WO2023172571A1

WO2023172571A1 - Automated candidate generation with matching based on artificial intelligence and predictive analytics

Info

Publication number: WO2023172571A1
Application number: PCT/US2023/014732
Authority: WO
Inventors: Dawn CORNELIUS
Original assignee: Human Enterprise, Inc.
Priority date: 2022-03-08
Filing date: 2023-03-07
Publication date: 2023-09-14

Abstract

Artificial intelligence, predictive analytics and machine learning may be used to create a recommendation system (with less bias) leveraging customers' offline and online patterns, preferences and habits to predict the type of human they will best connect with based on their real behavior patterns. Blockchain may be used to verify identities and create a safer more secure platform for present and future applications of the technology/app. Such a recommendation system may be used in a variety of contexts, including love and romance (specifically long term committed relationships), workforce/talent acquisition and college roommate matching.

Description

AUTOMATED CANDIDATE GENERATION WITH MATCHING BASED ON ARTIFICIAL

INTELLIGENCE AND PREDICTIVE ANALYTICS

BACKGROUND

[0001] There is a disconnected experience between the online world and offline reality. For example, in the romantic connection context, consumers currently pay a lower price for online dating (and often use these tools for free) compared to paying a premium for a traditional matchmaking service. Accordingly, there is a need for technology which closes the gap between online (e.g., online dating) and offline reality of making connections (e.g., meeting people by chance, in a romantic setting). Additionally, in scenarios where matching functionality relies on profiles based on user supplied information, it can be difficult to obtain the necessary information for creating the profiles. Accordingly, there is a need for technology which facilitates the acquisition of information for creating matching profiles. Further, matching functionality often suffers from a deficiency of matches for a given query, and so there is a need for technology that can be used for populating databases for supporting match functionality.

BRIEF DESCRIPTION OF THE DRAWINGS

[0002] FIG. 1 illustrates a customer journey which may be enabled using the disclosed technology; and

[0003] FIG. 2 illustrates a method which may be used to populate a universe;

[0004] FIG. 3 illustrates an exemplary method for creating and using ALgenerated profiles;

[0005] FIG. 4 illustrates an exemplary method for creating and using ALgenerated profiles; and

[0006] FIG. 5 illustrates an exemplary computer system which may be used in creating and using

ALgenerated profiles.

[0007] FIG. 6 is a diagram of the overall system for creating and using Al generated profiles wherein users access the software platform through a web and/or mobile app accessible on mobile devices, tablets, computers or other computing apparatus using methods such as illustrated in and described in the context of FIGS. 1-5. SUMMARY

[0008] In some embodiments, the disclosed technology may be used to implement an algorithm which factors in several different aspects (features) from a person ranging from their social media interactions, text messages and even public records. By gathering more information from different sources and aggregating everything into a single formula, such an embodiment may better connect people by surpassing traditional surveys and accounting for the unconscious wants and needs which may be found across our consumers’ actual interactions with other people, social media, electronic communications (text messages and emails), viewing and listening habits, biometrics, court records and other publicly available data.

DETAILED DESCRIPTION

[0009] Some embodiments may provide a complex algorithm utilizing social media, electronic communications (text messages and emails), viewing and listening habits, biometrics, court records and other publicly available data to produce more positive matches, engagement and human connections than other algorithms. A unique consumer profile may be created from the supplied data which will provide a basis for the consumer’s “true self’ to create the best “human recommendations.” In this context, “human recommendations” may be analogized to product recommendations generated using a recommendation system. The disclosed technology may create a recommendation system leveraging customers’ offline and online patterns, preferences and habits to predict the type of human they will best connect with based on their real behavior patterns. This may be applied in contexts such as human connections for love and romance (specifically long term committed relationships) and may also be applied elsewhere, such as workforce/talent acquisition and college roommate matching.

[0010] Implementations of the disclosed technology may increase the number of users (grow revenue), reduce customers’ time and friction in finding positive human connections and improve the quality of matches.

[0011] User Reviews / Ratings - 1: After each pairing a customer receives, each customer will provide a deep review communicating likes and dislikes, rate the match based on the profile only (a type of product recommendation but in this case the “human recommendation”) of the potential match they receive and indicate if the customer would like to meet in person. Embodiments of the disclosed technology may utilize both explicit (as described here) and implicit ratings (such as clicks, views, purchase records, mouse movements, etc.) in their models. Leveraging reviews and ratings may facilitate embodiments of the disclosed technology retaining knowledge of the customer’s preferences over time relative to the machine’s “human recommendation.” This metric may be used in assessing success as well as optimizing the algorithm adding weights to “human recommendation” features and factors.

[0012] Percentage and Number of Initial Meetings - 2: After a customer reviews the profile of their “human recommendation,” each customer will provide detailed feedback and select to meet or not meet their “recommendation.” By tracking the percentage of and actual number of initial in-person meetings, an embodiment of the disclosed technology may measure the effectiveness of its algorithm and the value of the information being gathered. Using this percentage of initial meetings as a measure of success may be used by some embodiments to close the gap of offline and online realities accelerating positive human connections for our customers.

[0013] App Engagement and Utilization Rate - 3: Another measure of success will be app engagement and utilization rate, growth and churn rate, comparing connection rate achieved by an app implemented using the disclosed technology with other mobile apps and offline services offering matchmaking.

[0014] Other metrics which may be measured in some cases are percentage of subsequent meetings and number of leads, human recommendations and matches generated.

[0015] In some cases, analytics may play the role of raw material used to provide user benefits. In some embodiments, customers may not have to provide data but only access to their data. The data may be applied to create a better algorithm through machine learning processes. Some embodiments may continue harvesting more information as people continue to interact with different elements and as it enlarges its customer base.

[0016] Some embodiments may rely on existing data from consumers through their consent and access to their proprietary data. In some cases, embodiments may not rely on arbitrary or user-generated data instead will analyze actual consumer behavior and past preferences. When a customer provides access to their data, an embodiments may continue to monitor their interactions and preferences over time to keep track of each person’s decisions and changes through different stages of their life. In some embodiments, users may not create their profiles in the app, and instead the app may leverage Al to create each users’ profile after consumers’ consent to access by analyzing their actual user data (types of data noted below) to create their user profile. In some cases, no surveys, no profiles are typed. Each user uploads a selfie picture and has the opportunity to draw' a picture or answer one prompt question which provides the app more data to create a more secure environment (biometric data from the drawing by analyzing the drawing strokes and analyzing key strokes from the one prompt answer) reducing the option for bots or other bad actors on the platform.

[0017] As noted, in some cases success may be measured using an outcome target of successful meetings in person. The variables used for this may include one or more of:

• Biometrics

• Court records

• Streaming habits (viewing and listening)

• Social media habits

• Texts/Language processing data

• Geographic location data

• Demographic

• Overall human/dating preferences (sexual orientation, religion, race, etc.)

[0018] Some implementations may include determining if the algorithm is being fed with the right information and if the algorithm is making the right connections based on the information being provided in order to create successful first meetings.

[0019] Successful first connections are the goal after two people are presented to each other through the app and then compelled to meet offline to learn more about each other and/or take the connection further.

[0020] In some cases, social scientists may be involved to help determine lead scoring and what features, characteristics combined constitute best matches.

[0021] Applications of the disclosed technology may allow for the automation of repetitive, low- value add tasks such as swiping and surveys.

[0022] The following description is exemplary of a customer journey which may be facilitated using the disclosed technology. Further illustration of this type of customer journey is provided in FIG. 1. It should be understood that FIG. 1, like the description below, is intended to be illustrative only, and should not be treated as limiting.

[0023] After matches are created, the app prompts users to shift from in-app texting to video chatting. If a user chooses not to move forward to the next step with their best potential match (bpm), then they are granted the opportunity to extend the in-app texting for a set amount of time. After this time allotment, the user must move forward with video chatting or choose to end the “journey” with the match and move on to their next match.

[0024] Only seven bpms are shown at one time limiting the users’ ability to juggle multiple conversations and matches at one time. The goal of this app is to connect people to “their person” and is tailored to an experience that allows those who are ready for a long term committed relationship to experience success - marrying their online behavior to a more “human” and natural offline experience of meeting someone in a public setting, having a conversation that prompts them to move forward to have more in-person conversations to determine if they are a good match for each other.

[0025] The next step in the customer journey is to have an in-person meeting or date experience. The app automatically prompts users to take this next step in the journey also providing a recommendation engine that powers the date experience. The app leverages the deep data it has for each user to recommend the types of experiences (restaurants, activities, etc.) that would provide the most ideal date experience or in-person meeting. Experiences are tailored to their unique needs. Recommendations can be made for any jurisdiction based on publicly available data.

[0026] The app provides smarter people analytics by analyzing people’s actual statements, mood and intentions on social media, along with other public data sources, simulating this human behavior with autonomously learning machines.

[0027] This app inherently reduces and quite possibly removes biases (unconscious or implicit) based on the process for matching. This may prove extremely beneficial for use cases applied to workforce recruiting / employ er/employee matching.

[0028] Some embodiments may be implemented to recognize the importance of chemistry and attraction. The app helps users to plan the ultimate face-to-face date for them.

[0029] Some embodiments may use blockchain technology to verify the identities of individuals who sign up for services - utilizing an identity vault.

[0030] Some embodiments of the disclosed technology may include functionality to “create the universe” therefore reducing the thin-market problem that every app faces or sometimes referred to as the “empty room problem.” The thin-market or empty room problem is the dilemma matching apps of any kind face when it must recruit an ample number of users onto the platform in order to create quality matches. The disclosed technology may eliminate this issue by “creating the universe.” Some embodiments may create the universe by launching digital marketing campaigns to fill the universe with bpms for each user profile. An illustrative example of this is provided in FIG. 2. Once a user onboards to a platform and their profile is created by the platform’s algorithms, the technology launches a digital search for the bpms for each user and fills the universe with their bpms.

[0031] Some embodiments may use analytics which are predictive.

[0032] This analytics may predict customers’ best choices for a human connection amongst their many different options of people with whom they could match. Some embodiments may determine a profile for each customer and predict their best potential match or matches (“human recommendations”) for a long-term committed relationship. To this end, some embodiments may use predictive analytics. Some embodiments may avoid addressing if an action of one of the two paired people would lead to somewhere different. Instead, embodiments of the disclosed technology may strive to predict the best choice for a person’s initial meeting. Some embodiments of the disclosed technology may avoid answering the “why” question. Instead, embodiments may use a data-driven model paired with a data mining process to get the right information to determine the best features/factors for predicting dating compatibility.

[0033] The disclosed technology may be used to build a recommender system which makes predictions based on users’ historical behaviors. An adage says, “the best predictor of a person’s future behavior is their past behavior.” The disclosed technology may be used to predict consumer preference for a set of “features/factors” in another human based on past experiences. Building on lectures and conversations with subject matter experts regarding predictive models, deep learning and neural networks, the disclosure may be implemented using multiple approaches to building a recommender system.

[0034] However, a preferred approach for implementing a recommender system is to use content- boosted filtering and collaborative filtering using matrix factorization combined with proprietary personalization of this model. Matrix factorization may be used to provide how much a consumer is aligned with a set of latent features and how much a “human recommendation” fits into this set of latent features. These approaches may be used to achieve a goal of finding the similarity between two people among the issues which matter most and to determine if they share similar underlying values, tastes, preferences regarded as latent features.

[0035] To overcome sparsity of data, some embodiments may compute “product descriptions” (consumer profile) based on the consumer’ s data and attributes as well as user demographic to make “human recommendations” to consumers. Some embodiments may also use dimensionality reduction and remove unnecessary users and “products” from where not much is learned and reduce sparsity of user-item rating matrix. Another issue is preventing and reducing the potential for consumers to “game” the recommendation system, which some embodiments may address through processes for monitoring user behavior.

[0036] In some cases, implementing the disclosed technology may include determining which factors/features within available datasets are more useful than others (for example: Facebook versus Instagram, etc.) and which factors/features provide the best intel for consumers’ preferences. Some embodiments may have particular data mining processes which work better for their particular contexts, and will continue gathering information from that actual dataset while monitoring consumer behavior in a less invasive way.

[0037] An illustrative example of the computer-implemented method for creating and using AI- generated profiles is provided in FIG. 3 and FIG. 4. Wherein for each user, from a plurality of users, data is collected by accessing that user’s personal and public information from online platforms other than the software platform.

[0038] The method of FIG. 3 begins with collecting 301 data from each of a plurality of users.

This may be done by for each user wherein that user gives access to that user’s personal and public information from online platforms other than the software platform. After the data is collected 301, a plurality of Al generated profiles could be created 302. This may be done by processing the collected data using one or more machine learning algorithms, wherein the Al-generated profile includes a set of attributes that represent that user's personal information, interests, and preferences. After the Al generated profiles are created 302, the plurality of Al-generated profiles is stored in a database 303. A request and search criteria are received from a first requesting user from the plurality of users for a match 304. A first search profile is generated 305 based on analyzing the first requesting user’s profile and their search criteria with an artificial intelligence algorithm. A search of the database of Al-generated profiles 306 using the first search profile to identify potential matches is deployed. Then, 307 one or more Al-generated profiles from the database are selected based on: (i) the first requesting user's request, (ii) the attributes of the Al-generated profiles, (iii) predictive analytics, and (iv) a scoring system which weights compatibility based on a set of compatibility factors. The first requesting user 308 receives a list of recommended potential matches based on the selected Al-generated profiles.

[0039] The method of FIG. 4 begins with receiving 401 a request and search criteria from a second requesting user from the plurality of users for a match. After the request is received 401, a second search profile is generated based on analyzing the second requesting user’s profile and their search criteria with the artificial intelligence algorithm 402. Using the second search profile to identify potential matches, 403 the database of Al generated profiles is searched. Determining that the match requested by the second requesting user cannot be found in the database 403 based on: (i) the second requesting user's match request 401, (ii) the attributes of the plurality of Al-generated profiles, (iii) predictive analytics, and (iv) the scoring system which weights compatibility based on the set of compatibility factors; (m) based on determining that the requested match cannot be found for the second requesting user, executing a populate the universe process, illustrated in FIG 2 that uses the second search profile to activate digital database population and match generation campaigns in which: (i) the second search profile is used to communicate to potential users who share common attributes with the second search profile; (ii) the potential users who share common attributes with the second search profile are invited to create accounts within the software platform; and (k) upon creating an Al generated profile for a new user which is compatible with the second search profile, recommending the new user to the second requesting user.

[0040] FIG. 5 is a block diagram illustrating an example computing apparatus 500 that may be used in connection with various embodiments described herein. For example, computing apparatus 500 may be programmed to create and perform matches using Al generated profiles, using methods such as illustrated in and described in the context of FIGS. 1-4. Computing apparatus 500 can be a server or any conventional personal computer, or any other processor-enabled device that is capable of wired or wireless data communication. Other computing apparatus, systems and/or architectures may be also used, including devices that are not capable of wired or wireless data communication, as will be clear to those skilled in the art.

[0041] Computing apparatus 500 preferably includes one or more processors, such as processor 510. The processor 510 may be for example a CPU. GPU, TPU or arrays or combinations thereof such as CPU and TPU combinations or CPU and GPU combinations. Additional processors may be provided, such as an auxiliary processor to manage input/butput, an auxiliary processor to perform floating point mathematical operations (e.g. a TPU), a special-purpose microprocessor having an architecture suitable for fast execution of signal processing algorithms (e.g., digital signal processor, image processor), a slave processor subordinate to the main processing system (e.g., back-end processor), an additional microprocessor or controller for dual or multiple processor systems, or a coprocessor. Such auxiliary processors may be discrete processors or may be integrated with the processor 510. Examples of CPUs which may be used with computing apparatus 500 fire, the Pentium processor, Core 17 processor, and Xeon processor, all of which are available from Intel Corporation of Santa Clara, Calif. An example GPU which may be used with computing apparatus 500 is Tesla K80 GPU of Nvidia Corporation, Santa Clara, Calif.

[0042] Processor 510 is connected to a communication bus 505. Communication bus 505 may include a data channel for facilitating information transfer between storage and other peripheral components of computing apparatus 500. Communication bus 505 further may provide a set of signals used for communication with processor 510, including a data bus, address bus. and control bus (not shown). Communication bus 505 may comprise any standard or non-standard bus architecture such as, for example, bus architectures compliant with industry standard architecture (ISA), extended industry’ standard architecture (EISA). Micro Channel Architecture (MCA), peripheral component interconnect (PCI) local bus, or standards promulgated by the Institute of Electrical and Electronics Engineers (IEEE) including IEEE 488 general-purpose interface bus (GPIB). IEEE 696/S-100, and the like.

[0043] Computing apparatus 500 preferably includes a main memory 515 and may also include a secondary memory 520. Main memory §15 provides storage of instructions and data for programs executing on processor 510, such as one or more of the functions and/or modules discussed above. It should be understood that computer readable program instructions stored in the memory’ and executed by processor 510 may be assembler instructions, instniction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state- setting data, configuration data for integrated circuitry', or either source code or object code written in and/or compiled H orn any combination of one or more programming languages, including without limitation Smalltalk. C/C++, Java, JavaScript, Perl, Visual Basic, .NET, and the like. Main memory 515 is typically semiconductor-based memory such as dynamic random access memory (DE AM) and/or static random access memory (SR AM). Other semiconductorbased memory types include, for example, synchronous dynamic random access memory (SDRAM), Rambus dynamic random access memory (RDRAM), ferroelectric random access memory (FR.AM), and the like, including read only memory (ROM).

[0044] The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the users computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Sendee Provider). [0045] Secondary memory 520 may optionally include an internal memory 525 and/or a removable medium 530. Removable medium 530 is read from and/or written to in any well-known manner. Removable storage medium 530 may be. for example, a magnetic tape drive, a compact disc (CD) drive, a digital versatile disc (DVD) drive, other optical drive, a dash memory drive, etc.

[0046] Removable storage medium 530 is a non -Iran si lory computer-readable medium having stored thereon computer-executable code (i.e., software) and/or data. The computer software or data stored on removable storage medium 530 is read into computing apparatus 500 for execution by processor 510.

[0047] The secondary memory 520 may include other similar elements for allowing computer programs or other data or instructions to be loaded into computing apparatus 500. Such means may include, for example, an external storage medium 545 and a communication interface 540, which allows software and data to be transferred from external storage medium 545 to computing apparatus 500. Examples of external storage medium 545 may include an external hard disk drive, an external optical drive, an external magneto-optical drive, etc. Other examples of secondary memory 520 may include semiconductor-based memory such as programmable read-only memory (PROM), erasable programmable readonly memory (EPROM), electrically erasable read-only memory (EEPROM). or flash memory (block-oriented memory similar to EEPROM).

[0048] As mentioned above, computing apparatus 500 may include a communication interface 540. Communication interface 540 allows software and data to be transferred between computing apparatus 500 and external devices (e.g. printers), networks, or other information sources. For example, computer software or executable code may be transferred to computing apparatus 500 from a network server via communication interface 540. Examples of communication interface 540 include a built-in network adapter, network interface card (NIC), Personal Computer Memory Card International Association (PCMCIA) network card, card bus network adapter, wireless network adapter, Universal Serial Bus (USB) network adapter, modem, a network interface card (NIC), a wireless data card, a communications port, an infrared interface, an IEEE 1394 fire-wire, or any other device capable of interfacing system 550 with a network or another computing device. Communication interface 540 preferably implements industry-promulgated protocol standards, such as Ethernet IEEE 802 standards, Fiber Channel, digital subscriber line (DSL), asynchronous digital subscriber line (ADSL), frame relay, asynchronous transfer mode (ATM), integrated digital services network (ISDN), personal communications services (PCS), transmission control protocol/lntemet protocol (TCP/IP), serial line Internet protocol/point to point protocol (SLIP/PPP), and so on, but may also implement customized or non-standard interface protocols as well.

[0049] Software and data transferred via communication interface 540 are generally in the form of electrical communication signals 555. These signals 555 may be provided to communication interface 540 via a communication channel 550. In an embodiment, communication channel 550 may be a wired or wireless network, or any variety of other communication links. Communication channel 550 carries signals 555 and can be implemented using a variety of wired or wireless communication means including wire or cable, fiber optics, conventional phone line, cellular phone link, wireless data communication link, radio frequency C‘RF”) link, or infrared link, just to name a few.

[0050] Computer-executable code (i.e., computer programs or software) is stored in main memory 515 and/or the secondary memory 520. Computer programs can also be received via communication interface 540 and stored in main memory 515 and/or secondary memory 520. Such computer programs, when executed, enable computing apparatus 500 to perform the various functions of die disclosed embodiments as described elsewhere herein.

[0051] In this document, the term ‘'computer- readable medium’’ is used to refer to any non- transitory computer-readable storage media used to provide computer-executable code (e.g., software and computer programs) to computing apparatus 500. Examples of such media include main memory 515, secondary memory 520 (including internal memory 525. removable medium 530, and external storage medium 545), and any peripheral device communicatively coupled with communication interface 540 (including a network information server or other network device). These non -transitory computer-readable media are means for providing executable code, programming instructions, and software to computing apparatus 500. [90] In an embodiment that is implemented using software, the software may be stored on a computer-readable medium and loaded into computing apparatus 500 by way of removable medium 530. I/O interface 535, or communication interface 540. In such an embodiment, die software is loaded into computing apparatus 500 in the form of electrical communication signals 555. The software, when executed by processor 510, preferably causes processor 510 to perform the features and functions described elsewhere herein.

[0052] 170 interface 535 provides an interface between one or more components of computing apparatus 500 and one or more input and/or output devices. Example input devices include, without limitation, keyboards, touch screens or other touch- sensitive devices, biometric sensing devices, computer mice, trackballs, pen-based pointing devices, and the like. Examples of output devices include, without limitation, cathode ray tubes (CRTs), plasma displays, light-emitting diode (LED) displays, liquid crystal displays (LCDs), printers, vacuum florescent displays (VFDs), surface-conduction electron-emitter displays (SEDs), field emission displays (FEDs), and the like.

[0053] Computing apparatus 500 also includes optional wireless communication components that facilitate wireless communication over a voice network and/or a data network. The wireless communication components comprise an antenna system 570, a radio system 565, and a baseband system 560. In computing apparatus 500, radio frequency (RF) signals are transmitted and received over the air by antenna system 570 under the management of radio system 565.

[0054] Antenna system 570 may comprise one or more antennae and one or more multiplexors (not shown) that perform a switching function to provide antenna system 570 with transmit and receive signal paths. In the receive path, received RF signals can be coupled from a multiplexor to a low noise amplifier (not shown) that amplifies the received RF signal and sends the amplified signal to radio system 565.

[0055] Radio system 565 may comprise one or more radios that are configured to communicate over various frequencies. In an embodiment, radio system 565 may combine a demodulator (not shown) and modulator (not shown) in one integrated circuit (IC). The demodulator and modulator can also be separate components. In the incoming path, the demodulator strips away the RF carrier signal leaving a baseband receive audio signal, which is sent from radio system 565 to baseband system 560.

[0056] If the received signal contains audio information, then baseband system 5560 decodes the signal and converts it to an analog signal. Then the signal is amplified and sent to a speaker. Baseband system 560 also receives analog audio signals from a microphone. These analog audio signals are converted to digital signals and encoded by baseband system 560. Baseband system 560 also codes the digital signals for transmission and generates a baseband transmit audio signal that is routed to the modulator portion of radio system 565. The modulator mixes the baseband transmit audio signal with an RF carrier signal generating an RF transmit signal that is routed to antenna system 570 and may pass through a power amplifier (not shown). The power amplifier amplifies the RF transmit signal and routes it to antenna system 570 where the signal is switched to the antenna port for transmission.

[0057] Baseband system 560 is also communicatively coupled with processor 510, which may be a central processing unit (CPU). Processor 510 has access to data storage areas 515 and 520. Processor 510 is preferably configured to execute instructions (i.e., computer programs or software) that can be stored in main memory 515 or secondary memory 520. Computer programs can also be received from baseband processor 560 and stored in main memory 510 or in secondary memory 520. or executed upon receipt. Such computer programs, when executed, enable computing apparatus 500 to perform the various functions of the disclosed embodiments. For example, data storage areas 515 or 520 may include various software modules.

[0058] The computing apparatus further comprises a display 575 directly attached to the communication bus 505 which may be provided instead of or addition to any display connected to the I/O interface 535 referred to above.

[0059] FIG. 6 is a diagram of the overall system for creating and using Al generated profiles wherein users access the software platform through a web and/or mobile app accessible on mobile devices, tablets, computers or other computing apparatus using methods such as illustrated in and described in the context of FIGS. 1-5.

[0060] Various embodiments may also be implemented primarily in hardware using, for example, components such as application specific integrated circuits (ASICs), programmable logic arrays (PLA), or field programmable gate arrays (FPGAs). Implementation of a hardware state machine capable of performing the functions described herein will also be apparent to those skilled in the relevant art. Various embodiments may also be implemented using a combination of both hardware and software.

[0061] To further illustrate potential variations on the ways the disclosed technology could be implemented, the below examples specify various non-exhaustive ways in which the teachings herein may be combined or applied. It should be understood that the following examples, like the other examples and variations set forth herein, are not intended to restrict the coverage of any claims that may be presented at any time in this document or any related document. No disclaimer is intended. The following examples are being provided for nothing more than merely illustrative purposes. It is contemplated that the various teachings herein may be arranged and applied in numerous other ways. It is also contemplated that some variations may omit certain features referred to in the below examples. Therefore, none of the aspects or features referred to below should be deemed critical unless otherwise explicitly indicated as such at a later date by the inventor or by a successor in interest to the inventor. If any claims are presented in this document or a related document that include additional features beyond those referred to below, those additional features shall not be presumed to have been added for any reason relating to patentability.

[0062] Example 1

[0063] A computer-implemented method for creating and using Al-generated profiles comprising the steps of: (a) for each user from a plurality of users, collecting data from that user, the data including: (i) personal information, (ii) interests, and (iii) preferences; wherein the data is collected when that user creates an account on a software platform; wherein collecting data from that user comprises accessing that user’s personal and public information from online platforms other than the software platform; (h) creating a plurality of Al-gcncratcd profiles by, for each user from the plurality of users, creating an AI- generated profile for that user by processing the collected data using one or more machine learning algorithms, wherein the Al-generated profile includes a set of attributes that represent that user's personal information, interests, and preferences; (c) storing the plurality of Al-generated profiles in a database; (d) receiving a request and search criteria from a first requesting user from the plurality of users for a match; (e) generating a first search profile based on analyzing the first requesting user’s profile and their search criteria with an artificial intelligence algorithm; (f) searching the database of Al-generated profiles using the first search profile to identify potential matches; (g) selecting one or more Al- generated profiles from the database based on: (i) the first requesting user's request, (ii) the attributes of the Al-generated profiles, (iii) predictive analytics, and (iv) a scoring system which weights compatibility based on a set of compatibility factors; and (h) providing the first requesting user with a list of recommended potential matches based on the selected Al-generated profiles; (i) receiving a request and search criteria from a second requesting user from the plurality of users for a match; (j) generating a second search profile based on analyzing the second requesting user’s profile and their search criteria with the artificial intelligence algorithm; (k) searching the database of Al-generated profiles using the second search profile to identify potential matches; (1) determining that the match requested by the second requesting user cannot be found in the database based on: (i) the second requesting user's match request, (ii) the attributes of the plurality of Al-generated profiles, (iii) predictive analytics, and (iv) the scoring system which weights compatibility based on the set of compatibility factors; (m) based on determining that the requested match cannot be found for the second requesting user, executing a fill the universe process that uses the second search profile to activate digital database population and match generation campaigns in which: (i) the second search profile is used to communicate to potential users who share common attributes with the second search profile; (ii) the potential users who share common attributes with the second search profile are invited to create accounts within the software platform; and (n) upon creating an Al generated profile for a new user which is compatible with the second search profile, recommending the new user to the second requesting user. [0064] Example 2

[0065] The method of example 1, wherein the machine learning algorithms include natural language processing, clustering analysis, content-boosted filtering and collaborative filtering using matrix factorization.

[0066] Example 3

[0067] The method of any of examples 1-2, wherein each of the Al-generated profiles includes a combination of quantitative and qualitative data.

[0068] Example 4

[0069] The method of any of examples 1-3, wherein the attributes of the Al-gcncratcd profiles include demographic information, personality traits, interests, hobbies, and values.

[0070] Example 5

[0071] The method of any of examples 1-4, further comprising: (a) generating a compatibility score between potential users and the second requesting user based on the potential users’ attributes and the second search profile; and (b) providing the second requesting user with the compatibility score for each potential user who shares attributes with the second search profile.

[0072] Example 6

[0073] ‘The method of any of examples 1-5, wherein the method includes the software platform periodically updating the Al-generated profiles based on user feedback and behavior.

[0074] Example 7

[0075] The method of any of examples 1-6, wherein the software platform uses machine learning to improve accuracy of its matches over time.

[0076] Example 8

[0077] The method of any of examples 1-7, wherein the search criteria received from the second requesting user comprise at least one of desired age range, gender, location, personality traits, interests, hobbies, and preferences.

[0078] Example 9

[0079] The method of any of examples 1-8, wherein for each user from the plurality of users, that user’s personal and public information comprises: social media accounts, shopping activity, viewing and listening habits, biometric data, financial information, texts and language processing data, publicly available information such as court records, real estate transactions, education records, geographic information and demographics such as age, ethnicity, gender, religion, and other personal identifying information.

[0080] Example 10

[0081] The method of any of examples 1-9, wherein the compatibility factors comprise positive personality traits, intelligence, social network, social conformity, attractiveness, wealth and status, familiarity, morals and values.

[0082] Example 11

[0083] The method of any of examples 1-10, wherein the potential users who share common attributes with the second search profile arc invited to create accounts within the software platform using digital database population and match generation tactics comprising email, social media ads, and mobile ads.

[0084] Example 12

[0085] The method of any of examples 1-11, wherein, for each user from the plurality of users, creating the Al-generated profile for that user does not comprise that user creating the AI- generated profile by submission of typed information.

[0086] Example 13

[0087] A non-transitory computer readable medium having stored thereon instructions operable to configure a processor to perform the method of any of examples 1-12.

[0088] Example 14 [0089] A computing system for creating and using AT-generated profiles, the computing system comprising the non-transitory computer readable medium of example 13 and a processor configured by instructions stored on the non-transitory computer readable medium.

[0090] It should be understood that any one or more of the teachings, expressions, embodiments, examples, etc. described herein may be combined with any one or more of the other teachings, expressions, embodiments, examples, etc. that are described herein. The abovedescribed teachings, expressions, embodiments, examples, etc. should therefore not be viewed in isolation relative to each other. Various suitable ways in which the teachings herein may be combined will be readily apparent to those of ordinary skill in the art in view of the teachings herein. Such modifications and variations are intended to be included within the scope of the claims. Other variations are also possible, and will be immediately apparent to and could be implemented without undue experimentation by those of ordinary skill in the art in light of this disclosure. Accordingly, the protection provided by this document, or any related document, should not be treated as being limited to the embodiments, examples and variations described herein, but instead should be understood as being defined by the claims set forth in the relevant document when the terms of those claims which are explicitly defined in the following paragraphs or by subsequently provided explicit definitions are given their explicit definitions, and when the other terms are given their broadest reasonable definitions as provided by a general purpose dictionary.

[0091] In this document, “based on” should be understood to mean that something is determined at least in part by the thing it is indicated as being “based on.” The phrase “based EXCLUSIVELY on” is used to indicate that something must be completely determined based on something else.

[0092] In this document, modifiers such as “first,” “second,” etc. should be understood as labels used to facilitate identification of a particular item being referred to, and, unless context clearly indicates otherwise, should not be understood as implying any required order or other relationship between the labeled objects. For example, a statement that there is a “first value” and a “second value” should not be understood as implying that one of the values comes first, or is determined first, or even that the “first value” and the “second value” are necessarily different values.

[0093] In this document, “set” should be understood to refer to a number, group or combination of zero or more elements of similar nature, design or function. The terms “subset” and “superset" should be understood as being synonymous with set, with the different terms being used for the sake of understanding, and with a subset and a superset of a set potentially each having the same cardinality as the set, rather than necessarily being smaller or larger than the set they are contained by (in the case of a subset) or that they contain (in the case of a superset).

Claims

CLAIMS A computer- implemented method for creating and using Al-generated profiles comprising the steps of:

(a) for each user from a plurality of users, collecting data from that user, the data including:

(i) personal information,

(ii) interests, and

(iii) preferences wherein the data is collected when that user creates an account on a software platform; wherein collecting data from that user comprises accessing that user’s personal and public information from online platforms other than the software platform;

(b) creating a plurality of Al-generated profiles by, for each user from the plurality of users, creating an Al-generated profile for that user by processing the collected data using one or more machine learning algorithms, wherein the Al-generated profile includes a set of attributes that represent that user's personal information, interests, and preferences;

(c) storing the plurality of Al-generated profiles in a database;

(d) receiving a request and search criteria from a first requesting user from the plurality of users for a match;

(e) generating a first search profile based on analyzing the first requesting user’ s profile and their search criteria with an artificial intelligence algorithm;

(f) searching the database of Al-generated profiles using the first search profile to identify potential matches;

(g) selecting one or more Al-generated profiles from the database based on:

(i) the first requesting user's request,

(ii) the attributes of the Al-gcncratcd profiles,

(iii) predictive analytics, and

(iv) a scoring system which weights compatibility based on a set of compatibility factors; and (h) providing the first requesting user with a list of recommended potential matches based on the selected Al-gcncratcd profiles;

(i) receiving a request and search criteria from a second requesting user from the plurality of users for a match;

(j) generating a second search profile based on analyzing the second requesting user’s profile and their search criteria with the artificial intelligence algorithm;

(k) searching the database of Al-generated profiles using the second search profile to identify potential matches;

(l) determining that the match requested by the second requesting user cannot be found in the database based on:

(i) the second requesting user's match request,

(ii) the attributes of the plurality of Al-generated profiles,

(iii) predictive analytics, and

(iv) the scoring system which weights compatibility based on the set of compatibility factors;

(m) based on determining that the requested match cannot be found for the second requesting user, executing a fill the universe process that uses the second search profile to activate digital database population and match generation campaigns in which:

(i) the second search profile is used to communicate to potential users who share common attributes with the second search profile;

(ii) the potential users who share common attributes with the second search profile are invited to create accounts within the software platform; and

(n) upon creating an Al generated profile for a new user which is compatible with the second search profile, recommending the new user to the second requesting user.

The method of claim 1, wherein the machine learning algorithms include natural language processing, clustering analysis, content-boosted filtering and collaborative filtering using matrix factorization. The method of any of claims 1 -2, wherein each of the AT-generated profiles includes a combination of quantitative and qualitative data. The method of any of claims 1-3, wherein the attributes of the Al-generated profiles include demographic information, personality traits, interests, hobbies, and values. The method of any of claims 1-4, further comprising:

(a) generating a compatibility score between potential users and the second requesting user based on the potential users’ attributes and the second search profile; and

(b) providing the second requesting user with the compatibility score for each potential user who shares attributes with the second search profile. The method of any of claims 1-5, wherein the method includes the software platform periodically updating the Al-generated profiles based on user feedback and behavior. The method of any of claims 1-6, wherein the software platform uses machine learning to improve accuracy of its matches over time. The method of any of claims 1-7, wherein the search criteria received from the second requesting user comprise at least one of desired age range, gender, location, personality traits, interests, hobbies, and preferences. The method of any of claims 1-8, wherein for each user from the plurality of users, that user’s personal and public information comprises: social media accounts, shopping activity, viewing and listening habits, biometric data, financial information, texts and language processing data, publicly available information such as court records, real estate transactions, education records, geographic information and demographics such as age, ethnicity, gender, religion, and other personal identifying information. The method of any of claims 1 -9, wherein the compatibility factors comprise positive personality traits, intelligence, social network, social conformity, attractiveness, wealth and status, familiarity, morals and values. The method of any of claims 1-10, wherein the potential users who share common attributes with the second search profile are invited to create accounts within the software platform using digital database population and match generation tactics comprising email, social media ads, and mobile ads. The method of any of claims 1-11, wherein, for each user from the plurality of users, creating the Al-generated profile for that user does not comprise that user creating the AI- generated profile by submission of typed information. A non-transitory computer readable medium having stored thereon instructions operable to configure a processor to perform the method of any of claims 1-12. A computing system for creating and using Al-generated profiles, the computing system comprising the non-transitory computer readable medium of claim 13 and a processor configured by instructions stored on the non-transitory computer readable medium.