System and method for user communication in a network

Abstract

The method is implemented by an electronic device and includes sending a registration request for a first user, receiving photo identification information including appealing image information, identifying a set of preliminary images stored on the electronic device based at least in part on the appealing image information, and displaying the set of preliminary images.

Description

[Technical Field]

[0001] (CROSS-REFERENCE TO RELATED APPLICATIONS) This application claims priority to U.S. Provisional Patent Application No. 63 / 534,087, filed August 22, 2023, entitled "System and Method for User Communication in a Network," the entire contents of which are incorporated herein by reference. The present disclosure relates generally to the field of online matching, and more particularly to improving the onboarding process and increasing the likelihood of a match. [Background technology]

[0002] Online communities provide users with a convenient platform for finding each other, posting content, and communicating with each other. Some online communities match users with each other based on their shared interests (e.g., matching job seekers with job openings, or matching members with other members in online dating services). In online dating services, users may communicate with other users using various communication methods while searching for potential dates. [Brief explanation of the drawings]

[0003] For a better understanding of the present disclosure, and the features and advantages thereof, reference is made to the following description taken in conjunction with the accompanying drawings, in which like reference numerals represent like parts and in which:

[0004] [Figure 1A] FIG. 1 illustrates an example of the first page of a subject's profile in an online community. [Figure 1B] FIG. 10 illustrates an example of a second page of a subject's profile in an online community. [Figure 1C] FIG. 10 illustrates an example of a third page of a subject's profile in an online community.

[0005] [Figure 1D] FIG. 1 shows an example of a portion of a searcher's profile. [Figure 1E] FIG. 10 shows an example of a portion of another searcher's profile.

[0006] [Figure 1F] FIG. 10 illustrates a first example of the first page of a user's profile according to an implementation of the present disclosure. [Figure 1G] FIG. 10 illustrates a second example of page 1 of user Brettman's profile, according to an implementation of the present disclosure.

[0007] [Figure 1H] FIG. 10 illustrates an example profile in which a searcher navigates through successive vertical pages, according to an implementation of the present disclosure.

[0008] [Figure 2] FIG. 1 illustrates an algorithm for encouraging users to add photos to their profiles, according to one implementation of the present disclosure.

[0009] [Figure 3] FIG. 10 illustrates an algorithm for narrowing down a population based on basic information, according to an implementation of the present disclosure.

[0010] [Figure 4] FIG. 10 illustrates an algorithm for selecting images of a user that are likely to be well-received among people who are likely to be interested in the user, according to one implementation of the present disclosure.

[0011] [Figure 5] FIG. 10 illustrates an algorithm for adding interests to a user's profile, according to one implementation of the present disclosure.

[0012] [Figure 6] FIG. 10 illustrates an algorithm for determining potential shared interests with a searcher based on the interests of a subject, according to one implementation of the present disclosure.

[0013] [Figure 7A] FIG. 1 illustrates a first portion of an algorithm for determining subject interests to highlight to a searcher, according to one implementation of the present disclosure.

[0014] [Figure 7B] FIG. 10 illustrates a second portion of an algorithm for determining target interests to highlight to a searcher when considering the searcher's "likes," according to one implementation of the present disclosure.

[0015] [Figure 8] FIG. 1 illustrates an algorithm for dynamically ordering content according to one implementation of the present disclosure.

[0016] [Figure 9] FIG. 1 illustrates a computing device according to an implementation of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0017] Users of online dating services typically have profiles that are both "searchers" and "targets." When a first user evaluates a second user's profile and determines whether they are a match (e.g., by sending unfavorable feedback such as "dislike" or favorable feedback such as "like"), the first user becomes the "searcher" and the second user becomes the "target." In many dating services, a match occurs when a first user expresses a favorable interest in a second user, and the second user subsequently expresses a favorable interest in the first user's profile as a searcher, making the second user a target.

[0018] Existing dating services include multiple profiles, each corresponding to a user who can be either a searcher or a target. Each profile includes one or more interests of the respective user. In a typical dating service, some users have expressed interest in some other users by sending positive feedback.

[0019] Therefore, such dating services have received various information from users via a network interface or the like. The information for each user may include, for example, the user's photo, the user's interests, the user's tolerance level, and the user's preferences. In addition, the information from each user may include the user's interests in other users. Dating services typically receive multiple pieces of this data for each user as users add more information and provide more positive feedback in an attempt to successfully match.

[0020] The following basic information can be considered as a basis for describing the present disclosure. Such information is presented for illustrative purposes only and should not be construed as limiting the scope of the present disclosure and its potential applications.

[0021] Online dating services traditionally involve detailed profiles containing a great deal of information about the user. These detailed profiles have become unpopular for several reasons, including the lengthy onboarding process. For example, some dating services require users to provide such detailed information that it takes 20 to 45 minutes to complete the profile.

[0022] As a result, some dating services have attempted to reduce the onboarding process to just 30 seconds, and to achieve this onboarding efficiency, the level of detail in user profiles to get started has been reduced to just a photo.

[0023] However, in this efficient paradigm, some users prefer a deeper level of matching than the superficial attractiveness provided by a photo. For example, a user may want to learn about another user's interests (e.g., hobbies, beliefs, etc.). Previously, users informed dating services of their interests by entering their own interests, leading to inconsistent identification of the same interests by different users. Alternatively, users could search service-generated lists to identify their interests, adding to the onboarding process.

[0024] Additionally, in this efficient paradigm, photos become especially important for profiles due to the lack of traditional profile details: a service striving for successful matches would naturally be interested in users who have uploaded photos that are most likely to bring users success on the service.

[0025] Additionally, in such online communities, users may make a matching decision in a very short time, such as within one or two seconds. In fact, many users do not tap beyond the initial screen of a target's profile. Therefore, the information presented on the initial screen is the target's first and only opportunity to prevent the searcher from making a permanent decision to decline further interaction with the target.

[0026] Furthermore, while users of conventional services can update their profiles at any time, the profiles themselves are typically static. That is, if two searchers simultaneously view a target's profile, the service will display the same target's profile to both searchers. If the dating service could personalize a target's profile for each of the two searchers by displaying information to each searcher about targets that a particular searcher is most likely to find relevant, the two searchers' level of interest in the target could be increased.

[0027] To address these challenges and others, various implementations of the present disclosure may implement systems and methods for user communication in a network, as described herein.

[0028] A server in such an online community can display a user profile in the form of one or more pages, each of which can contain one or more elements, each of which represents, for example, a field of content that can be rendered by an electronic device (e.g., biography, job title or description, educational institution).

[0029] 1A is a diagram illustrating an example of a first page of a subject's profile in an online community; FIG. 1B is a diagram illustrating an example of a second page of a subject's profile in an online community; and FIG. 1C is a diagram illustrating an example of a third page of a subject's profile in an online community.

[0030] In particular, Figure 1A includes a first index 12 indicating that page 1 of a five-page profile of user Katie is being displayed. Page 1 includes a first photo and biography 110 of user Katie.

[0031] FIG. 1B includes a second index 14 indicating that page two of user Katie's profile is currently being displayed. Page two includes a first element 120, a second element 130, a third element 140, and a fourth element 150. The first element 120 indicates the title or position of user Katie. The second element 130 indicates the school that user Katie attends. The third element 140 indicates the location of user Katie. The fourth element 150 indicates the distance from the viewer (searcher) to user Katie.

[0032] 1C includes a third index 16 indicating that page 3 of user Katie's profile is being displayed. Page 3 includes element 160. Element 160 includes additional photos. These photos may be determined as described below with respect to FIGS. 2 and / or 4.

[0033] An application program on the searcher's electronic device can navigate between pages of the user Katie's profile. An application program is software that runs on an electronic device for a specific purpose. Application programs are typically downloaded from an "app store," such as, but not limited to, the Apple App Store, Google Play, Samsung Galaxy Store, or Valve Steam. Examples of online dating application programs include Tinder® by Tinder LLC and Hinge® by Hinge Inc., both owned by Match Group LLC. In some implementations, an application program is a web browser that executes code or a program at a designated network location, such as a website. In such a situation, the code or program at the network location may be considered an application program, such as in the case of Match.com, owned by Match Group LLC.

[0034] Furthermore, a searcher's electronic device is not limited to a person's owned electronic device; a user's electronic device may be any electronic device through which the user can log into an online community. As such, it is specifically contemplated that a user's electronic device may be owned, leased, or provided by someone else.

[0035] In some implementations, if the application program does not receive user input within a predetermined period of time, the program can move between pages (e.g., like a carousel). In other implementations, if the application program receives a specific user input, the program can move between pages. For example, the application program can advance from page 1 to page 2 of the profile when it receives a right input (e.g., tapping the right side of the touchscreen, pressing the right arrow, dragging to the right, or other selection input). Conversely, the application program can move from page 2 of the profile back to page 1 when it receives a left input (e.g., tapping the left side of the touchscreen, pressing the left arrow, dragging to the right, or other selection input).

[0036] Traditionally, the order in which content in a target's profile is displayed to a searcher has been static. However, sometimes a user's impression of a profile is based on the content they see first. Therefore, it can be advantageous for a matching community to allow users to present their best attributes first (e.g., on the very first page of their profile).

[0037] In various implementations of the present disclosure, a server can run a dynamic content ordering algorithm to promote attributes (e.g., elements) of a subject's profile to the first page of the display. Further implementations of the algorithm can personalize the ordering of attributes based on searcher preferences.

[0038] For example, the server may receive preferences from user Jane indicating that she is looking for a long-term partner. The server may also receive preferences from user Liz indicating that she is looking for new friends. Thus, Figure 1D illustrates an example portion of a profile for searcher Jane. Figure 1E illustrates an example portion of a profile for another searcher, Liz.

[0039] In this way, the server can prioritize displaying various elements of user Bretman's profile to a searcher based on the element's value. For example, the server can prioritize elements of Bretman's profile if they match Jane or Liz's preferences (e.g., have identical or overlapping values).

[0040] That is, the server can analyze the profiles of Jane and Bretman to determine that certain elements should be prioritized for Jane. Similarly, the server can analyze the profiles of Liz and Bretman to determine that certain elements should be prioritized for Liz. The server can send information to each of Liz and Jane to display Bretman's profile.

[0041] This information may indicate the order in which Bretman's profile should be displayed to each recipient. This information may include, for example, a flag indicating the cohort to which the searcher (e.g., Jane or Liz) belongs.

[0042] A cohort is generally a group of users who share defining characteristics in a particular context. For example, there may be a cohort defined based on a user's gender combined with the gender the user is interested in. One such cohort may be women who are interested in women. Thus, a particular user is often a member of multiple cohorts, each with a different context. In this example involving Jane and Liz, the cohorts may be defined at least in part based on their individual relationship goals.

[0043] The information itself may follow a particular data structure that includes one or more fields, each of which may correspond to a particular element of the profile. Thus, for example, a first field may contain the subject's name (e.g., "Bretman"), a second field may contain the subject's image, a third field may contain the subject's biography, a fourth field may contain the subject's relationship goals, etc.

[0044] The searcher's electronic device receiving the information may display the contents of certain fields on the first page of the profile, or may display them in a different order.

[0045] For example, if Bretman's relationship goal is "Looking for long term, short term acceptable," the server may determine that Bretman's relationship goal matches Jane's relationship goal of "long term partner." Thus, the server may cause Bretman's profile to be displayed on Jane's electronic device, as shown in FIG. 1F.

[0046] 1F is a diagram illustrating a first example of page 1 of user Bretman's profile according to one implementation of the present disclosure. As shown in FIG. 1F, when Jane views Bretman's profile, his relationship goals, rather than his biography, are displayed on page 1 of his profile. Displaying matching relationship goals on page 1 of Bretman's profile is advantageous for creating the best first impression for Jane.

[0047] Furthermore, because Bretman's relationship goal is "long-term seeking, short-term acceptable," the server can determine that Bretman's relationship goal does not match Liz's relationship goal of "new friends." The server can determine that Bretman's relationship goal should not be prioritized for Liz. Thus, the server can cause Liz's electronic device to display the first page of Bretman's profile, which includes his biography but not his relationship goals.

[0048] 1G illustrates a second example of page 1 of user Bretman's profile in accordance with one implementation of the present disclosure. Because Bretman's relationship goals do not match Liz's relationship goals, showing his background on page 1 of Bretman's profile can provide Liz with the best first impression of him.

[0049] 1A to 1C, user Katie's profile page is perceived as being landscape-oriented, i.e., a searcher viewing the page moves left and right across the page. In contrast, FIG. 1H illustrates an example profile 100 in which a searcher sequentially moves through pages vertically, according to one implementation of the present disclosure.

[0050] Profile 100 further includes page 1 110, page 2 130, and page 3 160. In the implementation of FIG. 1H, a user can vertically scroll profile 100 on an electronic display device, such as a smartphone. FIG. 1H illustrates profile 100 in a state where the device has scrolled past page 1 110 and is currently displaying page 2 130 but has not yet scrolled to page 3 160. While FIG. 1H depicts pages 1 110, 2 130, and 3 160 as separate portions, those skilled in the art will understand that these pages can be scrolled continuously and displayed together. Thus, an application program on the electronic device can smoothly scroll to simultaneously display all or part of page 1 110 and all or part of page 2 130, depending on, for example, the size of the display and the size of the profile. Similarly, all or part of page 2 130 can simultaneously display all or part of page 3 160, depending on, for example, the size of the display and the size of the profile.

[0051] Page 1 110 includes a photograph 120, which may be determined as described below with respect to Figure 2. Page 1 110 may include one or more elements (not shown in Figure 1H).

[0052] The second page 130 may include one or more groups of one or more elements, such as a first element portion 140 and a second element portion 150. As shown in FIG. 1H, the first element portion 140 includes a + (plus) icon and two elements (e.g., title, geographic location, distance, travel time, relationship of interest, hobby, belief, etc.). The second element portion 150 includes four elements. The content of the elements in the second element portion 150 is typically different from the content of the elements in the first element portion 140. In many implementations, the type of one or more elements in the second element portion 150 (e.g., hobby, belief, location, etc.) is the same as the type of one or more elements in the first element portion 140. In the example shown in FIG. 1H, the searcher has selected the first element portion 140 but has not selected the + icon, as indicated by the fingerprint. The second page 130 may include one or more photographs (not shown in FIG. 1H).

[0053] Page 3 160 includes element portion 170. Element portion 170 also includes four elements (e.g., interests). As noted above, the elements in element portion 170 typically differ in content from the elements in first element portion 140 and / or second element portion 150, but are necessarily different in type. Page 3 160 may also include one or more photographs (not shown in FIG. 1H).

[0054] In another implementation of the present disclosure, FIG. 2 illustrates an algorithm that encourages users to add photos to their profile.

[0055] The server can accumulate various data regarding top-rated profile photos. A "top-rated" profile photo is generally defined as the photo on a target's profile that receives the most "likes" when searchers view the photo. In some implementations, a different definition is used, such as the photo with the highest percentage of searchers who "liked" the target's profile. In this manner, various implementations of the present disclosure can identify user photos that are likely to be top-rated and potentially increase the likelihood of a match.

[0056] Photo performance data pertains to millions of existing photos, with thousands more being uploaded daily. Human or machine analysis of the data can build computer models that identify highly rated profile photos. Models can also be generated for detecting users' faces and / or the server can be programmed with the models. Based on these models, when a user grants an application program access to their photo library, the application program can detect the user's best profile photos. In various implementations, the server can select and arrange photos to create profiles that consistently represent various interests.

[0057] Additionally, a user's interests can be detected based on their local photo library or other photo repositories to which they have access. Such photo repositories can be Drive® by Google LLC, iCloud® by Apple Inc., or Facebook® by Meta Platforms, Inc. Interests detected in those photos can be suggested or automatically added to the user's profile. These interests can then be displayed on the user's profile for searchers to see or used by the system in suggesting targets.

[0058] The algorithm 200 starts at S205 and proceeds to S215.

[0059] At S215, the server receives a registration request from the first user, including the first user's preferences, such as the gender the first user is willing to match with, the age range the first user is willing to match with, the geographic distance the first user is willing to match with, etc. The registration request may also include preferences, such as hair color of potential matches.

[0060] The registration request may also include a photograph or video of the first user. In some such cases, the photograph or video is a verification video that can be used to determine whether the first user is who they claim to be. In some implementations, the registration request may include a voice recording of the user. In some such implementations, the server may generate a biometric identification of the first user's face based at least in part on the verification photograph or video of the first user. The server may use this biometric identification to identify whether another facial photograph shows the first user's face. This biometric identification may include, for example, detailed facial features.

[0061] In some implementations, the server can receive a photo or video of the first user to include in the first user's profile. In various implementations, this profile photo or video can be the same as or different from the verification photo or video.

[0062] The algorithm 200 then proceeds to S225.

[0063] At S225, the server displays the second user's profile to the first user. The server, for example, transmits the second user's profile to the first user's electronic device. The server then receives preferences for the second user's profile from the first user. These preferences can be manifested by a drag gesture, such as dragging in a particular direction, thereby indicating interest. The action can be a tap or click gesture, such as tapping an icon representing a heart, a thumbs-up, or the word "like," or other equivalent. The algorithm 200 then proceeds to optional S235.

[0064] In optional S235, the server receives an action from the third user on a portion of the first user's profile. As previously described, the action may be a gesture such as a drag or a tap or click on an icon. The algorithm 200 then proceeds to S245.

[0065] In S245, the server narrows the user population based on basic information such as tolerances, preferences, likes, etc. S245 is described in more detail below with respect to Figure 3. The algorithm 200 then proceeds to S255.

[0066] At S255, the server determines one or more attributes of the appealing image based at least in part on the narrowed population: In an implementation in which the server receives a like for the first user from a third user, the appealing image may include the first user's profile image. As described above, this determination may be based on data accumulated by the server regarding highly rated photos, typically resulting in an increase in "likes" for the profile. The server may determine the attributes via deterministic programming and / or machine learning (also referred to as artificial intelligence or "AI"). These attributes may identify, for example, the user's face, natural yet indirect lighting, a clear photo (e.g., a photo with clear and distinct details), or a user's smile. They may also identify objectionable features. These attributes may represent, for example, a preference for fewer faces in an image rather than more, or a preference to avoid blurry photos. These attributes may further represent, for example, a preference for a subject's posture other than standing, sitting, or lying down. The algorithm 200 then proceeds to S265.

[0067] At S265, the server transmits photo identification information to the first user's electronic device, the photo identification information including and / or identifying attributes of the one or more appealing images, and may also include a verification video or photo of the first user and / or biometric information of the first user.

[0068] The electronic device may then select images of the first user that are more likely to be liked by people who are likely to be interested in the first user, as will be described in more detail below with respect to Figure 4. The algorithm 200 then proceeds to S275.

[0069] At S275, the server receives the uploaded image from the first user's electronic device, for example, via an application program. The algorithm 200 then proceeds to S285.

[0070] At S285, the server adds the images to the first user's profile. In some implementations, the server can recognize the first user's interests as manifested by the images. For example, if the server recognizes a football in the image, the first user may be interested in football. Algorithm 200 then proceeds to S295, where algorithm 200 ends.

[0071] FIG. 3 illustrates an algorithm 300 for narrowing down a population based on basic information, according to one implementation of the present disclosure.

[0072] Algorithm 300 begins at S310 and proceeds to S320, where the server determines potential favorites for the first user based at least in part on the profile of the second user who was liked at S225 and the first user's tolerance level. In this way, the universe from which appealing photos are determined can be limited to users who are likely to be of interest to the first user. Algorithm 300 then proceeds to S330.

[0073] At S330, the server determines potential romantic partners for the first user based at least in part on the third user's profile and potential romantic partner tolerances. In this manner, the universe from which appealing photos are determined can be limited to users who are likely to be of interest to the first user. The algorithm 300 then proceeds to S340.

[0074] At S340, the server optionally narrows down the first user's potential favorites based at least in part on the first user's preferences. In this way, the universe from which appealing photos are determined can be limited to users who are more likely to be of interest to the first user. The algorithm 300 then proceeds to S350.

[0075] At S350, the server optionally narrows the potential partners based on the potential partners' preferences, thereby limiting the universe from which appealing photos are determined to users who are more likely to be of interest to the first user.

[0076] The algorithm 300 then proceeds to S360 and ends.

[0077] FIG. 4 illustrates an algorithm 400 for selecting images of a user that are likely to be well-received among people who are likely to be interested in the user, according to one implementation of the present disclosure.

[0078] The algorithm 400 begins at S410 and proceeds to S420, where the electronic device sends a registration request for a first user to a server. As previously described, the registration request may include the first user's tolerance level, the first user's preferences, a verification photo or video of the first user, and / or a profile photo or video of the first user. The algorithm 400 then proceeds to S430.

[0079] At optional S430, the server may transmit the second user's profile to the first user's electronic device, which may output (e.g., display) the second user's profile. The first user may then express his or her preferences in the second user's profile, such as by "liking" the profile. The electronic device may transmit this expression of preferences to the server. The algorithm 400 then proceeds to S440.

[0080] At S440, the electronic device receives photo identification information including appealing image information. The appealing image information may indicate an image that performs in a particular way in online matching, such as a highly rated image. For example, a photo of a man holding a fish may be known not to receive a high rating, whereas a photo of a man without a shirt may be known to receive a high rating. The photo identification information may include a biometric identification of the first user's face.

[0081] Thus, in some implementations, the server can determine the photo identification based at least in part on the second user's actions on the profile. Accordingly, some implementations of algorithm 400 can select photos of the first user that are more likely to be favorably rated by users who are likely to be of interest to the first user based on the photo identification. Algorithm 400 then proceeds to S450.

[0082] At S450, the electronic device identifies a preliminary set of images for the first user based at least in part on the appealing image information. An application program on the electronic device can then access images and / or videos in the electronic device's camera roll. Camera rolls are a common feature on smartphones, for example. In some implementations, software on the electronic device can access all images stored locally on the electronic device, such as images downloaded from a social media application program. In advanced implementations, the electronic device can access images and / or videos "on the cloud" via a network interface.

[0083] In some implementations, the electronic device simply scans images in a camera roll or a set of photos selected by the user for faces. In other implementations, the electronic device identifies a preliminary set of images based at least in part on biometric identification information to distinguish photos of the first user's face from photos of other people. In such implementations, the photo identification information may include expected facial attributes (e.g., eye distance or nose shape). Algorithm 400 then proceeds to S460.

[0084] In many implementations, a camera roll may contain hundreds of photos. Requiring the first user to scroll through all of these photos to determine which are likely to receive high ratings and the most likes can be burdensome, and the user may not even know which photos will receive high ratings. Therefore, in S460, the electronic device displays this preliminary set of images to the first user. The electronic device can then visually identify photos that include a face, satisfy appealing image information, and, optionally, satisfy the first user's biometric identification information.

[0085] For example, the electronic device may display all photos containing faces and surround those photos that satisfy the appeal image information with a colored border. In another example, the electronic device displays a predetermined number (e.g., 36) of photos containing faces that satisfy the first user's biometric identification information and best satisfy the appeal image information (e.g., have the highest scores based on the criteria in the appeal image information). The electronic device then surrounds the top 6 of the 36 photos with a different colored border. Of course, other implementations are possible. The algorithm 400 then proceeds to S470.

[0086] At S470, the first user approves the set of photos. In some implementations, this set is a subset of the preliminary set of photos. The first user may, for example, approve the top six photos of the 36 photos displayed. The first user may also exclude one or more of the preliminary set of photos from the set of photos. Thus, the electronic device may maintain the privacy aspects of the first user. The first user may also include other photos in the set, regardless of whether these photos are part of the preliminary set. The algorithm 400 then proceeds to S480.

[0087] In S480, the electronic device sends, for example, the approved set of images to a server. The algorithm 400 then proceeds to S490 and ends.

[0088] At S450, the identification of the preliminary set of images may be enhanced based on previous input by the first user. This photo identification information may, for example, indicate that full-body photos are likely to be highly rated. Nevertheless, the first user may have excluded one or more full-body photos of themselves when previously executing S470. Thus, the electronic device may exclude another full-body photo of the first user in the next preliminary set of images.

[0089] The first user may also have frequently included a photo of the first user holding a fish when previously executing S470. Such a photo may not be expected to receive a high rating. Nevertheless, the electronic device may include the photo of the first user holding a fish in the next preliminary set of images.

[0090] To maintain user privacy, machine learning enabling these inclusions and / or exclusions can be performed on the user's electronic device. In implementations where machine learning is performed on a server, for example, information enabling these inclusions and / or exclusions can be included in the photo identification information.

[0091] Additionally, algorithms 200, 300, 400 generally relate to selecting an image for a user's profile. In many implementations, other media can be selected instead of or in addition to an image. This media can be, for example, video in any video format (e.g., MP4, AVI, WMV, MOV, etc.), Graphics Interchange Format (GIF) format, and / or still and / or animated files in augmented reality (AR) or virtual reality (VR) formats. In another implementation of the present disclosure, FIG. 5 illustrates an algorithm 500 for adding interests to a user's profile.

[0092] Adding interests to a user's profile can be a tedious part of the onboarding process. Rather than completing the onboarding process, some implementations of algorithm 500 allow users to primarily browse profiles and add interests to their profile as they express preferences for other users.

[0093] The algorithm 500 starts at S505 and proceeds to S510.

[0094] In S510, the server displays the subject's profile to the searcher. For example, the server transmits the subject's profile to the searcher's electronic device. This profile may look like the profile illustrated in FIG. 1H. The algorithm 500 then proceeds to S515.

[0095] At S515, the server receives an action on the target's profile from the searcher's electronic device. The action may be, for example, a "like." The algorithm 500 then proceeds to S520.

[0096] At S520, the server determines potential shared interests with the searcher based at least in part on the interests listed in the subject's profile, as will be described in more detail below with respect to Figure 6. The algorithm 500 then proceeds to S525.

[0097] At S525, the server determines existing interests from the searcher's profile. The algorithm 500 then proceeds to S530.

[0098] In S530, the server determines whether the interest candidate is likely to be a further interest of the searcher. For example, the server may determine that the interest candidate is not a further interest because the searcher's interests already include the interest candidate.

[0099] In some implementations, a searcher's interests may include interests that suggest the searcher is unlikely to share this potential interest, at least relative to the subject's other interests. For example, if a searcher is interested in a soccer team, the searcher is unlikely to share potential interests about different soccer teams in the same league.

[0100] In many implementations, if the candidate interest is not a further interest, the server can select another interest of the subject as the candidate interest and repeat S530. For example, if the server determines that the searcher has touched the second element portion 150, the server can select a different interest in the second element portion 150 as the candidate interest.

[0101] If the server determines that the interest candidate is not a further interest of the searcher (or, in some implementations, the interest candidate is unlikely to be a further interest of the searcher), the algorithm 500 proceeds to S550.

[0102] If the server determines that the potential interest is likely to be a further interest of the searcher, the algorithm 500 proceeds to S535.

[0103] In S535, the server prompts the searcher to confirm further interests. The server can, for example, send data indicating the further interests to the searcher's electronic device, and the electronic device can display a prompt based on the further interests. The electronic device can receive a confirmation or denial of the further interests from the searcher. The electronic device can optionally send an indication of the confirmation or denial to the server.

[0104] At S540, the server determines whether the searcher has confirmed the addition of the additional interest as an interest (e.g., accepted the prompt). This determination may be based, for example, on receiving an explicit confirmation or rejection of the additional interest. If the server determines that the searcher has accepted the addition of the additional interest, the algorithm 500 proceeds to S545.

[0105] At S545, the server adds additional interests to the searcher's profile. The algorithm 500 then proceeds to S550.

[0106] Returning to S540, if the server determines that the searcher has not accepted the addition of further interests, the algorithm 500 proceeds to S550. In this way, the server can respect the will of the searcher when selecting their interests.

[0107] At S550, the algorithm 500 ends.

[0108] 6 illustrates an algorithm 600 for determining potential shared interests with a searcher based on the interests of the subject, according to one implementation of the present disclosure. In many implementations, this determination is based on the searcher liking the subject or portions of the subject's profile.

[0109] When a searcher selects a portion of a subject's profile (e.g., by selecting the first element portion 140, or more specifically, by selecting the + icon in the first element portion 140), there is a high degree of certainty that the searcher intends to designate the interests in the first element portion 140 as common interests. In this manner, the server can determine potential interests based on such searcher selections.

[0110] In some implementations, the server can infer the searcher's interests listed in the displayed profile portion. The searcher may spend a long time looking at, for example, travel photos (e.g., by not continuing to scroll through the second portion 130 along the profile 100), and the server can infer that this additional time represents the searcher's interest in the travel or the locations where the photos were taken. Interest in locations can be identified, for example, using geolocation tags, hashtags, or image recognition. In this way, the server can infer that the searcher is interested in the displayed portion even if they do not tap on it.

[0111] The server may further infer that the searcher is not negative about the interests listed in the earlier off-screen portion of the subject's profile because they continue to view the subject's profile. Therefore, the interests listed in the earlier off-screen portion of the profile may be potential common interests. Suggesting such interests may be particularly valuable when the searcher's profile contains few interests (e.g., the searcher is a new user of the service) and / or when other options for potential common interests are few (e.g., few interests are displayed, or those displayed are either existing common interests or unlikely common interests).

[0112] To achieve these advantages, algorithm 600 begins at S610 and proceeds to S620.

[0113] In S620, the server determines a previous off-screen portion of the subject's profile. In the example of FIG. 1H, page 1 110 is an example of a previous off-screen portion because page 2 130 is currently displayed on the electronic device. Additionally or alternatively, the server determines a portion of the subject's profile currently displayed to the searcher on the electronic device. This portion may be, for example, a portion of the profile most recently sent to the electronic device. Thus, second element portion 150 of page 2 130 in FIG. 1H is an example of an on-screen portion of the subject's profile. Additionally or alternatively, the server determines a selected portion of the subject's profile. This selected portion may be a portion of the profile displayed on the electronic device and selected by the searcher. First element portion 140 of page 2 130 in FIG. 1H is an example of a selected portion of the subject's profile. The algorithm 600 then proceeds to S630.

[0114] In optional S630, the server determines off-screen portions of the subject's profile. Page 3 160 in FIG. 1 is an example of an off-screen portion of the subject's profile. The server may, for example, determine portions of the profile that have not yet been requested by or sent to the electronic device. The algorithm 600 then proceeds to S640.

[0115] In S640, the server determines the searcher's potential interests based on interests described in the previous off-screen, on-screen, and / or selected portions of the subject's profile. That is, in many implementations, the server does not determine the searcher's potential interests based on interests described only in the off-screen, hidden portion of the profile, because that portion may not have influenced the searcher.

[0116] In some implementations, the server can determine potential common interests by performing image recognition on images in previous off-screen, on-screen, or selected portions of the subject's profile.

[0117] The algorithm 600 proceeds to S650 and ends.

[0118] In another implementation of the present disclosure, Figure 7A illustrates a first portion of an algorithm 700 for determining which subject interests should be highlighted in a profile to a searcher. Such an algorithm may be implemented using machine learning to tailor the display of a subject's profile based on the searcher's interests or preferences. That is, the algorithm may determine aspects of a subject that a searcher is likely to "like."

[0119] In many implementations of algorithm 700, the server has received a profile of the searcher, which profile specifies the searcher's interests, and the server has further determined which targets to suggest to the searcher based on any criteria (e.g., whether the targets meet the searcher's preferences, whether the targets have paid to promote their profile, etc.).

[0120] Matching services can typically divide their population into cohorts based on interests, "liking" similar people, being "liked" by similar people, etc. Each cohort a user belongs to can inform aspects of the people the user may "like."

[0121] For example, a searcher may be interested in running. Another user who is interested in running may be interested in beer. Therefore, the searcher may be interested in beer. The server can then highlight the subject's interest in beer to the searcher.

[0122] Additionally, additional information can be gleaned by considering the interests of people liked by other members of the cohort. For example, a runner might "like" a user who is interested in swimming. The server can then highlight the subject's interest in swimming to the searcher.

[0123] This chaining can continue, for example, by the server considering what other swimmers might be interested in. However, the value of the information diminishes at some point, especially as it consumes more resources (e.g., processing time, memory, etc.). Therefore, some implementations limit the amount of chaining that is performed, but not necessarily at the points listed above.

[0124] The algorithm 700 starts at S705 and proceeds to S710.

[0125] At S710, the server determines one or more interests of the searcher and one or more interests of the target person. The algorithm 700 then proceeds to S715.

[0126] At S715, the server determines other users (e.g., "interest-sharing buddies") who share one or more interests with the searcher. This determination may be based, for example, on the interests of the searcher and the interests of each of the other users. The server then determines other interests of the interest-sharing buddies. The algorithm 700 then proceeds to S720.

[0127] At S720, the server determines other users that the searcher's interest-sharing buddies have "liked" (e.g., "favorited"). The server may, for example, determine whether positive feedback on the favorite's profile has been received from the searcher's interest-sharing buddies. The server then determines the favorite's interests. The algorithm 700 then proceeds to S725.

[0128] In S725, the server determines whether the searcher has received positive feedback (e.g., at least one "like") from the other subject (e.g., whether the other subject is a favorite of the searcher). If the server determines that the searcher has received positive feedback from the other subject, the algorithm 700 proceeds to other page connector A, which will be described with reference to FIG. 7B.

[0129] If the server determines that no positive feedback has been received from the searcher for another subject, the algorithm 700 proceeds to S730.

[0130] At S730, the server determines common interests between the searcher and the subject based at least in part on the interests of the searcher, the interests of the subject, the interests of the searcher's interest-sharing buddies, and the favorite interests of the searcher's interest-sharing buddies. The algorithm 700 then proceeds to S735.

[0131] At S735, the server highlights to the searcher one, some, or all of the determined interests listed in the subject's profile. The server may, for example, send data to the searcher's electronic device to display text identifying these interests in bold or enlarged type, or with a colored border. In some implementations, the server may send data to the searcher's electronic device to display these determined interests (possibly exclusively) and hide other interests. In this manner, the server may highlight the interests of the searcher, the subject, people who share the searcher's interests, and people who are liked by people who share the searcher's interests. Algorithm 700 then proceeds to S780 and ends.

[0132] FIG. 7B illustrates a second portion of an algorithm 700 for determining target interests to highlight to a searcher when considering the searcher's "likes," according to one implementation of the present disclosure.

[0133] Figure 7B begins at the other page connector A in Figure 7A. The algorithm 700 then proceeds to S745.

[0134] At S745, the server determines one or more users who are favorites of the searcher based on positive feedback (e.g., one or more "likes") received by the server from the searcher on one or more user profiles. The server then determines the interests of the searcher's favorite(s). In this way, the server can later determine whether to highlight to the searcher particular interests of the subject because the searcher likes people who share those interests. Algorithm 700 then proceeds to S750.

[0135] At S750, the server determines users who "liked" the searcher's favorite profile ("likers"). The server can determine, for example, whether the likers have received positive feedback on the searcher's favorite profile. The server also determines the likers' interests.

[0136] That is, the server determines that the searcher is a member of a cohort of people that includes a particular favorite. The server can then take into account the interests of people who have favorites. Thus, the server can later decide to highlight that particular interest to the searcher because the searcher is interested in that favorite and is the type of person who is likely to have that subject's particular interest. Algorithm 700 then proceeds to S755.

[0137] At S755, the server determines the searcher's interest-sharing buddies based on common interests between the interest-sharing buddies and the searcher's favorites. That is, the server can determine that the searcher is a favorite member of a cohort of subjects who have a particular interest. The server also determines the interests of these interest-sharing buddies. In this way, the server can later decide to highlight the subject's particular interest to the searcher because the searcher "likes" the type of users who share that interest. Algorithm 700 then proceeds to S760.

[0138] At S760, the server determines who liked the searcher's favorite interest-sharing buddies. In many implementations, the server does not necessarily determine the interests of the liked buddies, since the likelihood that the searcher is interested in them is small. For example, simply because a person likes someone who shares the searcher's favorite common interests, the searcher is unlikely to share those interests. Algorithm 700 then proceeds to S765.

[0139] At S765, the server determines the likes of people who liked the searcher's favorite interest-sharing buddies. In addition, the server may determine these favorite interests. In this way, the server can later decide to highlight a particular interest to the searcher because people who share a common interest with people who the searcher "liked" are "liked" by people who also "like" other people who share the subject's particular interest. The algorithm 700 then proceeds to S770.

[0140] At S770, the server determines potential common interests between the searcher and the subject based on previously determined interests (e.g., the subject's interests, the searcher's interests, the interests of the searcher's interest-sharing buddies, the favorite interests of the searcher's interest-sharing buddies, the searcher's favorite interests, the interests of the searcher's favorite interest-sharing buddies, and the favorite interests of people who have liked the searcher's favorite interest-sharing buddies). In some implementations, the potential common interests may additionally or alternatively be based on the interests of people who have liked the searcher's favorites. The algorithm 700 then proceeds to S775.

[0141] In S775, the server highlights to the searcher the potential common interests listed in the target person's profile using bold typeface or a bold border, as described above.

[0142] The algorithm 700 then proceeds to S780 and ends.

[0143] FIG. 8 illustrates an algorithm 800 for dynamically ordering content according to one implementation of the present disclosure. The algorithm 800 starts at S810 and proceeds to S820. In S820, the server determines the identity of the searcher. When the searcher opens an online matching application program on their electronic device, the application program sends, for example, an identifier of the searcher's identity to the server. This identifier may be or may include a user ID, login, and / or biometric information of the searcher (e.g., a photo taken by a camera or a voice recording). In some implementations, this identifier may be provided by a third-party authentication (e.g., Google or Facebook). The server may receive this identifier via the server's network interface. The algorithm 800 then proceeds to S830.

[0144] At S830, the server determines one or more cohorts for the searcher. The server may determine the cohort based on relatively static identifying information, such as gender identification or sexual preference, provided by the searcher at the time of registration. Other examples of relatively static identifiers may be or include the country from which the searcher is accessing the service or a nationality previously provided by the searcher, since some cohorts are culture-based. The server may determine the cohort based on other information provided by the searcher, such as interests.

[0145] Additionally, the server may determine the cohort based on dynamic identifiers, such as the interests of the searcher. The server may also determine the cohort based on meta-identifiers, such as objects recognized in photos uploaded by the searcher.

[0146] The algorithm 800 then proceeds to S840.

[0147] In S840, the server may determine the target audience to display to the searcher. The server may determine the target audience in any manner. For example, the server may determine the target audience based at least in part on the searcher's tolerance or preferences. The server may determine the target audience based at least in part on the target audience's tolerance or preferences. The server may determine the target audience based at least in part on the target audience's willingness to pay a fee to increase their visibility. The server may determine the target audience based on the searcher's account lifetime and / or the target audience's account lifetime (e.g., less than one week). The server may determine the target audience based at least in part on the searcher's interests and / or the target audience's interests. Other implementations are also possible.

[0148] The algorithm 800 then proceeds to optional S850.

[0149] In S850, the server optionally determines matching characteristics of the searcher and the subject. The server may receive preferences, such as relationship goals, from the searcher and the subject, for example. The server may determine whether the preferences are the same (e.g., both the searcher and the subject have a preference of "long-term") or overlap (e.g., the searcher has a preference of "long-term partner" and the subject has a preference of "long-term preferred, short-term acceptable"). In some implementations, the server determines that the characteristics match if both preferences are the same. In other implementations, the server may determine that the characteristics match if the preferences overlap.

[0150] The algorithm 800 then proceeds to S860.

[0151] In S860, the server determines elements of the first page of the subject's profile based at least in part on the searcher's cohort. If the searcher's cohort is identified as female, the server may determine, for example, that the elements include the searcher's biography. If the searcher's cohort is identified as male, the server may determine that the elements include the searcher's geographic distance from the subject.

[0152] In various implementations, this element can be or include a predetermined number of lines of biographical information for the subject. In at least one such implementation, the server can determine the predetermined number of lines based at least in part on the cohort of searchers. If the cohort of searchers is identified as female, the predetermined number of lines can be greater than, for example, if the cohort of searchers is identified as male.

[0153] In many implementations in which the server determines the matching characteristics in S850, the elements of the first page of the subject's profile are determined based at least in part on the matching characteristics.

[0154] The algorithm 800 then proceeds to S870.

[0155] At S870, the server causes the searcher's electronic device to display the first page of the target person's profile.

[0156] The algorithm 800 then proceeds to S880 where the algorithm 800 ends.

[0157] The searcher can then interact with the target's profile. The searcher can, for example, navigate (e.g., scroll or flip) to additional pages of the target's profile. In this way, the searcher can view additional information in the target's profile. For example, for Jane, a later page (e.g., page 2) of Bretman's profile may include Bretman's biography. Similarly, for Liz, a later page (e.g., page 2) of Bretman's profile may include Bretman's relationship goals. Additionally, the searcher can "like" or "not interested" the target's profile, thereby moving on to the next target.

[0158] In this way, some implementations of the present disclosure may allow searchers to make quicker decisions about a target's profile and "like" more of the target's profile. For example, users identified as male are more likely to favorably engage with a profile if the target's distance is displayed first. Additionally, users identified as female are more likely to favorably engage with a profile if the target's biography is displayed first. Furthermore, users identified as female prefer to see the number of lines of the target's biography displayed first.

[0159] In this way, implementations allow members of online communities to surface relevant content to searchers first. Additionally, some implementations can resolve content conflicts, thereby avoiding overcrowding caused by failing to prioritize elements on the first page of a subject's profile.

[0160] Additionally, in some implementations of algorithm 900, the server may determine the elements of the first page of the subject's profile based at least in part on comparing the value to a predetermined threshold.

[0161] The server can determine, for example, the geographic distance from the searcher's location to the target's location. In doing so, the server can use any location information to determine the target's and / or searcher's location. In some implementations, the location is based on GPS location information received by the target's and / or searcher's electronic device. In other implementations, the location is based on the electronic device's location via triangulation. In some implementations, the location is based on a network location, such as network registration information or the known location of a nearby Wi-Fi router. In certain implementations, the location is based on the target's and / or searcher's self-reported location, such as a physical address. In some implementations, a location is temporarily specified by the user, such as by using Tinder Passport®.

[0162] The server may calculate the distance between locations in any manner. For example, the server may calculate the distance using a straight line. The server may calculate the distance based on a particular mode of transportation, such as road or rail.

[0163] The predetermined threshold can be a predetermined value (e.g., 15 miles), a set of values ​​set by the searcher (e.g., as preferences), or a dynamically calculated value. The server can determine the predetermined threshold based on average values ​​for a cohort (e.g., users identified as male) or subcohort (e.g., users identified as male in a particular country or region).

[0164] In some implementations, the server can calculate travel time based on geographic distance and mode of transportation. Thus, in some implementations, the server can compare the travel time to a predetermined threshold. If the travel time is less than a predetermined period (e.g., 20 minutes), the server can determine that the elements on the first page of the profile are or include travel distance and / or travel time.

[0165] In another implementation of the present disclosure, Figure 9 illustrates a computing device 900. The computing device 900 may implement a user device or a server of the present disclosure.

[0166] The computing device 900 includes a network interface 910 , a user input interface 920 , a memory 930 , a program 935 , a processor 940 , a user output interface 950 , and a bus 955 .

[0167] The network interface 910 facilitates communication between the computing device 900 and other devices over a network.

[0168] The user input interface 920 receives one or more inputs from a human user.

[0169] The user output interface 950 provides one or more outputs to a human user. In many implementations, the user input interface 920 and the user output interface 950 can be included in the same structure, such as a touchscreen.

[0170] Bus 955 facilitates communication between elements of computing device 900 .

[0171] In certain example implementations, the matching operations outlined herein, such as those executed by a server and / or provided as an application program for an endpoint operated by an end user (e.g., a mobile application program for an iPhone or Android device), may be implemented by logic encoded in one or more non-transitory tangible media (e.g., embedded logic provided in an application specific integrated circuit (“ASIC”), digital signal processor (“DSP”) instructions, software executed by a processor (potentially including object code and source code), or other similar machine). In some of these cases, memory 930 may store data used for the operations described herein. This includes memory 930, which may store software, logic, code, or processor instructions (e.g., program 935) executed to perform the activities described herein.

[0172] The processor 940 may execute any type of instruction associated with that data to accomplish the operations detailed herein. The activities outlined herein may be implemented using fixed or programmable logic (e.g., software / computer instructions executed by a processor), and elements identified herein may be a programmable processor, programmable digital logic (e.g., a field programmable gate array (“FPGA”), erasable programmable read-only memory (“EPROM”), electrically erasable programmable ROM (“EEPROM”)), or an ASIC containing digital logic, software, code, electronic instructions, or any suitable combination thereof.

[0173] The devices illustrated herein may maintain information in any suitable memory (such as random access memory ("RAM"), ROM, EPROM, EEPROM, ASIC), software, hardware, or any other suitable component, device, element, or object, as applicable. Any of the memory types described herein should be construed as being encompassed within the broad term "memory." Similarly, any of the processing elements, modules, and potential machines described herein should be construed as being encompassed within the broad term "processor." Each network element may also include suitable interfaces for receiving, transmitting, and / or otherwise communicating data or information in a network environment.

[0174] In the described examples, interactions may be described with respect to two or more network elements. However, this is for purposes of clarity and illustration only. In some cases, it may be easier to describe one or more of the functions of a given set of flows by referencing only a limited number of network elements. Servers and electronic devices are readily scalable to accommodate more complex / advanced arrangements and configurations as well as larger numbers of components. Thus, the described examples should not limit the scope or preclude the broad teachings of servers and electronic devices, which may be applicable to myriad other architectures.

[0175] The operations in the foregoing flow diagrams represent only some of the situations and patterns that may be performed by or within the system. Portions of these operations may be deleted or eliminated, as desired, or these operations may be significantly modified or changed without departing from the scope of the present disclosure. The timing of these operations may also be significantly changed. The foregoing operational flows are provided for purposes of example and explanation. The present system is quite versatile in that any suitable arrangement, timeline, configuration, and timing mechanism may be implemented without departing from the teachings of the present disclosure. While the present disclosure has been described in detail with reference to particular arrangements and configurations, these exemplary configurations and arrangements may be significantly modified without departing from the scope of the present disclosure.

[0176] Those skilled in the art may recognize many other variations, substitutions, variations, alterations, and modifications, and the present disclosure is intended to encompass all such variations, substitutions, variations, alterations, and modifications as fall within the scope of the present disclosure. [Example]

[0177] In example AM1, a method includes receiving a registration request from a first user including a tolerance range for the first user; receiving an action on a profile of a second user from the first user; determining attributes of an appealing image based at least in part on a user population; sending photo identification information including the attributes of the appealing image to the first user; receiving a plurality of images from the first user; and adding the plurality of images to the profile of the first user.

[0178] Example AM2 is the method of example AM1, further comprising narrowing the user population, wherein the attributes of the appealing image are based at least in part on the population.

[0179] Example AM3 is the method of example AM2, in which narrowing the universe includes determining the first user's favorite candidates based at least in part on the second user and the first user's tolerance ranges.

[0180] Example AM4 is the method of example AM3, in which narrowing the universe includes narrowing the first user's potential favorites based at least in part on the first user's preferences.

[0181] Example AM5 is a method according to any of Examples AM2 to AM4, further comprising receiving an action on the first user's profile from a third user, the first user's profile including an image, and the appeal image including the image.

[0182] Example AM6 is the method of example AM5, in which narrowing the universe includes determining potential romantic partners based at least in part on a potential romantic partner tolerance range of the third user and the first user.

[0183] Example AM7 is the method of example AM6, in which narrowing the population includes narrowing the potential romantic partners based on preferences of the potential romantic partners.

[0184] Example AM8 is the method of any of examples AM1 to AM7, wherein the photo identification information includes biometric identification information of the first user.

[0185] Example AM9 is a method as described in example AM8, further including generating biometric identification information of the first user based at least in part on verification video of the first user, wherein the enrollment from the first user includes the verification video.

[0186] In example AA1, an apparatus includes a network interface that receives a registration request from a first user, sends a profile of a second user to the first user, and receives actions on the profile of the second user from the first user; and a processor configured to determine attributes of an appealing image based at least in part on a user population, wherein the network interface sends photo identification information including the attributes of the appealing image to the first user and receives a plurality of images from the first user, and the processor is further configured to add the plurality of images to the profile of the first user.

[0187] Example AA2 is the apparatus of example AA1, wherein the processor is further configured to perform a targeting of a user population, and the attributes of the appealing image are based at least in part on the population.

[0188] Example AA3 is the device described in example AA2, wherein the narrowing down includes determining the first user's favorite candidates based at least in part on the second user and the first user's tolerance levels, and the registration request further includes the first user's tolerance levels.

[0189] Example AA4 is the apparatus of example AA3, in which the narrowing includes narrowing the first user's potential favorites based at least in part on preferences of the first user.

[0190] Example AA5 is the device described in example AA2, wherein the network interface receives tolerances for registering potential romantic partners for the first user, receives actions on the first user's profile from a third user, the first user's profile includes an image, the narrowing down includes determining potential romantic partners for the first user based at least in part on the tolerances of the third user and the potential romantic partners, and the appeal image includes the image.

[0191] Example AA6 is the device according to example AA5, in which the narrowing down of the lover candidates includes narrowing down the lover candidates based on the preferences of the lover candidates, and the registration of the lover candidates includes the preferences.

[0192] Example AA7 is the device of any of Examples AA1 to AA6, wherein the processor is further configured to generate biometric identification information of the first user based at least in part on a verification video of the first user, wherein the enrollment request from the first user includes the verification video, and wherein the photo identification information further includes the biometric identification information of the first user.

[0193] In example AC1, a computer-readable medium is encoded with executable instructions that, when executed by a processing unit, perform operations including receiving a registration request from a first user, sending a profile of a second user to the first user, receiving an action from the first user on the profile of the second user, determining attributes of an appealing image based at least in part on a user population, sending photo identification information to the first user that includes the attributes of the appealing image, receiving a plurality of images from the first user, and adding the plurality of images to the profile of the first user.

[0194] Example AC2 is the medium of example AC1, wherein the operations further include narrowing a population of users, and the attributes of the appealing image are based at least in part on the population.

[0195] Example AC3 is the medium described in example AC2, wherein narrowing the population includes determining favorite candidates for the first user based at least in part on tolerances of the second user and the first user, and the registration request further includes tolerances of the first user.

[0196] Example AC4 is the medium of example AC3, in which narrowing the universe includes narrowing the first user's favorite candidates based at least in part on preferences of the first user.

[0197] Example AC5 is the medium described in Example AC2, wherein the operations include receiving an action on the first user's profile from a third user, wherein the first user's profile includes an image and the appeal image includes the image, and receiving a tolerance range in registering potential romantic partners for the first user, and narrowing the population further includes determining the potential romantic partners for the first user based at least in part on the tolerance range of the third user and the potential romantic partners.

[0198] Example AC6 is the medium of example AC5, in which narrowing down the population includes narrowing down the lover candidates based on preferences of the lover candidates, and registering the lover candidates includes the preferences.

[0199] Example AC7 is the medium described in any of Examples AC1 to AC6, wherein the operations further include generating biometric identification information for the first user based at least in part on verification footage of the first user, wherein the enrollment request from the first user includes the verification footage, and wherein the photo identification information includes biometric identification information for the first user.

[0200] In example BM1, a method is implemented by an electronic device, the method including: sending a registration request for a first user, receiving photo identification information including appeal image information, identifying a set of preliminary images stored on the electronic device based at least in part on the appeal image information, and displaying the set of preliminary images.

[0201] Example BM2 is the method of example BM1, in which the photo identification includes biometric identification, and the preliminary set of images is identified based at least in part on the biometric identification.

[0202] Example BM3 is the method of example BM1 or BM2, wherein the enrollment request includes a verification video including a face of the first user, and the biometric information is based at least in part on the face of the first user.

[0203] Example BM4 is a method of any of Examples BM1 to BM3, further including displaying a profile of a second user, receiving an input indicating a preference for the profile of the second user, and transmitting an indication in the input, wherein the photo identification information is based at least in part on the preference.

[0204] Example BM5 is the method of any of examples BM1-BM4, in which the preliminary set of images is identified based at least in part on containing a human face.

[0205] Example BM6 is the method of any of examples BM1-BM5, further comprising receiving an input for approving the subset of preliminary images.

[0206] Example BM7 is the method of example BM6, further comprising transmitting a subset of the preliminary images.

[0207] In example BC1, a computer-readable medium is encoded with executable instructions that, when executed by a processing unit, perform operations including: sending a registration request for a first user via a network interface, receiving photo identification information including appeal image information via the network interface, identifying a set of preliminary images stored on the electronic device based at least in part on the appeal image information, and displaying the set of preliminary images via a display.

[0208] Example BC2 is the medium of example BC1, wherein the photographic identification information includes biometric identification information, and the preliminary image set is identified based at least in part on the biometric identification information.

[0209] Example BC3 is the medium of example BC1 or BC2, wherein the enrollment request includes a verification video including a face of the first user, and the biometric information is based at least in part on the face of the first user.

[0210] Example BC4 is a medium described in any of Examples BC1 to BC3, wherein the operations further include displaying a profile of the second user via the display, receiving input indicating preferences for the second user's profile, and transmitting an indication in the input via the network interface, wherein the photo identification information is based at least in part on the preferences.

[0211] Example BC5 is the medium of any of examples BC1-BC4, in which the preliminary set of images is identified based at least in part on including a human face.

[0212] Example BC6 is a medium described in any of Examples BC1 to BC5, wherein the operations further include receiving an input for approving a subset of the preliminary image group and transmitting the subset of the preliminary image group via a network interface.

[0213] In embodiment BA1, an electronic device includes a network interface for transmitting a registration request for a first user and receiving photo identification information including appeal image information, a memory for storing a plurality of images, a processor configured to identify a group of preliminary images based at least in part on the appeal image information, and a display for displaying the group of preliminary images.

[0214] Example BA2 is the electronic device of example BA1, wherein the photo identification includes biometric identification, and the preliminary image set is identified based at least in part on the biometric identification.

[0215] Example BA3 is the electronic device of example BA1 or BA2, wherein the enrollment request includes a verification video including a face of the first user, and the biometric information is based at least in part on the face of the first user.

[0216] Example BA4 is an electronic device described in any of Examples BA1 to BA3, further comprising a user interface that receives input indicating preferences for a profile of a second user, the display displays the profile of the second user, the network interface transmits an indication in the input, and the photo identification information is based at least in part on the preferences.

[0217] Example BA5 is the electronic device of any of examples BA1-BA4, in which the preliminary images are identified based at least in part on including a human face.

[0218] Example BA6 is the electronic device of any of Examples BA1 to BA5, further comprising a user interface for receiving input for approving the subset of preliminary images.

[0219] Example BA7 is the electronic device of example BA6, in which the network interface transmits a subset of the preliminary images.

[0220] In example CM1, a method includes displaying a profile of a subject to a searcher, receiving input from the searcher, determining potential interests for the searcher, determining existing interests of the searcher, determining that the potential interests are further interests of the searcher, and adding the potential interests of the searcher to the searcher's profile.

[0221] Example CM2 is the method of example CM1, further including prompting the searcher to identify additional interests.

[0222] Example CM3 is the method of example CM1 or CM2, wherein determining the searcher's potential interests includes determining an in-screen portion of the subject's profile and determining a selection portion of the subject's profile.

[0223] Example CM4 is the method of any of examples CM1-CM3, wherein determining the searcher's potential interests includes determining a previous off-screen portion of the subject's profile.

[0224] Example CM5 is the method of any of examples CM1 to CM4, wherein determining the searcher's potential interests includes performing image recognition on images displayed in the on-screen portion of the subject's profile.

[0225] Example CM6 is the method of any of examples CM1-CM5, wherein determining the searcher's potential interests includes determining off-screen portions of the subject's profile.

[0226] Example CM7 is the method of any of Examples CM1 to CM6, further including determining existing interests listed in the searcher's profile and determining that the potential interests are further interests of the searcher based on the searcher's interests, and wherein the adding is performed based at least in part on determining that the potential interests are further interests of the searcher.

[0227] Example C8 is the method of example CM4, in which the suggested interests are based at least in part on previous off-screen portions of the subject's profile.

[0228] In example CC1, a computer-readable medium is encoded with executable instructions that, when executed by a processing unit, perform operations including displaying a subject's profile to a searcher, determining potential interests for the searcher based at least in part on the subject's profile, and adding the potential interests for the searcher to the searcher's profile.

[0229] Example CC2 is the medium of example CC1, wherein the actions further include prompting the searcher to identify additional interests.

[0230] Example CC3 is the media described in example CC1 or CC2, wherein the operations further include receiving input from the searcher regarding an in-screen portion of the subject's profile, and determining the searcher's potential interests includes determining the in-screen portion of the subject's profile based at least in part on the input, and determining a selected portion of the subject's profile based on the input, and the potential interests are based at least in part on the selected portion of the subject's profile.

[0231] Example CC4 is the medium described in any of Examples CC1 to CC3, wherein determining the searcher's potential interests includes determining a previous off-screen portion of the subject's profile, and the potential interests are based at least in part on the previous off-screen portion of the subject's profile.

[0232] Example CC5 is the media described in any of Examples CC3 to CC4, wherein determining the searcher's potential interests includes performing image recognition on images displayed in a selected portion of the subject's profile based at least in part on the input, and the potential interests are based at least in part on the image recognition.

[0233] Example CC6 is the medium of any of examples CC1-CC5, in which determining the searcher's potential interests includes determining off-screen portions of the subject's profile.

[0234] Example CC7 is the medium described in any of examples CC1 to CC6, wherein the operations further include determining existing interests listed in the searcher's profile and determining that the interest candidates are further interests of the searcher based on the searcher's interests, and wherein the adding includes being performed based at least in part on determining that the interest candidates are further interests of the searcher.

[0235] In example CA1, an apparatus includes a memory that stores instructions and at least one processor, the at least one processor being configured to execute the instructions to cause the apparatus to display at least a subject profile to a searcher, determine potential interests for the searcher based at least in part on the subject profile, and add the potential interests for the searcher to the searcher's profile.

[0236] Example CA2 is the device of example CA1, wherein the at least one processor is further configured to execute instructions to cause the device to prompt the searcher to at least confirm further interests.

[0237] Example CA3 is the device described in example CA1 or CA2, wherein at least one processor executes instructions to cause the device to receive input from the searcher regarding at least an in-screen portion of the subject's profile, and further configured such that determining the searcher's potential interests includes determining the in-screen portion of the subject's profile based at least in part on the input, and determining a selected portion of the subject's profile.

[0238] Example CA4 is the device of any of examples CA1 to CA3, wherein determining the searcher's potential interests includes determining a previous off-screen portion of the subject's profile, and the potential interests are based at least in part on the previous off-screen portion of the subject's profile.

[0239] Example CA5 is the device described in example CA3 or CA4, wherein determining the searcher's potential interests includes performing image recognition based on the input on images displayed in the selected portion of the subject's profile, and the potential interests are based at least in part on the image recognition.

[0240] Example CA6 is the apparatus of any of examples CA1-CA5, wherein determining the searcher's potential interests includes determining off-screen portions of the subject's profile.

[0241] Example CA7 is the device of any of Examples CA1 to CA6, wherein at least one processor is configured to execute instructions to cause the device to at least determine existing interests listed in the searcher's profile, and determine that the potential interests are further interests of the searcher based at least in part on the searcher's existing interests, and wherein adding the potential interests is performed based at least in part on the searcher's further interests.

[0242] In embodiment DM1, a method includes receiving a profile of a searcher, the profile indicating the interests of the searcher; determining a target audience for the searcher; determining interests of the searcher and interests of the target audience; determining common interests based at least in part on the interests of the target audience; and displaying the target audience profile to the searcher, the display highlighting the common interests.

[0243] Example DM2 is a method according to example DM1, further comprising determining interest-sharing buddies of the searcher based at least in part on the interests of the searcher, and determining the interests of the interest-sharing buddies of the searcher, wherein the common interests are based at least in part on the interests of the interest-sharing buddies of the searcher.

[0244] Example DM3 is a method according to example DM1 or DM2, further comprising determining interest-sharing buddies of the searcher based at least in part on the interests of the searcher, determining favorites of the interest-sharing buddies of the searcher, and determining interests of the interest-sharing buddies of the searcher, wherein the common interests are based at least in part on the favorite interests of the interest-sharing buddies of the searcher.

[0245] Example DM4 is the method of any of Examples DM1 to DM3, further including determining that favorites have been received from the searcher, determining the searcher's favorites, and determining the searcher's favorite interests, wherein the common interests are based at least in part on the searcher's favorite interests.

[0246] Example DM5 is the method of example DM4, further comprising determining people who liked the searcher's favorites and determining interests of the people who liked the searcher's favorites, wherein the common interests are based at least in part on the interests of the people who liked the searcher's favorites.

[0247] Example DM6 is the method of example DM4 or DM5, further including determining favorite interest-sharing buddies of the searcher based at least in part on the favorite interests of the searcher, and determining interests of the favorite interest-sharing buddies of the searcher, wherein the common interests are based at least in part on the interests of the favorite interest-sharing buddies of the searcher.

[0248] Example DM7 is the method of example DM6, further comprising determining people who have liked the searcher's favorite interest-sharing buddies and determining interests of people who have liked the searcher's favorite interest-sharing buddies, wherein the common interests are based at least in part on the interests of people who have liked the favorite interest-sharing buddies.

[0249] Example DM8 is the method of example DM7, further comprising determining favorites of people who liked the searcher's favorite interest-sharing buddies and determining favorite interests of people who liked the searcher's favorite interest-sharing buddies, wherein the common interests are based at least in part on the interests of people who liked the searcher's favorite interest-sharing buddies.

[0250] In embodiment DA1, the device includes a network interface that receives a profile indicating the interests of a subject and a profile indicating the interests of a searcher, and a processor configured to determine to suggest the subject to the searcher, determine common interests based at least in part on the interests of the subject, and display the subject's profile to the searcher with the common interests highlighted.

[0251] Example DA2 is the device described in example DA1, wherein the processor is further configured to determine interest-sharing companions of the searcher based at least in part on the interests of the searcher and first interests of the interest-sharing companions, and to determine second interests of the interest-sharing companions of the searcher, wherein the common interests are based at least in part on the second interests of the interest-sharing companions of the searcher.

[0252] Example DA3 is the device described in example DA1 or DA2, wherein the processor is further configured to determine interest-sharing buddies of the searcher based at least in part on the interests of the searcher and the interests of the interest-sharing buddies, wherein the processor is further configured to determine whether favorable feedback has been received from the searcher's interest-sharing buddies for favorite profiles of the searcher's interest-sharing buddies, and wherein the processor is further configured to determine favorite interests of the searcher's interest-sharing buddies, wherein the common interests are based at least in part on the favorite interests of the searcher's interest-sharing buddies.

[0253] Example DA4 is the device of any of Examples DA1 to DA3, wherein the processor is further configured to determine that positive feedback has been received from the searcher for the searcher's favorite profile, and to determine the searcher's favorite interests, wherein the common interests are based at least in part on the searcher's favorite interests.

[0254] Example DA5 is the device described in DA4, wherein the processor is further configured to determine whether positive feedback has been received from people who have liked the profiles of the searcher's favorites, and the processor is further configured to determine interests of the people who have liked the searcher's favorites, and the common interests are based at least in part on the interests of the people who have liked the searcher's favorites.

[0255] Example DA6 is the device described in example DA4 or DA5, wherein the processor determines the searcher's favorite interest-sharing buddies based at least in part on the searcher's favorite interests and the interests of the searcher's favorite interest-sharing buddies, and the common interests are based at least in part on the interests of the searcher's favorite interest-sharing buddies.

[0256] Example DA7 is the device described in DA6, wherein the processor is further configured to determine that favorable feedback has been received on the profiles of the searcher's favorite interest sharing buddies from people who have liked the searcher's favorite interest sharing buddies, and the processor is further configured to determine that favorable feedback has been received on the favorite profiles of people who have liked the searcher's favorite interest sharing buddies from people who have liked the searcher's favorite interest sharing buddies, wherein the favorite profiles of people who have liked the searcher's favorite interest sharing buddies indicate interests, and the common interests are based at least in part on the favorite interests of people who have liked the searcher's favorite interest sharing buddies.

[0257] In example DC1, a computer-readable medium is encoded with executable instructions that, when executed by a processing unit, perform operations including receiving a profile indicating the interests of a searcher and a profile indicating the interests of a subject, determining to suggest the subject to the searcher, determining common interests based at least in part on the interests of the subject, and displaying the subject's profile to the searcher in a manner that highlights the common interests.

[0258] Example DC2 is the medium described in Example DC1, wherein the operations further include determining interest-sharing companions of the searcher based at least in part on the interests of the searcher and first interests of the interest-sharing companions, and determining second interests of the searcher's interest-sharing companions, wherein the common interests are based at least in part on the second interests of the searcher's interest-sharing companions.

[0259] Example DC3 is the medium described in example DC1 or DC2, wherein the operations further include determining the searcher's interest-sharing buddies based at least in part on the searcher's interests and the interests of the interest-sharing buddies, determining whether favorable feedback has been received from the searcher's interest-sharing buddies for the searcher's interest-sharing buddies' favorite profiles, and determining the interests of the searcher's interest-sharing buddies, wherein the common interests are based at least in part on the favorite interests of the searcher's interest-sharing buddies.

[0260] Example DC4 is the medium described in any of Examples DC1 to DC3, wherein the operations further include determining that positive feedback has been received from the searcher for the searcher's favorite profile and determining the searcher's favorite interests, wherein the common interests are based at least in part on the searcher's favorite interests.

[0261] Example DC5 is the medium described in Example DC4, wherein the operations further include determining whether positive feedback has been received for the searcher's favorite profile from the people who liked it, and determining the interests of the people who liked the searcher's favorite, and the common interests are based at least in part on the interests of the people who liked the searcher's favorite.

[0262] Example DC6 is the medium described in example DC4 or DC5, wherein the operations further include determining the searcher's favorite interest-sharing buddies based at least in part on the searcher's favorite interests and the interests of the searcher's favorite interest-sharing buddies, and the common interests are based at least in part on the interests of the searcher's favorite interest-sharing buddies.

[0263] Example DC7 is the medium described in Example DC6, wherein the operations further include determining that a profile of the searcher's favorite interest sharing companion has received positive feedback from people who have indicated a liking for the searcher's favorite interest sharing companion, and determining that a favorite profile of the person who has indicated a liking for the searcher's favorite interest sharing companion, which profile shows an interest, has received positive feedback from people who have indicated a liking for the searcher's favorite interest sharing companion, wherein the common interests are based at least in part on the favorite interests of the person who has indicated a liking for the searcher's favorite interest sharing companion.

[0264] In example EM1, a method includes determining a cohort of searchers in a matching community; determining targets for the searcher in the matching community, the targets' profiles including a plurality of elements; determining an element of the plurality of elements based at least in part on the cohort of searchers; and displaying the targets' profiles across a plurality of pages, the first page including the element.

[0265] Example EM2 is the method of example EM1, further including determining matching characteristics of the searcher and the subject, wherein the elements are determined based at least in part on the matching characteristics.

[0266] Example EM3 is the method of example EM2, in which the matching property is a relational goal.

[0267] Example EM4 is the method of any of examples EM1-EM3, further including transitioning the display from page 1 of the subject's profile to page 2 of the subject's profile.

[0268] Example EM5 is the method of any of Examples EM1, EM2, or EM4, wherein the searcher cohort is identified as female and the element includes a subject history.

[0269] Example EM6 is the method of any of Examples EM1, EM2, or EM4, wherein the cohort of searchers is identified as male and the factor comprises the geographic distance of the subjects.

[0270] Example EM7 is the method of example EM4 or EM5, wherein the element includes a predetermined number of lines of the subject's biography, the predetermined number of lines being determined based at least in part on a cohort of searchers.

[0271] In example EA1, an apparatus includes a memory that stores instructions and at least one processor, the at least one processor being configured to execute the instructions to cause the apparatus to determine a cohort of searchers in a matching community, determine targets for the searcher in the matching community that include a target profile that includes a plurality of elements, determine an element of the plurality of elements based at least in part on the cohort of searchers, and display the target profile across multiple pages that include the element on a first page.

[0272] Example EA2 is the device described in example EA1, wherein the at least one processor is further configured to execute instructions to cause the device to determine matching characteristics between the searcher and the subject, and the elements are determined based at least in part on the matching characteristics.

[0273] Example EA3 is the apparatus of example EA2, in which the matching property is a relational goal.

[0274] Example EA4 is the device described in any of examples EA1 to EA3, wherein the at least one processor is configured to execute instructions to cause the device to at least transition the display from page 1 of the subject's profile to page 2 of the subject's profile.

[0275] Example EA5 is the apparatus of any of Examples EA1, EA2, or EA4, wherein the cohort of searchers is identified as female and the element includes a biography of the subject.

[0276] Example EA6 is the apparatus of any of Examples EA1-EA3 or EA4, wherein the cohort of searchers is identified as male and the element includes the geographic distance of the subject.

[0277] Example EA7 is the apparatus of example EA4 or EA5, wherein the element includes a predetermined number of lines of the subject's biography, the predetermined number of lines being determined based at least in part on a cohort of searchers.

[0278] In example EC1, a computer-readable medium is encoded with executable instructions that, when executed by a processing unit, perform operations including determining a cohort of searchers in a matching community, determining targets for the searcher in the matching community that include target profiles that include a plurality of elements, determining an element of the plurality of elements based at least in part on the cohort of searchers, and displaying the target profiles across a plurality of pages with the element on a first page.

[0279] Example EC2 is the medium of example EC1, wherein the operations further include determining matching characteristics between the searcher and the subject, and the element is determined based at least in part on the matching characteristics.

[0280] Example EC3 is the medium of example EC2, wherein the matching property is a relationship goal.

[0281] Example EC4 is the medium of any of examples EC1-EC3, wherein the actions further include transitioning the display from page 1 of the subject's profile to page 2 of the subject's profile.

[0282] Example EC5 is the medium of any of Examples EM1, EM2, or EM4, wherein the searcher cohort is identified as female, and the element includes subject biographies.

[0283] Example EC6 is the media of any of Examples EM1, EM2, or EM4, wherein the cohort of searchers is identified as male and the element comprises the geographic distance of the subjects.

[0284] Example EC7 is the medium of Example EC4 or EC5, wherein the element includes a predetermined number of lines of the subject's biography, the predetermined number of lines being determined based at least in part on a cohort of searchers.

Claims

1. 1. A method implemented by an electronic device, comprising: Sending a registration request for a first user; receiving photo identification information including appeal image information; identifying a set of preliminary images stored on the electronic device based at least in part on the appeal image information; displaying the set of preliminary images; A method comprising:

2. The method of claim 1 , wherein the photo identification information includes biometric identification information, and the preliminary set of images is identified based at least in part on the biometric identification information.

3. The method of claim 1 , wherein the enrollment request includes a verification video including a face of the first user, and the biometric information is based at least in part on the face of the first user.

4. Displaying a profile of a second user; receiving input indicating preferences for the profile of the second user; sending a manifestation in said input; further comprising The method of claim 1 , wherein the photo identification information is based at least in part on the preferences.

5. The method of claim 1 , wherein the images are identified based at least in part on containing a human face.

6. The method of claim 1 , further comprising receiving an input for approving a subset of the preliminary image set.

7. The method of claim 6 further comprising transmitting the subset of the preliminary images.

8. A computer-readable medium encoded with executable instructions that, when executed by a processing unit, perform operations, the operations including: Sending a registration request for the first user via the network interface; receiving photo identification information including appeal image information via the network interface; identifying a set of preliminary images stored on the electronic device based at least in part on the appeal image information; displaying the preliminary images via a display; Including, media.

9. The medium of claim 8 , wherein the photo identification information includes biometric identification information, and the preliminary set of images is identified based at least in part on the biometric identification information.

10. The medium of claim 8 , wherein the enrollment request includes a verification video including a face of the first user, and the biometric information is based at least in part on the face of the first user.

11. The operation is displaying a profile of a second user via said display; receiving input indicating preferences for the profile of the second user; transmitting a manifestation of said input via said network interface; further comprising The media of claim 8 , wherein the photo identification information is based at least in part on the preferences.

12. The media of claim 8 , wherein the images are identified based at least in part on containing a human face.

13. The operation is receiving an input to approve a subset of the preliminary images; transmitting the subset of the preliminary images via the network interface; The medium of claim 8 further comprising:

14. a network interface for transmitting a registration request for a first user and receiving photo identification information including appeal image information; a memory for storing a plurality of images; a processor configured to identify a preliminary set of images for the image based at least in part on the appealing image information; a display for displaying the preliminary images; An electronic device comprising:

15. The electronic device of claim 14 , wherein the photo identification information includes biometric identification information, and the preliminary set of images is identified based at least in part on the biometric identification information.

16. The electronic device of claim 14 , wherein the enrollment request includes a verification video including a face of the first user, and the biometric information is based at least in part on the face of the first user.

17. a user interface for receiving input indicating a preference for the profile of the second user; the display displays the profile of the second user; the network interface sends a manifestation at the input; The electronic device of claim 14 , wherein the photo identification information is based at least in part on the preferences.

18. The electronic device of claim 14 , wherein the images are identified based at least in part on containing a human face.

19. The electronic device of claim 14 , further comprising a user interface for receiving input for approving the subset of preliminary images.

20. The electronic device of claim 19 , wherein the network interface transmits the subset of the preliminary images.

Images