EP1297448A1 - Systeme et procede faisant appel a des informations de modeles de portee psychologique pour les mettre en correspondance avec des informations cibles - Google Patents

Systeme et procede faisant appel a des informations de modeles de portee psychologique pour les mettre en correspondance avec des informations cibles

Info

Publication number
EP1297448A1
EP1297448A1 EP01955058A EP01955058A EP1297448A1 EP 1297448 A1 EP1297448 A1 EP 1297448A1 EP 01955058 A EP01955058 A EP 01955058A EP 01955058 A EP01955058 A EP 01955058A EP 1297448 A1 EP1297448 A1 EP 1297448A1
Authority
EP
European Patent Office
Prior art keywords
user
target information
classification
computer
significance pattern
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.)
Withdrawn
Application number
EP01955058A
Other languages
German (de)
English (en)
Inventor
Desmond Mascarenhas
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Protigen Inc
Original Assignee
Protigen Inc
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 Protigen Inc filed Critical Protigen Inc
Publication of EP1297448A1 publication Critical patent/EP1297448A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification
    • G06F16/353Clustering; Classification into predefined classes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/954Navigation, e.g. using categorised browsing

Definitions

  • This invention relates generally to a computer-implemented system for creating a psychological, personality, or behavioral significance pattern for end users, more particularly, using such psychological significance pattern to match users with target information, such as information on products, services, and career openings.
  • Search engines such as Alta Nista, Excite, Webcrawler, and the like, are available on the Internet. Users typically enter a keyword on the Web page and the search engine returns a list of documents (e.g., through hyperlinks) where the keywords may be found. (Individuals and users herein are used interchangeably.) Depending on several factors such as the keywords used, the search engine's algorithms, available user related data, and the like, the resulting list may contain hundreds and even thousands of documents. A way to refine a search result, i.e., shorten the list returned, based on the personal characteristics and/or archetypes (e.g., "personality") of a user is highly desirable.
  • personal characteristics and/or archetypes e.g., "personality”
  • Displayed advertisements or offers may also be keyword-linked, such that advertisements indexed or related to certain keywords are displayed only if the user enters at least one of those keywords.
  • Keyword-linked mechanism does not take into account the personality, behavior, or psychology of a user.
  • a user's personality, behavior, and psychology are herein collectively referred to as "personality").
  • a way to take into account a user's personality so as to have a more efficient and effective targeted marketing is highly desirable.
  • Targeted marketing conventionally also employs information about the user.
  • Internet service providers ISPs
  • ISPs Internet service providers
  • a profile based on these prior and explicit declarations of interest is created for each user such that only advertisements that would likely interest the user are displayed on a Web page.
  • personal profile information is usually obtained without the consent or knowledge of the user and typically does not adequately predict a user's preference when a new situation occurs, such as a search for an item that the user has never requested or explicitly expressed an interest in before.
  • Target information includes all information that a user may want to do a search on or information that a third party may want to present (e.g., auditory) or display to a user. It also includes information such as information on products and services, articles, music, logos, advertisements, images, videos, and the like.
  • European Patent Application EP-A-0718784 describes a system for retrieving information based on a user-defined profile.
  • a server acting on behalf of the client identifies information on the basis of the user-defined profile, to generate a personalized newspaper which is delivered to the user.
  • This provides for an automatic sorting of the large volume of data available on the World Wide Web to generate a subset of information which is tailored to the user's specific interest.
  • this system is only used for providing newspaper data to a static user whose desires may change periodically.
  • Multivariate data derived from a variety of sources represent a vector of measures that describe the state or condition of a particular subject. Accessing the descriptive and predictive capabilities inherent in these vectors requires the use of powerful but general analytic techniques. Standard statistical analysis packages that contain this "toolbox" of techniques are commercially available (e.g., SASTM, SPSSTM, BMDPTM), as are an array of texts describing general multivariate techniques (Johnson, 1998; Sharma, 1996; Tabachnick and Fidell., 1996; Srivastava and Carter, 1983; Romesburg, 1984). However, while supplying the basic tools for formal analysis, none of these resources specifically addresses the issues faced when trying to extrapolate from these kinds of data to probable outcomes in "real-world, real-time" settings.
  • RNA expression data generated from genome-wide expression patterns in the budding yeast S. cerevisiae were used by Eisen, et al. (1998) to understand the life cycle of the yeast. They employed a cluster analysis to identify patterns of genomic expression that appear to correspond with the status of cellular processes within the yeast during diauxic shift, mitosis, and heat shock disruption.
  • the clustering algorithm employed was hierarchical, based on the average linkage distance method.
  • Greller and Tobin (1999) developed a more general approach to the pattern recognition/discrimination problem. They derived a measure of statistical discrimination by establishing an analysis that transposes the clustering question into an outlier detection problem. Assuming a uniform distribution of interstate expression, and by accounting for both a statistical distribution of baseline measures and uncertainty in the observation technology, they derive a decision function that assigns a subject, in their case a gene, to one of three states: selectively upregulated, selectively downregulated, or unchanged. And Brown, et al. (2000) derived a knowledge-based analysis engine based on a technique known as "support vector machines” (SNMs). These "machines” are actually nonlinear in silico discrimination algorithms that "learn” to discriminate between, and derive archetypes for, binarially attributed data.
  • SNMs support vector machines
  • the goal is to explore the possibility of applying such tools to such areas as the real-time adjustment of online education to a user's cognitive (learning) style, point-of-care serum diagnostics for osteoporotic women, and the accurate prediction of a protein's solubility in a heterologous system based on its sequence.
  • Toronen P., M. Kolehmaninen, G. Wong, and E. Castren. (1999). Analysis of gene expression data using self-organizing maps. FEBSLett. 451(2):142-146.
  • What is claimed is a computer implemented method for matching a computer user with target information by creating a classification significance pattern for the user through the use of a psychological test, by creating a classification index for the target information, and by finding relevant target information for the user by matching one or more elements of the classification significance pattern to the target information classification index.
  • a classification significance pattern herein includes psychological, behavioral, personality, or other attributes that may be tested, created, and/or maintained by a psychological testing tool for a user.
  • Such classification significance pattern includes, but is not limited to, the classification of a user into certain characteristics and/or archetypes or models.
  • the invention enables a user to take an online psychological test, have the system automatically score such test, have the system create and/or maintain a classification significance pattern for the user, such as a classification significance pattern that contains the characteristics and/or archetypes measured by the online psychological test, and have the system use such classification significance pattern to match users with target information.
  • the user may log into the system and take the online psychological test anonymously, by supplying a pseudonym (i.e., a fictitious name), such as a user-supplied user name, and thus, enforcing an additional level of privacy.
  • a pseudonym i.e., a fictitious name
  • create a classification significance pattern herein refers to the creation and maintenance (updates) of a classification significance pattern.
  • the online psychological test measures various aspects of a user, such as personality, psychology, disposition, behavior and the like. Based on these aspects, classifications are created which are used to match the users with target information, such that both the user and the target information contain classification information (e.g., fields in a database). Furthermore, the target information may be classified, for example, by characteristics and/or archetypes rather than or in addition to the contents of the electronic information (e.g., having a search filtered not only by keywords but also by classifications measured by the psychological test).
  • classification information e.g., fields in a database
  • the target information may be classified, for example, by characteristics and/or archetypes rather than or in addition to the contents of the electronic information (e.g., having a search filtered not only by keywords but also by classifications measured by the psychological test).
  • Fig 1. is a diagram illustrating an exemplary architecture of the present invention.
  • Fig. 2 is a block diagram representation of one of the computers in the system illustrated in Fig. 1.
  • Fig. 3 illustrates a high level block diagram showing how a user obtains a classification profile and uses such profile to search for information.
  • Fig. 4 is an exemplary representation of a user interface enabling a user to enter a response to a question from a psychological test.
  • Fig. 5 illustrates a high-level block diagram showing targeted marketing based on the user's classification profile.
  • Fig. 6 illustrates functional block diagrams describing an exemplary set of steps to determine a user's personal significance pattern.
  • Fig. 7 illustrates a functional block diagram describing an exemplary set of steps in matching the user's significance pattern to target information.
  • PTT Personality Trait Topography
  • customer input and actions described refer to inputs from a keyboard or a mouse
  • this invention also covers other interfaces such as those using voice or a touch screen.
  • specific computational methods and correlation schemes described herein may be replaced with equivalent statistical methods within the framework and claims of the present invention.
  • FIG. 1 shows an exemplary system architecture to carry out the present invention, including a standard Internet or Intranet web server 150 that is capable of sending Web pages and processing scripts, a database server 160 that stores and handles database manipulation and updates, and an application server 180 that contains and executes the logic embodying the features of the present invention.
  • a standard Internet or Intranet web server 150 that is capable of sending Web pages and processing scripts
  • a database server 160 that stores and handles database manipulation and updates
  • an application server 180 that contains and executes the logic embodying the features of the present invention.
  • a user (local user 105 or remote user 115, respectively) employs typically a computer containing an Internet browser software 110, 120 (or an Internet-enabled appliance) to access and connect to the Web server 150, database server 160, and application server 180.
  • an Internet browser software 110, 120 or an Internet-enabled appliance
  • the Web server 150, database server 160, and application server 180 are connected to a data network, such as a local area network 130 which may also be connected to the Internet through a wide area network (WAN) 140.
  • the Web server is a device, typically a computer, which contains a Web server software 152 and scripts 154. Scripts are programs that contain instructions that may be executed, for example, by a Web server software. Scripts are typically written using scripting languages, such as JavaScript, Microsoft® VBScript, Microsoft® Active Server Page, and Allaire® ColdFusion. Microsoft® Internet Information Server is an example of a Web server software.
  • the database server 160 is a device, typically a computer, which contains a database management system (DBMS) software 161, as well as the data used and/or manipulated in the present invention.
  • DBMS database management system
  • Microsoft® SQL Server and Oracle's DBMS products are examples of DBMS software.
  • the registration database 162 maintains data on users who have registered in the system. It contains fields such as user name, password, demographic information (e.g., zip code), user occupation, household income, education, gender, whether the user has completed the psychological test, the user's characteristic(s) and/or archetype(s) and the like.
  • the user name is a pseudonym that is user-supplied to provide the user with another level of privacy.
  • Information contained in the registration database 162 (Fig. 1) is typically obtained when the user first registers with the system, however, calculated or derived information, such as the numeric or textual representation of the user characteristic may also be stored.
  • the preferred embodiment of the invention uses a psychological test or trait evaluation method developed by the inventor herein generically referred to as "Personality Trait Topography" (PTT).
  • PTT comprises a psychometric inventory in which user responses to a set of questions are solicited on a seven-point scale.
  • Other embodiments include a number of psychological tests, preferably consisting of a personality test, a design taste test, a color test, an interactive game module, a recreation/travel test, a life satisfaction test, and a career/job test.
  • An alternative psychological testing methodology may be substituted for the PTT.
  • the database elements of the preferred PTT are shown in Fig. 1.
  • the personality significance pattern database 163, the design taste database 164, the recreation/travel database 165, the life satisfaction database 166, and the career/job database 167 maintain data on the responses by and scores of the user in the personality test, the design taste test, the recreation/travel test, the life satisfaction test, and the career/job test, respectively.
  • Fig. 1 also shows product database 168 maintains data on products available within the system including: the classification of the products (compatible with or matching that measured by the psychological test). Fields include product name, description, correlation value, and the like. This classification is described below in an exemplary description with respect to Fig. 8. Relationships are initially established between archetypes, on the one hand, and behaviors, preferences or attitudes on the other. For example, individuals assigned to archetypes can be polled on the extent of their preferences, or self-reported skills. Using canonical correlation, chi square, and other appropriate tools well known to a professional statistician, actual numerical values linking archetypes to an increased (or decreased) affinity for a particular product, activity, behavior or attitude can be derived.
  • the PTT generates robust, quantitative and reliable relationships between archetypes and each of dozens of behavioral and product categories. Such known relationships can, in turn be used to generate reliable predictions of an individual's disposition to the given items, provided that individual's archetype pattern has first been measured using the PTT.
  • the service database 169 maintains data on services available within the system, including the classification of the services (compatible with or matching that tested by the psychological test.) Fields include service name, description, correlation value, and the like.
  • the product and service databases (which are examples of target information), as well, as other information database, contain fields that match or are compatible with the classification of the users.
  • the classification such as for the product or service, is typically determined by the supplier of the target information.
  • a user interface as part of the system, may be provided enabling a supplier of such information to enter or indicate the proper classification, for example, through check boxes, lists, and the like.
  • the supplier of information checks these two boxes to have an "M” in the mythic_empiric field and a "Yes" in the artist field be stored in the appropriate databases. This way, the target information may be matched with the user's classification profile.
  • the PTT is described in detail below.
  • the application sever 180 is a device, typically a computer, which contains certain application software, such as the user interface program 182, the profiling program 184 (e.g., Brain Terrain), the search engine 186, and the targeted marketing program 188.
  • application software such as the user interface program 182, the profiling program 184 (e.g., Brain Terrain), the search engine 186, and the targeted marketing program 188.
  • the user interface program 182 generally comprises program logic that displays Web pages to users, typically web pages enabling users to register within the system, take the psychological test, or search the system for products or services. In the preferred embodiment, it is employed using a Web server software in conjunction with scripts.
  • the profiling program 184 is a software program that calculates and creates the user significance pattern by considering user's responses to the psychological test and classifying the user, e.g., based on the characteristics and archetypes measured by the psychological test.
  • the search engine 186 is a software program that enables users to search for target information in the system, such as products, services, and employment opportunities, based on the user's significance pattern. It may also provide user interface logic. (Thus, if a user is interested in a product, the user searches for target information about the product.)
  • search algorithm employed by the Search Engine 186 may be employed in a number of ways.
  • Any search methodology that computes and sorts outcomes according to predetermined algorithmic relationships between the PTT personal style patterns and behavioral or other outcomes, may be used.
  • the methods by which these algorithmic relationships can be established are described hereunder.
  • the targeted marketing program 188 is a software program that contains logic that determines what advertisement is to be displayed.
  • Fig. 1 may be implemented in a single computer, where the database are stored in computer readable medium, such as in a hard disk drive or a CD ROM, as well as having the user interface described above, not generated by a web server software and scripts, but rather displayed and executed by a interpretive or compiled programming language such as Visual Basic or C++.
  • the above embodiment illustrates the various components, such as the web server 150, the database server 160, and the application server 180 embodied in an individual device
  • the functionality may be distributed over a plurality of computers.
  • the databases defined herein, as well as the fields in the database may be modified, added, or deleted depending for example, on what psychological test is employed, the information desired to be stored and monitored, the system and/or implementation design, and the like.
  • an articles database containing articles classified by the characteristics defined in the psychological test may be added to provide users in the system with articles suited to their personality.
  • the psychological test need not be taken online, but rather the user significance pattern, for example, as a result of a written (non- online) psychological test), maybe directly stored into the database, e.g., the registration database 162 in Fig. 1.
  • Fig. 2 is a block diagram of an exemplary computer 200 such as might comprise any of the servers or computers in Fig. 1.
  • Each computer 200 operates under control of a central processor unit (CPU) 1102, such as a "PentiumTM" microprocessor and associated integrated circuit chips, available from Intel CorporationTM of Santa Clara, California, USA.
  • CPU central processor unit
  • a computer user can input commands and data from a keyboard and mouse 212 and can view inputs and computer output at a display 210.
  • the display is typically a video monitor or flat panel display device.
  • the computer 200 also includes a direct access storage device (DASD) 204, such as a fixed hard disk drive.
  • the memory 206 typically comprises volatile semiconductor random access memory (RAM).
  • Each computer preferably includes a program product reader 214 that accepts a program product storage device 216, from which the program product reader can read data (and to which it can optionally write data).
  • the program product reader can comprise, for example, a disk drive, and the program product storage device can comprise removable storage media such as a floppy disk, an optical CD- ROM disc, a CD-R disc, a CD-RW disc, DVD disk, or the like.
  • Each computer 200 can communicate with the other connected computers over the network 220 through a network interface 208 that enables communication over a connection 218 between the network and the computer.
  • the CPU 202 operates under control of programming steps that are temporarily stored in the memory 206 of the computer 200.
  • the programming steps implement the functionality of the system components illustrated in Fig. 1.
  • the programming steps can be received from the DASD 204, through the program product 216, or through the network connection 218.
  • the storage drive 204 can receive a program product, read programming steps recorded thereon, and transfer the programming steps into the memory 206 for execution by the CPU 202.
  • the program product storage device can comprise any one of multiple removable media having recorded computer-readable instructions, including magnetic floppy disks, CD-ROM, and DVD storage discs.
  • Other suitable program product storage devices can include magnetic tape and semiconductor memory chips. In this way, the processing steps necessary for operation in accordance with the invention can be embodied on a program product.
  • the program steps can be received into the operating memory 206 over the network 218.
  • the computer receives data including program steps into the memory 206 through the network interface 208 after network communication has been established over the network connection 218 by well-known methods that will be understood by those skilled in the art without further explanation.
  • the program steps are then executed by the CPU 202 to implement the processing and features of the present invention.
  • Fig. 3 illustrates an exemplary logic flow on how a user uses his or her own significance pattern to conduct searches.
  • the user first logs onto the system as shown in step 302. The user does this by accessing a web site using an Internet browser 110, 120 (as shown in Fig. 1), typically by typing the URL address on the Internet browser address box or by selecting the Web site via a hyperlink.
  • a user who is new to the system is asked to register with the system by supplying a user name and a password.
  • the user name and password are stored in the registration database 162 (Fig. 1).
  • the user takes the psychological test, as shown in box 304.
  • the psychological test may be broken down into a series of mini-tests.
  • the profiling program 184 converts each test response by the user to a raw score points or index. These raw points are further manipulated to create a significance pattern represented by numbers and text.
  • the system then stores the user's significance pattern at step 306 in the Registration database 162 (Fig. 1).
  • the user may use his/her significance pattern to conduct searches, as shown in box 308, thereby making the significance pattern part of the search criteria.
  • a search for the keyword "travel" results in a user interface or Web page listing tours suited to the user's personality. For example, if the user has been determined to having a personality that prefers fixed schedules rather than spontaneity, tours that have a number of preplanned activities are listed rather than those tours with little or minimal preplanned activities or have those non-preferred tours listed last on the list.
  • the classifications of the tours based on the characteristics and archetypes measured are stored as part of the target information database, e.g., the service database 169 (Fig. 1).
  • Employment matching or searching may also be done.
  • One way of employing the features of the present invention is to have supervisors take a similar psychological test and create a significance pattern for such supervisors.
  • a search for jobs results in a list of jobs, considering both the user's personality and that of the prospective supervisor.
  • the preferred psychological testing methodology is the PTT, which may be used as follows:
  • a field indicating the archetype being measured may be added in the product, service, or other target information database (such as, employment database).
  • the product or service database contains a field called Empiric_Mythic, which is one archetype tested by the psychological test. (See Table I below).
  • An "M” in this field indicates that the product is more suited for users who are “mythic,” a “E” indicates that the product is more suited for users who are “empiric,” and a "" (blank or null string) indicates that the product equally applies regardless of the characteristic.
  • the invention uses a psychological test, herein referred to as "PTT”, which measures several characteristics (listed below in Table I).
  • PTT is conducted by asking a user a set of questions addressing the characteristics that are measured. Based on the user's response, the profiling program 184 (in Fig. 1) then classifies the user. 1. Index OJ.
  • Type "O" (open-ended) users consider all decisions to be provisional and, thus, are constantly reevaluating issues. They do not care much for regimentation, and generally will ignore rules that they deem do not make sense. Typically, they are spontaneous and are happy to make plans as they go along.
  • Type "J" (judgmental) users are typically driven by rules, tradition, and formal decision-making processes, and are generally law-abiding. They expect and feel comfortable with some amount of regimentation and structure in their lives. They typically plan ahead and feel uncomfortable just 'playing it by ear.'
  • Type "F” (focused) users (line 2) typically tend to be driven, “one-track-minded,” “goal- oriented,” and intensely focused on their endeavors. Often they will work for hours, while completely oblivious to surroundings. They tend to take things seriously, and sometimes, need to learn to lighten up.
  • Type "U” (unfocused) users tend to take things lightly. They tend to take frequent breaks while working and are very conscious of their immediate surroundings and, thus, are easily distracted from their current work or purpose. They tend to have the philosophy that having fun is more important than achieving goals.
  • Type "C” (concrete) (line 3) users tend to be detail-oriented, tend to be very sensitive to their immediate surroundings, are more interested in the details rather than in the big picture. Generally, they have little patience for grand ideas and theories, and are more likely to focus on the present rather than on the future.
  • Type "B” (abstract) users, on the other hand, tend to easily synthesize information and abstract ideas. Their insights make them excellent "high- altitude” or "big picture” analysts. They usually are good inventors and are able to easily conceptualize complex systems. They tend to enjoy reading novels with complicated but ingenious plots and tend to be good at extrapolating to the future.
  • Type "T” (territorial) users tend to be aggressive, to be very loyal, to root for the home team, to not value diversity, to be very team-oriented, and to be fierce competitors. Thus, they will often exclude “outsiders.”
  • Type "P” (pacifist) users tend to look for mediated solutions to conflict and are more willing to consider rehabilitation than punishment. They tend to be "politically correct,” to be very inclusive of other cultures and ways of life, to have diverse interests, and to see the planet as an organic whole.
  • Type "E” (empiric) users (line 5) are driven primarily by logic, not subject to making emotional decisions as other people, at times, cold and unemotional, methodical and hierarchical in their thinking, and often very intelligent. They tend to look for the facts of the case before making a decision.
  • Type "M” mythic users are generally spiritual, superstitious, and very likely to believe in the real, in an after-life, or reincarnation. They are likely to consider the existence of angels and extraterrestrials and believe in their existence. They tend to be exceptionally receptive to nature, art, and beauty.
  • Type "A” (anomic) (line 6) users are often loners and enjoy solitary pursuits. They tend to place a low value on social status, fashion, and chitchat, tend to be independent thinkers and usually develop extremely close relationships with pet animals.
  • Type "G” (gregarious) users, on the other hand, often value their status within their own social group, and will diligently work to improve their standing. They tend to pay great attention to appearances and grooming, and "fitting in” with their friends. They are great to have at parties and often adopt socially extroverted behaviors, even if this is an unnatural characteristic of their personalities.
  • Type "I” internal locus of control users (line 7) tend to take responsibility for their own actions and the consequences thereof, and generally have a better self-esteem than average people. They see their lives as being under their own control, with the outcome dependent upon their own actions.
  • Type "X" external locus of control users, on the other hand, have low self-esteem, tend to blame luck or some external authority for their own failings in life, and tend to seek and often meekly submit to the direction from others. They usually feel a sense of powerlessness about their world and feel that they are incapable of changing the world to their own advantage.
  • R is a Risk-Taker.
  • S is Security-Conscious.
  • Archetypes are derived from the pattern of scores obtained by an individuals across the above indexes, or scales. Archetypes are heuristic abstractions that can be constructed in a number of ways. The example shown below illustrates one method currently in use. Other methods may be developed in the future.
  • Table II shows sample archetypes based on the characteristics listed in Table I.
  • the PTT is also a psychological test that creates cognitive user significance patterns that are typically "stable” over time. That is, changeable data such as demographic data, address, phone number, age, etc. is not used.
  • Fig. 4 is an exemplary representation of a user interface or GUI, such as a Web page, enabling a user to take a psychological test, e.g., a PTT assessment.
  • the personality test portion of PTT quantifies the user's personality.
  • the personality test asked a set of questions, to which the user may respond by choosing one of the displayed options.
  • the question 402 ("If a leader can't build consensus, the policy should be abandoned") is a sample question testing the personality of the user.
  • the user responds by clicking on one of the option boxes (as shown in 404).
  • Each question is scored on a seven-point scale (-3 to +3) where -3 is "Strongly Disagree” and +3 is "Agree Strongly,” (with each user's response contributing to the relevant characteristic and/or archetype measured, e.g., adding 3 points or subtracting 3 points).
  • the user's response is then stored in an appropriate user storing database, in this case, the personality profile database 163 (in illustrated in Fig. 1).
  • each question may contribute to multiple scales.
  • the precise contribution to each scale is hypothesis-based, and may be adjusted empirically until the results obtained are consistent.
  • An alternative approach is to perform 'factor analysis' by traditional statistical methods and then use the results from such an analysis to assign the scoring matrix.
  • the response of the user may be ignored in the calculation of the significance pattern depending on traditional measures such as factor analysis and discriminant analysis. Answers to questions that do not show a factor analysis, i.e., show a 0.40 correlation coefficient or less, for example, to the desired characteristic, are ignored in determining or calculating the significance pattern.
  • the profiling program 184 calculates the mean and standard deviation for all answers for each user and then normalizes the answers based on these two numbers, thereby expressing a set of responses as normalized standard deviations. Each response is then multiplied by an appropriate factor, to generate an aggregate score set, representing the significance pattern. Each aggregate score set contains a score for each characteristic listed in Table 1.
  • the aggregate score set is then further normalized by taking the aggregate score set of a suitable large number of users (e.g., more than 75), calculating a mean and standard deviation for each type of aggregate score for each characteristic, and then further normalizing each user's score for that distribution.
  • the final result is a set of normalized aggregate scores expressed as standard deviations, i.e., the scores are normalized within a normalized aggregate score set compared to the result of each user.
  • the profiling program 184 generates a significance pattern or a portion of it based on the user's responses.
  • the significance pattern may also be expressed as a mnemonic string of characters that contains the three most deviant characteristic scored (normalized aggregate scores), plus an indicator for the strongest correlation to the existing archetypal patterns.
  • a user may be categorized as "MAU9R” meaning he is a "mythic,” “anomic,” and a “unfocused.”
  • the string “9R” means that in a scale of 1 to 10, the user is a 9 in the Artist archetype shown in Table II.
  • a search 308 requesting for products with a "travel" keyword results in a web page listing products that contain an "M” on the Empiric_Mythic field, "A” on the Anomic_Gregarious field, or "U” on the FocusedJUhfocused field.
  • the design taste psychological test measures the design and taste preference of the user.
  • the design taste test displays a number of sketches of house interiors and asks the user's preference by having the user select one of the options displayed (e.g., "Strongly Dislike,” “Dislike,” “Slightly Dislike,” “Neutral,” “Like Slightly,” “Like,” and “Love It.”).
  • Each question is scored on a seven-point scale (-3 to +3) where -3 is “Strongly Dislike” and +3 is "Love It.”
  • the Recreation/Travel survey measures the recreation and travel preference of the user by asking the user to enter his or her response in an online survey form.
  • This online survey form is implemented by using a Web server software and scripts.
  • the user for example, is asked to list the titles of three favorite books, to list the titles of five favorite movies, to list five activities (unrelated to the user's employment) which the user has spent the most time during the past year, and to list three subjects (unrelated to the user's employment) which the user wants to learn more about.
  • the user enters the responses into the online form and accordingly submits the responses by clicking on the "Submit" button.
  • the Life Satisfaction Survey measures the user's satisfaction with life in general.
  • a set of questions is posed to the user, which the user responds to by selecting an option box ("Highly Unsatisfied,” “Unsatisfied,” “Slightly Unsatisfied,” “Neutral,” “Slightly Satisfied,” “Satisfied,” and “Very Satisfied.")
  • Sample questions include: “How satisfied are you with your current job?"; "How satisfied are you with your current choice of profession?"; "How satisfied are you with your current family income?;” “How satisfied are you with the amount of time you have available for recreational activities?”; and the like.
  • Each question is scored on a seven-point scale (-3 to +3) where a score of -3 is "Highly Unsatisfied” and +3 is “Very Satisfied.”
  • the Jobs/Careers Test measures how compatible a user is with a particular job. Questions include, for example, "With appropriate training, how well do you think you could perform as an accountant or banker?;” "With appropriate training, how well do you think you could perform as a scientist?;” "With appropriate training, how well do you think you could perform as a high school schoolteacher?;” and the like.
  • Gather data on a quantitative scale e.g. collect responses to a questionnaire on a 7- point scale as generally described above (see Fig. 4 for an exemplary question display). 605, 607.
  • Scores under each scale are further normalized for the population mean and standard deviation for that scale. Scores are therefore expressed as standard deviations from the population mean.
  • Archetypes are empirically created sets that serve as reference points for the natural clustering of such sets (patterns) in any human population.
  • Traditional statistical tools such as procedure MODECLUS in SASTM can be used to generate such clusters and arrive at archetypes, or archetypes may be derived empirically, by trial and error.
  • the number of archetypes used in such an analysis will typically range from about six to about twelve. The exact number is defined by the operational needs of the analysis. For the purposes of this embodiment, the number of archetypes needed for analysis of personal style data is defined as the smallest number of archetypes that can generate Pearson correlations of at > 0.50 to at least one of the archetypes, for at least 95% of the population. 625
  • Pearson's correlation reflects the degree to which the variables are related.
  • the most common measure of correlation is the Pearson Product Moment Correlation (called Pearson's correlation for short).
  • Pearson Product Moment correlation When measured in a population the Pearson Product Moment correlation is designated by the Greek letter rho ( ⁇ ). When computed in a sample, it is designated by the letter “r” and is sometimes called “Pearson's r.”
  • Pearson's correlation reflects the degree of linear relationship between two variables. It ranges from +1 to -1. A correlation of +1 means that there is a perfect positive linear relationship between variables.
  • a correlation of -1 means that there is a perfect negative linear relationship between variables. It would be a negative relationship because high scores on the X-axis would be associated with low scores on the Y-axis.
  • a correlation of 0 means there is no linear relationship between the two variables.
  • z x is the variable X converted into z scores and z y is the variable Y converted into z scores.
  • z scores can be computed as follows:
  • the standard normal distribution is a normal distribution with a mean of 0 and a standard deviation of 1. Normal distributions can be transformed to standard normal distributions by the formula:
  • X is a score from the original normal distribution
  • is the mean of the original normal distribution
  • is the standard deviation of original normal distribution.
  • the standard normal distribution is sometimes called the z distribution.
  • a z score always reflects the number of standard deviations above or below the mean a particular score is. For instance, if a person scored a 70 on a test with a mean of 50 and a standard deviation of 10, then they scored 2 standard deviations above the mean. Converting the test scores to z scores, an X of 70 would be:
  • a z score of 2 means the original score was 2 standard deviations above the mean. Note that the z distribution will only be a normal distribution if the original distribution (X) is normal.
  • the following example illustrates the collection and analysis of PTT data from a large human sample, and how correlations were successfully made between archetypes and individual preferences for outdoor activities.
  • the trait scores of 1373 participants were analyzed using standard Principal Component Analysis (SAS Proc PRiNCOMP).
  • SAS Proc PRiNCOMP standard Principal Component Analysis
  • the technique reduced the true dimensionality of the data space to three or four dimensions (Scree plot analysis), with over 80% of the variance in the data being accounted for in the first two Principal Components.
  • the first Principal Component consisted mainly of measures that describe novelty-seeking while the second was composed of those that describe competitiveness.
  • the data were then clustered hierarchically using SAS procedure MODECLUS.
  • Fig. 5 illustrates a high-level block diagram showing targeted marketing based on the user's significance pattern.
  • the user logs onto the system by accessing the Website and entering the correct user name and password.
  • the system retrieves the user's significance pattern, e.g., the mnemonic code "MAU9R.”
  • MAU9R the user's significance pattern
  • the system may target the user at step 506, e.g., by showing ads on the Web page that would likely interest the user. This may be implemented by having the system show only search results that matches the user's archetype and characteristics, such as retrieving products which are classified for ARTISTS (i.e., contain a "yes" on the artist field).
  • ARTISTS i.e., contain a "yes" on the artist field.
  • chat room categorized by archetype may be created thus enabling users of similar personality to chat with each other.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Development Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
EP01955058A 2000-07-06 2001-07-05 Systeme et procede faisant appel a des informations de modeles de portee psychologique pour les mettre en correspondance avec des informations cibles Withdrawn EP1297448A1 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US21646900P 2000-07-06 2000-07-06
US216469P 2000-07-06
PCT/US2001/041261 WO2002005123A2 (fr) 2000-07-06 2001-07-05 Systeme et procede faisant appel a des informations de modeles de portee psychologique pour les mettre en correspondance avec des informations cibles

Publications (1)

Publication Number Publication Date
EP1297448A1 true EP1297448A1 (fr) 2003-04-02

Family

ID=22807197

Family Applications (1)

Application Number Title Priority Date Filing Date
EP01955058A Withdrawn EP1297448A1 (fr) 2000-07-06 2001-07-05 Systeme et procede faisant appel a des informations de modeles de portee psychologique pour les mettre en correspondance avec des informations cibles

Country Status (5)

Country Link
EP (1) EP1297448A1 (fr)
AU (1) AU2001277263A1 (fr)
CA (1) CA2412203A1 (fr)
WO (1) WO2002005123A2 (fr)
ZA (1) ZA200210287B (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103744971A (zh) * 2014-01-10 2014-04-23 广东小天才科技有限公司 一种主动推送信息的方法和设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8019639B2 (en) 2005-07-07 2011-09-13 Sermo, Inc. Method and apparatus for conducting an online information service
US10083420B2 (en) 2007-11-21 2018-09-25 Sermo, Inc Community moderated information
CN113344613B (zh) * 2021-05-26 2023-09-01 北京奇艺世纪科技有限公司 一种数据匹配的方法、装置、电子设备及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103744971A (zh) * 2014-01-10 2014-04-23 广东小天才科技有限公司 一种主动推送信息的方法和设备
CN103744971B (zh) * 2014-01-10 2017-09-15 广东小天才科技有限公司 一种主动推送信息的方法和设备

Also Published As

Publication number Publication date
WO2002005123A2 (fr) 2002-01-17
AU2001277263A1 (en) 2002-01-21
ZA200210287B (en) 2003-12-19
CA2412203A1 (fr) 2002-01-17

Similar Documents

Publication Publication Date Title
US7162432B2 (en) System and method for using psychological significance pattern information for matching with target information
US8010400B2 (en) System and method for using psychological significance pattern information for matching with target information
US20130101970A1 (en) System and method for using psychological significance pattern information for matching with target information
Hasan et al. Fischer linear discrimination and quadratic discrimination analysis–based data mining technique for internet of things framework for Healthcare
US11003694B2 (en) Learning systems for pangenetic-based recommendations
Abrahao et al. Reputation offsets trust judgments based on social biases among Airbnb users
Aditya et al. A comparative analysis of memory-based and model-based collaborative filtering on the implementation of recommender system for E-commerce in Indonesia: A case study PT X
Green et al. Integrating website usability with the electronic commerce acceptance model
Ansari et al. Internet recommendation systems
US9703877B2 (en) Computer-based evaluation tool for selecting personalized content for users
US7720784B1 (en) Emotive intelligence applied in electronic devices and internet using emotion displacement quantification in pain and pleasure space
Chen et al. Predicting the influence of users’ posted information for eWOM advertising in social networks
US6658391B1 (en) Strategic profiling
Li et al. Dynamic mapping of design elements and affective responses: a machine learning based method for affective design
US20050144158A1 (en) Computer network search engine
WO2002010954A2 (fr) Filtrage cooperatif
Huseynov et al. The influence of knowledge-based e-commerce product recommender agents on online consumer decision-making
Blanchard et al. Extracting summary piles from sorting task data
Glowacka Bandit algorithms in information retrieval
Sotoudeh et al. Coping with plenitude: A computational approach to selecting the right algorithm
Jesse et al. Intra-list similarity and human diversity perceptions of recommendations: the details matter
Atanasov et al. Talent spotting in crowd prediction
Ozer et al. Affective design using big data within the context of online shopping
Pallis et al. Model-based cluster analysis for web users sessions
WO2002005123A2 (fr) Systeme et procede faisant appel a des informations de modeles de portee psychologique pour les mettre en correspondance avec des informations cibles

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20021223

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE TR

AX Request for extension of the european patent

Extension state: AL LT LV MK RO SI

17Q First examination report despatched

Effective date: 20061110

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20070201

REG Reference to a national code

Ref country code: HK

Ref legal event code: WD

Ref document number: 1056236

Country of ref document: HK