues
CN111956239A (zh) * 2020-07-22 2020-11-20 黄山学院 高校辅导员情绪复杂性的测评方法、系统及电子设备
JP7205528B2 (ja) * 2020-11-17 2023-01-17 沖電気工業株式会社 感情推定システム

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100023300A1 (en) * 2008-07-28 2010-01-28 Charles River Analytics, Inc. Sensor based monitoring of social networks
WO2011153318A2 (fr) * 2010-06-02 2011-12-08 Q-Tec Systems Llc Procédé et appareil de contrôle des émotions dans un réseau interactif
US20120095979A1 (en) * 2010-10-15 2012-04-19 Microsoft Corporation Providing information to users based on context
US20120124122A1 (en) * 2010-11-17 2012-05-17 El Kaliouby Rana Sharing affect across a social network
US20120130196A1 (en) * 2010-11-24 2012-05-24 Fujitsu Limited Mood Sensor

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1606758B1 (fr) 2003-03-21 2015-11-18 Welch Allyn, Inc. Systeme de surveillance physiologique d'etat personnel
JP4520409B2 (ja) * 2003-06-18 2010-08-04 パナソニック株式会社 生体情報活用システム、生体情報活用方法、プログラムおよび記録媒体
JP4604494B2 (ja) * 2004-01-15 2011-01-05 セイコーエプソン株式会社 生体情報解析システム
JP2008532587A (ja) 2005-02-22 2008-08-21 ヘルス−スマート リミテッド 生理学的及び心理学的／生理学的モニタリングのための方法及びシステム並びにその使用
JP2007114931A (ja) * 2005-10-19 2007-05-10 Konica Minolta Holdings Inc 認証装置
JP5172167B2 (ja) * 2006-02-15 2013-03-27 株式会社東芝 人物認識装置および人物認識方法
EP2152155A4 (fr) * 2007-06-06 2013-03-06 Neurofocus Inc Système de surveillance des réactions aux programmes multimarchés et aux publicités utilisant des mesures des réactions neurologiques
US8327395B2 (en) * 2007-10-02 2012-12-04 The Nielsen Company (Us), Llc System providing actionable insights based on physiological responses from viewers of media
US9521960B2 (en) * 2007-10-31 2016-12-20 The Nielsen Company (Us), Llc Systems and methods providing en mass collection and centralized processing of physiological responses from viewers
CN101853259A (zh) * 2009-03-31 2010-10-06 国际商业机器公司 添加和处理带有情感数据的标签的方法和设备
AU2011265090A1 (en) * 2010-06-07 2012-11-29 Affectiva,Inc. Mental state analysis using web services

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100023300A1 (en) * 2008-07-28 2010-01-28 Charles River Analytics, Inc. Sensor based monitoring of social networks
WO2011153318A2 (fr) * 2010-06-02 2011-12-08 Q-Tec Systems Llc Procédé et appareil de contrôle des émotions dans un réseau interactif
US20120095979A1 (en) * 2010-10-15 2012-04-19 Microsoft Corporation Providing information to users based on context
US20120124122A1 (en) * 2010-11-17 2012-05-17 El Kaliouby Rana Sharing affect across a social network
US20120130196A1 (en) * 2010-11-24 2012-05-24 Fujitsu Limited Mood Sensor

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2016009342A (ja) * 2014-06-25 2016-01-18 日本電信電話株式会社 エリアバースト推定提示装置、エリアバースト推定提示方法及びエリアバースト推定提示プログラム
US10387898B2 (en) 2014-08-21 2019-08-20 Affectomatics Ltd. Crowd-based personalized recommendations of food using measurements of affective response
US11907234B2 (en) 2014-08-21 2024-02-20 Affectomatics Ltd. Software agents facilitating affective computing applications
US11269891B2 (en) 2014-08-21 2022-03-08 Affectomatics Ltd. Crowd-based scores for experiences from measurements of affective response
US9805381B2 (en) 2014-08-21 2017-10-31 Affectomatics Ltd. Crowd-based scores for food from measurements of affective response
US10198505B2 (en) 2014-08-21 2019-02-05 Affectomatics Ltd. Personalized experience scores based on measurements of affective response
US11494390B2 (en) 2014-08-21 2022-11-08 Affectomatics Ltd. Crowd-based scores for hotels from measurements of affective response
CN110085319A (zh) * 2014-10-28 2019-08-02 林志成 用于提供对个体健康的指示的系统和方法
CN106231996A (zh) * 2014-10-28 2016-12-14 林志成 用于提供对个体健康的指示的系统和方法
US10572679B2 (en) 2015-01-29 2020-02-25 Affectomatics Ltd. Privacy-guided disclosure of crowd-based scores computed based on measurements of affective response
US11232466B2 (en) 2015-01-29 2022-01-25 Affectomatics Ltd. Recommendation for experiences based on measurements of affective response that are backed by assurances
US10769737B2 (en) * 2015-05-27 2020-09-08 Sony Corporation Information processing device, information processing method, and program
CN106339668A (zh) * 2016-08-16 2017-01-18 信利光电股份有限公司 一种虹膜识别方法及虹膜识别系统
CN108538397A (zh) * 2017-12-23 2018-09-14 天津国科嘉业医疗科技发展有限公司 一种基于粒子滤波模型的流感趋势预测系统及方法
US11315088B1 (en) 2018-11-27 2022-04-26 Wells Fargo Bank, N.A. Geolocation and physiological signals for transaction initiation
EP4006750A1 (fr) 2020-11-27 2022-06-01 Prisma Analytics GmbH Génération d'ensembles de paramètres multidimensionnels lisibles par machine
EP4006751A1 (fr) 2020-11-27 2022-06-01 Prisma Analytics GmbH Procédure matérielle efficace automatisée pour représenter des mégadonnées

Also Published As

Publication number Publication date
GB201411008D0 (en) 2014-08-06
IN2014CN04566A (fr) 2015-09-18
KR20140097474A (ko) 2014-08-06
CN104145272B (zh) 2017-11-17
GB2511978A (en) 2014-09-17
RU2014126373A (ru) 2016-01-27
DE112013000324T5 (de) 2014-08-21
KR101617114B1 (ko) 2016-04-29
JP2015502624A (ja) 2015-01-22
CN104145272A (zh) 2014-11-12

Similar Documents

Publication Publication Date Title
KR101617114B1 (ko) 생리학적 데이터를 사용한 소셜 감성 결정
US11921669B2 (en) Computer systems and processes configured to identify behavioral, action, activity, and/or emotional states of a person and to respond to the identity of the states
AU2021200812B2 (en) A system and method for generating a profile of stress levels and stress resilience levels in a population
AU2017251705B2 (en) Device-based participant matching
Davidson et al. Internalized homonegativity, sense of belonging, and depressive symptoms among Australian gay men
Grov et al. Rules about casual sex partners, relationship satisfaction, and HIV risk in partnered gay and bisexual men
Grov et al. Perceived importance of five different health issues for gay and bisexual men: implications for new directions in health education and prevention
Oeldorf-Hirsch et al. Count your calories and share them: Health benefits of sharing mhealth information on social networking sites
US20200194125A1 (en) Method and System for Tracking, Storing, and Processing Data to Identify Risk Factors and Predict Health-Related Conditions
JP2021507366A (ja) ユーザの健康状態を監視するためのシステムおよび方法
Gonsalves et al. Exploring the use of online sexually explicit material: What is the relationship to sexual coercion?
Vaid et al. Smartphones in personal informatics: a framework for self-tracking research with mobile sensing
Kang et al. K-emophone: A mobile and wearable dataset with in-situ emotion, stress, and attention labels
Valera et al. Substance use and HIV-risk behaviors among young men involved in the criminal justice system
Gopalakrishnan et al. Mobile phone enabled mental health monitoring to enhance diagnosis for severity assessment of behaviours: a review
Grov et al. Patterns of client behavior with their most recent male escort: An application of latent class analysis
Baudouin et al. Factors affecting the preventive intention on premarital sexual behaviours among junior high school students in lower-northern region of Thailand
Wimonsate et al. Repeat HIV testing among HIV-uninfected men who have sex with men attending Silom Community Clinic, Bangkok, 2011− 2014
Capellan et al. Can information about “safe places” reduce female victimisation in Honduras? a quasi-experimental evaluation of the safeWalking app
Joinson et al. Technology and the formation of socially positive behaviours
Park et al. Demographic, deployment and post-deployment experiences predict trajectories of meaning in life in OEF/OIF/OND veterans
US20240134820A1 (en) Computer systems and processes configured to identify behavioral, action, activity, and/or emotional states of a person, by analyzing empirical data received from observations of the person, and to autonomously respond to the identity of the states
Platkin et al. The digital revolution and its potential impact on detection and treatment of depressive disorders
Zeng Social Support on Fitness Behavior in an Online Fitness Community
Kelly et al. Crowdsourced data collection of physical activity and health status: An App Solution

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 1411008

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20131104

Ref document number: 2014549012

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1411008.4

Country of ref document: GB

WWE Wipo information: entry into national phase

Ref document number: 112013000324

Country of ref document: DE

Ref document number: 1120130003244

Country of ref document: DE

ENP Entry into the national phase

Ref document number: 20147017646

Country of ref document: KR

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2014126373

Country of ref document: RU

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 13852963

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 13852963

Country of ref document: EP

Kind code of ref document: A1