Identifying resonance connections using machine learning

Abstract

The technical problem of identifying social consensus regarding premium services offered to a given member profile in an online connectivity network system is addressed by first capturing the intent of associated members based on their activity on websites provided by the online connectivity network system. The identified intent is used as input to a relevance machine learning model, which is executed to identify connections with members who are subscribers to premium services and have been identified as having the most compelling resonant connection regarding subscription to premium services.

Description

Technical Field

[0001] This application relates to the field of software and / or hardware technology, and in one example embodiment, it relates to a machine learning-based method for identifying resonant connections. Background Technology

[0002] An online networking system is a platform that connects people in virtual space. It can be a web-based platform, such as a networking website, and can be accessed by users via a web browser or through mobile applications available on mobile phones, tablets, etc. An online networking system can also be a business-centric networking system specifically designed for business communities, where registered members build and document networks of people they know and professionally trust. Each registered member can be represented by a member profile. A member profile can be represented by one or more web pages, or it can be a structured representation of member information in XML (Extensible Markup Language), JSON (JavaScript Object Notation), or a similar format. A member profile webpage on a networking website might highlight the work experience and professional skills of the associated member. Any two members can indicate their willingness to "connect" to each other within the context of an online networking system by viewing each other's profiles, recommending and endorsing each other's profiles, and otherwise contacting each other through the online networking system. Members connected within the context of an online networking system can be referred to as "connections" to each other, and their respective profiles are associated with corresponding connection links indicating that these two profiles are connected.

[0003] The online connection network system is also designed to allow job posters (e.g., companies) to post job openings, so that these openings (also simply called positions) can be presented to members, for example, as search results in response to searches submitted by members to the online connection network system or as recommendations that may appear in members' news feeds. Recommended positions are presented to members through a user interface (UI) that allows members to view job details and apply for positions electronically.

[0004] Providers of online connectivity systems can offer users free access to basic service functionality, but require a paid subscription for a premium service—a version that includes additional or enhanced features. Users can be presented with a message briefly describing the enhanced version of the service. Users can choose to purchase the offered premium subscription or decline and continue using the free version of the service. A current and ongoing challenge for online services is the effective promotion of premium subscriptions.

[0005] Social proof is the concept that consumers will adjust their behavior based on the behavior of others. It has been widely used in marketing because it is one of the most powerful tools. Of all types of social proof, user social proof involves sharing a user's success story with other users. For example, "your friend's wisdom" social proof is considered one of the most effective user social proof techniques, leveraging recommendations from people the user knows and trusts. Attached Figure Description

[0006] Embodiments of the invention are illustrated in the figures by way of example rather than limitation, wherein similar reference numerals denote similar elements, wherein:

[0007] Figure 1 is a graphical representation of a network environment in which an exemplary machine learning-based method for identifying resonant connections can be implemented.

[0008] Figure 2 This is a block diagram of the architecture of a machine learning-based method for identifying resonant connections according to an example embodiment;

[0009] Figure 3 This is a flowchart illustrating a machine learning-based method for identifying resonant connections according to an example embodiment;

[0010] Figure 4 It is a graphical representation of an example machine in the form of a computer system, in which a set of instructions can be executed to make the machine perform any or more of the methods discussed here;

[0011] Figure 5 It is a graphical representation of the example user interface (UI), which includes a description of the features offered by the premium subscription and also includes references to the UI elements selected for the most resonant connection to the object member profile. Detailed Implementation

[0012] Overview

[0013] A machine learning-based method for identifying resonated connections in online connected networks is described. In the following description, numerous specific details are set forth for purposes of explanation to provide a thorough understanding of embodiments of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without these specific details.

[0014] As used herein, the term "or" can be interpreted as inclusive or exclusive. Similarly, the term "exemplary" merely indicates an example or paradigm of something and is not necessarily the preferred or ideal way to achieve the objective. Furthermore, although the various exemplary embodiments discussed below can utilize Java-based servers and related environments, these embodiments are given merely for clarity of disclosure. Therefore, any type of server environment, including various system architectures, can employ the various embodiments of the application-centric resource systems and methods described herein and are considered to be within the scope of this invention.

[0015] For the purposes of this description, the phrases “online connection network application” and “online connection network system” may be referred to as the phrase “online connection network” or simply “connection network” and may be used interchangeably. It will also be noted that an online connection network can be any type of online connection network, such as a professional network, an interest-based network, or any online network system that allows users to join as registered members. Members in an online connection network system are represented by member profiles, which may include various information such as the member’s name, current and previous geographic locations, current and previous employment information, information related to the member’s education, information about the member’s professional achievements, publications, patents, and information about the member’s professional skills. Each member of an online connection network is represented by a member profile (also called a member’s profile or simply a profile). As mentioned above, an online connection network system can be designed to allow registered members to build and record networks of people they know and trust professionally. Any two members can indicate their willingness to “connect” with each other in the context of an online connection network system, as they can view each other’s profiles, recommend and endorse each other’s profiles, and otherwise contact each other via the online connection network system. In the context of an online network system, connected members can be referred to as each other's "connection", and their respective profiles are associated with the respective connection links that indicate that the two profiles are connected.

[0016] As mentioned above, providers of online connectivity systems can offer users free access to the basic functionality of their service, but require a paid subscription for a version that includes additional or enhanced features. These features, such as the ability to send messages directly to recruiters or the ability to retrieve more search results than the free version of the service offers, may be particularly useful to certain members, such as those actively searching for jobs or recruiters. The component of an online connectivity service that provides paid subscriptions (also known as premium subscriptions or services) is the subscription system. The subscription system is configured to present members with information about the premium service, which can be done when a member's interaction with the online connectivity system indicates a potential interest in the premium service. For example, a member might search for jobs at a specific frequency and intensity, or search for member profiles that include a specific skill set, etc. The subscription system can interpret this as an indication that the member will benefit from the features offered by the premium service, such as allowing them to send messages directly to recruiters or allowing them to compare their profile with those of other job seekers. The subscription system can then present members with a UI containing information about the premium service.

[0017] As mentioned above, social proof can be used as a powerful marketing tool. In the context of promoting premium services within an online networking system, a technical challenge is how to automatically identify the most resonant information for a given member profile. For the purposes of this description, the most resonant information is a member profile linked to a given member profile, where the linked member has been identified as a compelling reference for recommending premium services to that member. Another technical challenge is discerning the intent of the member recommending the premium service. For example, a challenge is that the same member may participate in the online networking system for several different purposes. For instance, a member identified as a recruiter in their job title field in an associated member profile may be searching for qualified candidates for a job at one time, while at other times, the same member may be searching for a job for themselves. These two different intents—recruiting and job seeking—can be important in selecting associated member profiles as social proof (i.e., as the most resonant connection). For example, if a member is searching for a job, pointing them to one of their connections successfully recruiting using a premium service would be largely ineffective.

[0018] In some embodiments, the technical problem of identifying the most resonant information regarding a given member profile on premium services is addressed by using a machine learning model (referred to as a member intent model for the purposes of this description) to capture member intent based on member activity on a website provided by an online connectivity network system. The member intent model is trained using previously observed behavioral data of members from the online connectivity network system. The intent model outputs the user's intent. The representation of intent can be an ID mapped to, for example, but not limited to, a job search intent, a networking intent, a sales intent, or a recruitment intent.

[0019] The intent determined by the execution intent machine learning model is used as input to another machine learning model, referred to as the relevance model for the purposes of this description. For a given member profile (called the object member profile, as it is the topic for which the most relevant resonant connections are identified), the relevance model generates scores for member profiles connected to that given member profile. These scores—relevance values—indicate the likelihood that the member will subscribe to the recommended premium service if presented with a message indicating that the associated connection already belongs to a subscriber to that premium service.

[0020] The subscription system selects at least one member profile (i.e., at least one resonant link) from the links in the object member profiles, based on their respective relevance values ​​and the member's near-line browsing behavior on the connected web service website, and presents a reference to that resonant link of the object member on the same screen as the description of the premium service, such as... Figure 5 As shown. Figure 5 The illustration shows sample UI 500, which includes a description of the features offered with the premium subscription and also includes UI element 502, which references the resonant connection selected for the object member profile as the one most likely to persuade the member represented by the object member profile that the premium service recommended is valuable to them.

[0021] Detailed description

[0022] Example subscription system can be found Figure 1 Implemented in the context of the network environment 100 shown.

[0023] like Figure 1As shown, network environment 100 may include client systems 110 and 120 and server system 140. Client system 120 may be a mobile device, such as a mobile phone or tablet. In one example embodiment, server system 140 may host online connection network system 142. As described above, each member of the online connection network is represented by a member profile, which contains personal and professional information about the member and may be associated with connection links indicating connections between the member and other member profiles in the online connection network. Member profiles and related information may be stored as member profile 152 in database 150. Database 150 also stores other entities, such as job postings 154 and job poster profiles 156.

[0024] Client systems 110 and 120 can access server system 140 via communication network 130 using, for example, a browser application 112 running on client system 110 or a mobile application running on client system 120. Communication network 130 can be a public network (e.g., the Internet, a mobile communication network, or any other network capable of transmitting digital data). Figure 1 As shown, server system 140 also hosts subscription system 144. Subscription system 144 is configured to perform a machine learning-based method for identifying resonant connections in an online network by applying the methods discussed herein. An example architecture of subscription system 144 is shown in... Figure 2 As shown in the image.

[0025] Figure 2 yes Figure 1 The subscription system 144 uses the architecture diagram 200 for multi-objective optimization of job application reallocation in an online network. For example... Figure 2As shown, architecture 200 includes at least two machine learning models—a member intent model 210 and a relevance model 220. As described above, member intent model 210 is trained using previously observed behavioral data of members of the online connection network system 142. In some embodiments, member intent model 210 uses a neural network machine learning algorithm. Member intent model 210 takes as input information about the target member (the member for whom resonance connection information is being generated)—member profile data 230 and member motion tracking data 240. Member profile data 230 includes information submitted by the target member to the online connection network system 142 (e.g., the target member's title, education information), information submitted by the target member's connections to the online connection network system 142 (e.g., recognition of the target member's skills), and information derived from the submitted data (e.g., the target member's professional qualifications, their status as an influencer, etc.). Member action tracking data 240 includes information tracked by the online connection network system 142 regarding member interactions with associated websites, such as the average number of job searches performed by a member over a period of time, the average number of job applications, the average number of connection requests, and the average number of direct messages sent and responded to. Member profile data 230 for general members of the online connection network system 142 or for a segment of members within the online connection network system 142, and member action tracking data 240 are used to train the member intent model 210.

[0026] The relevance model 220 takes as input a member intent model 210 (the intent of the object member), information about the object member's connections (member connection feature vector 250), and member-specific aggregated data features 280 and general aggregated data features 270. The member connection feature vector 250 includes information such as the time when the object member has connected to the corresponding connection and the corresponding interactions between the object member and its connection.

[0027] The advanced member feature vector 260 includes information about each connection to an object member's profile, such as whether they subscribe to the premium service, the number of times the object member's profile has been viewed, the number of direct messages with the object member, the time they used the premium service to find a job, average tenure, average promotion time, etc. Member-specific aggregated data features 280 are derived from the member connection feature vector 250 and the advanced member feature vector 260, and include features such as the connection count of object members by domain, the number of connections of object members subscribing to the premium service (referred to as advanced connections for this descriptive purpose), the corresponding number of connections of object members by job title, etc. A domain can be a geographic location (e.g., the San Francisco Bay Area), a professional title (e.g., software engineer), or a specific industry (e.g., marketing / sales / law). The concept of a domain restricts the computation to a smaller subset.

[0028] The general aggregated data feature 270 is derived from the high-level member feature vector 260 and includes information such as, for example, how long it takes for subscribers of high-level services to find a job in a particular industry on average.

[0029] Member connection feature vectors 250 and 260, including those relating to general members or a segment of members in the online connected network system 142, are used to train the correlation model 220. In some embodiments, the correlation model 220 uses a neural network machine learning algorithm.

[0030] Some operations performed by the subscription system 144 can be referenced. Figure 3 Provide a description.

[0031] Figure 3 It is used for in Figure 1 A flowchart of a multi-objective optimization method 300 for job application reallocation in an online connection network 142. Method 300 can be executed by processing logic, which may include hardware (e.g., dedicated logic, programmable logic, microcode, etc.), software, or a combination of both. In one example embodiment, the processing logic resides in... Figure 1 There are 140 server systems.

[0032] like Figure 3 As shown, method 300 begins with operation 310, monitoring the member's interactions with the online connected network system during the member's current login session. This member is represented by a subject profile in the online connected network system. In operation 320, based on the monitored interactions between the member and the online connected network system during the current login session, intent information from the subject profile is identified. Intent information may indicate job searching, recruiting professionals for specific job positions, searching for online education courses, etc., within the online connected network system. The process of identifying intent information may include identifying subdomains of the intent information. For example, when intent information indicates a job search, associated subdomain information may indicate that the job search is characterized as changing industries, searching for lateral changes in different geographical locations, or searching for higher-level positions, etc.

[0033] By executing an intent machine learning model, the intent information of a subject profile is identified using monitored interactions between a member and the online connectivity network system during the current login session as input. The intent machine learning model can be trained using previously tracked member activity (member behavioral data) within the online connectivity network system as training data. In operation 330, the intent information, along with data derived from the subject profile and data derived from profiles connected to the subject profile, is used as input to a relevance machine learning model. The relevance machine learning model is executed to generate a set of candidate profiles from the connected profiles. The relevance machine learning model assigns an associated relevance value to each profile in the candidate profile set. The relevance value assigned to a profile is generated in part based on the connection strength between the profile and the subject profile and represents the probability that the member will subscribe to the recommended premium service if presented with a message that the associated connection is already a subscriber to that premium service. The input to the relevance machine learning model is the intent information, data generated by tracking and storing information related to interactions between members and their connections within the online connectivity network system, and data generated by tracking and storing information related to members' connections and their corresponding status as subscribers to premium services.

[0034] In operation 340, a resonant connection profile is selected from the candidate profile set based on the monitored interactions between the member and the online connected network system during the current login session. The monitored interactions between the member and the online connected network system during the current login session can be referred to as near-line member browsing behavior data. The resonant connection profile selection is the result of performing a relevance-based machine learning model.

[0035] The relevance machine learning model is trained using the following information: previously tracked and stored information relating to the interactions between members of the online connected network system and their corresponding connections, and previously tracked and stored information relating to the behavior of members of the online connected network system as subscribers of advanced services.

[0036] In operation 350, a reference to the selected resonant connection profile is included in the UI as a social identifier regarding advanced services provided by the online connection network system. The UI is then presented on a display device associated with the member represented by the subject profile. Example UI examples including a reference to the selected resonant connection profile are included in the UI as a social identifier regarding advanced services provided by the online connection network system, such as... Figure 5 As shown.

[0037] Figure 4This is a schematic representation of a machine in the example form of a computer system 400, in which a set of instructions can be executed to cause the machine to perform any or more methods discussed herein. In alternative embodiments, the machine operates as a standalone device or can be connected (e.g., networked) to other machines. In a network deployment, the machine may operate as a server or client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), tablet PC, set-top box (STB), personal digital assistant (PDA), cellular phone, web tool, network router, switch, or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) specifying the action to be taken by the machine. Furthermore, although only one machine is shown, the term "machine" should also be considered as including any collection of machines that individually or jointly execute a set (or more) of instructions to perform any or more methods discussed herein.

[0038] Example computer system 400 includes a processor 402 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both), main memory 404, and static memory 406, which communicate with each other via bus 404. Computer system 400 may also include a video display unit 410 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)). Computer system 400 also includes an alphanumeric input device 412 (e.g., a keyboard), a user interface (UI) navigation device 414 (e.g., a cursor control device), a disk drive unit 416, a signal generation device 418 (e.g., a speaker), and a network interface device 420.

[0039] Disk drive unit 416 includes machine-readable medium 422 on which one or more sets of instructions and data structures (e.g., software 424) are stored, which are used by any one or more methods or functions described herein. Software 424 may also reside wholly or at least partially within main memory 404 and / or processor 402 during execution by computer system 400, wherein main memory 404 and processor 402 also constitute machine-readable medium.

[0040] Software 424 can also send or receive on network 426 via network interface device 420 using any of a variety of well-known transport protocols (e.g., Hypertext Transfer Protocol (HTTP)).

[0041] Although machine-readable medium 422 is shown as a single medium in the example embodiment, the term "machine-readable medium" should be considered to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store a set or more sets of instructions. The term "machine-readable medium" should also be considered to include any medium capable of storing and encoding a set of instructions that are executed by a machine and cause the machine to perform any one or more methods of the embodiments of the present invention, or capable of storing and encoding data structures used by or associated with such a set of instructions. Therefore, the term "machine-readable medium" should be understood to include, but is not limited to, solid-state storage, optical and magnetic media. Such media may also include, but is not limited to, hard disks, floppy disks, flash memory cards, digital video disks, random access memory (RAM), read-only memory (ROM), etc.

[0042] The embodiments described herein can be implemented in an operating environment that includes software, hardware, or a combination of software and hardware installed on a computer. Such embodiments of the subject matter of this invention may be referred to individually or collectively as the term "invention" herein, for convenience only, and are not intended to voluntarily limit the scope of this application to any single invention or inventive concept (if more than one invention or inventive concept is disclosed).

[0043] Modules, components and logic

[0044] Some embodiments are described herein as including logic or multiple components, modules, or mechanisms. Modules may constitute software modules (e.g., code embodied in (1) or (2) in transmitted signals on a non-transitory machine-readable medium) or hardware-implemented modules. Hardware-implemented modules are tangible units capable of performing certain operations and may be configured or arranged in a certain manner. In example embodiments, one or more computer systems (e.g., standalone, client, or server computer systems) or one or more processors may be hardware-implemented modules configured by software (e.g., an application or application portion) to operate to perform certain operations described herein.

[0045] In various embodiments, the hardware-implemented module can be implemented mechanically or electronically. For example, a hardware-implemented module may include dedicated circuitry or logic permanently configured (e.g., as a dedicated processor, such as a field-programmable gate array (FPGA) or application-specific integrated circuit (ASIC)) to perform certain operations. A hardware-implemented module may also include programmable logic or circuitry temporarily configured by software to perform certain operations (e.g., contained within a general-purpose processor or other programmable processor). It should be appreciated that the decision to implement a hardware-implemented module mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.

[0046] Therefore, the term "hardware-implemented module" should be understood to include tangible things that are physically constructed, permanently configured (e.g., hardwired) or temporarily or provisionally configured (e.g., programmed) to operate and / or perform certain operations described herein. Consider embodiments where hardware-implemented modules are provisionally configured (e.g., programmed), and each hardware-implemented module does not need to be configured or instantiated at any given time. For example, in cases where the hardware-implemented modules include a general-purpose processor configured using software, the general-purpose processor can be configured as various different hardware-implemented modules at different times. The software can accordingly configure the processor, for example, to constitute a specific hardware-implemented module at one time instance and different hardware-implemented modules at different time instances.

[0047] Hardware-implemented modules can provide information to and receive information from other hardware-implemented modules. Therefore, the described hardware-implemented modules can be considered communication-coupled. In the presence of multiple such hardware-implemented modules, communication can be achieved through signal transmission connecting the modules (e.g., via appropriate circuitry and buses). In embodiments where multiple hardware-implemented modules are configured or instantiated at different times, communication between these modules can be achieved, for example, through the storage and retrieval of information in a memory structure to which the multiple modules have access. For example, one hardware-implemented module can perform an operation and store the output of that operation in a memory device to which it is communication-coupled. Another hardware-implemented module can then later access the memory device to retrieve and process the stored output. Hardware-implemented modules can also initiate communication with input or output devices and can operate on resources (e.g., information sets).

[0048] The various operations of the example methods described herein can be performed, at least in part, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors can constitute modules of processor implementations that operate to perform one or more operations or functions. In some example embodiments, the modules referred to herein may include processor-implemented modules.

[0049] Similarly, the methods described herein can be implemented at least in part by a processor. For example, at least some operations of the methods can be performed by one or more processors or modules implemented by processors. The execution of certain operations may be distributed among one or more processors, residing not only within a single machine but deployed across multiple machines. In some example embodiments, one or more processors may reside in a single location (e.g., in a home environment, an office environment, or as a server cluster), while in other embodiments, the processors may be distributed across multiple locations.

[0050] One or more processors may also run to support the execution of related operations in a “cloud computing” environment or as “Software as a Service” (SaaS). For example, at least some operations may be performed by a group of computers (as an example of a machine that includes processors), which are accessible via a network (e.g., the Internet) and through one or more appropriate interfaces (e.g., application programming interfaces (APIs)).

[0051] Therefore, methods and systems for identifying resonant connections in online connected networks based on machine learning have been described. Although embodiments have been described with reference to specific example examples, various modifications and changes can be made to these embodiments without departing from the broader scope of the subject matter of the invention. Therefore, the specification and drawings are to be considered illustrative rather than restrictive.

Claims

1. A computer-implemented method, comprising: Maintain member profiles in an online connected network system, the member profiles including body profiles representing members in the online connected network system, the body profiles being associated with connection profiles derived from the member profiles; Monitor the member's interactions with the online connection network system during the member's current login session; Based on the monitored interactions between the member and the online connection network system during the current login session, the intent information of the subject profile is identified; Using the intent information, along with data derived from the subject profile and data derived from the connection profile, as input to the relevance machine learning model, the relevance machine learning model is executed to generate a set of candidate profiles from the connection profiles, each profile from the candidate profile set having an associated relevance value indicating the strength of the connection between the profile and the subject profile. Based on the monitored interactions between the member and the online connection network system during the current login session, a resonant connection profile is selected from the candidate profile set; as well as A reference to the selected resonance connection profile, along with information about advanced services provided by the online connection network system, is included in the user interface.

2. The method as described in claim 1, wherein, Identifying the intent information in the subject profile involves using monitored interactions between the member and the online connection network system during the current login session as input to perform an intent machine learning model.

3. The method of claim 2, comprising: Track and store the activities of members in the online connected network system to generate member behavioral data; as well as The intention machine learning model is trained using the behavioral data of the members.

4. The method of claim 1, further comprising rendering the user interface on a display device associated with a member represented by the subject profile.

5. The method of claim 1, wherein, The selection of the resonant connection profile includes using the monitored interactions between the member and the online connection network system during the current login session as input to execute the correlation machine learning model.

6. The method of claim 1, further comprising tracking and storing information related to interactions between the members and their connections in the online connection network system, wherein, The data derived from the subject profile and used as input to the relevance machine learning model includes tracked information related to the interactions between the members and the connections between the members.

7. The method of claim 1, further comprising tracking and storing information related to the members' connections and their respective status as subscribers of the premium service, wherein, The data derived from the connection profile and used as input to the relevance machine learning model includes information about the tracked connections with members and their respective status as subscribers to the advanced service.

8. The method of claim 1, comprising: Tracking and storing information related to the interactions between members of the online connection network system and their respective connections; Tracking and storing information related to the behavior of members of the online connection network system who are subscribers to the advanced service within the online connection network system; as well as The relevance machine learning model is trained using the following information: information relating to the interactions between members of the online connection network system and their respective connections, and information relating to the behavior of members of the online connection network system who are subscribers to the advanced service.

9. The method of claim 1, wherein, The intent information indicates a job search within the online connection network system.

10. The method of claim 1, wherein, Identifying the intent information of the subject profile includes identifying subdomains of the intent information, wherein the resonant connection profile is characterized as the subdomain of the intent information.

11. A system comprising: one or more processors; as well as A non-transitory computer-readable storage medium comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including: Maintain member profiles in an online connected network system, the member profiles including body profiles representing members in the online connected network system, the body profiles being associated with connection profiles derived from the member profiles; Monitor the member's interactions with the online connection network system during the member's current login session; Based on the monitored interactions between the member and the online connection network system during the current login session, the intent information of the subject profile is identified; Using the intent information, along with data derived from the subject profile and data derived from the connection profile, as input to the relevance machine learning model, the relevance machine learning model is executed to generate a set of candidate profiles from the connection profiles, each profile from the candidate profile set having an associated relevance value indicating the strength of the connection between the profile and the subject profile. Based on the monitored interactions between the member and the online connection network system during the current login session, a resonant connection profile is selected from the candidate profile set; as well as A reference to the selected resonance connection profile, along with information about advanced services provided by the online connection network system, is included in the user interface.

12. The system of claim 11, wherein, Identifying intent information in the subject profile involves using monitored interactions between the member and the online connection network system during the current login session as input to perform an intent machine learning model.

13. The system of claim 12, comprising: Track and store the activities of members in the online connected network system to generate member behavioral data; as well as The intention machine learning model is trained using the behavioral data of the members.

14. The system of claim 11, further comprising rendering the user interface on a display device associated with the member represented by the subject profile.

15. The system of claim 11, wherein, The selection of the resonant connection profile includes using the monitored interactions between the member and the online connection network system during the current login session as input to execute the correlation machine learning model.

16. The system of claim 11, further comprising tracking and storing information related to interactions between the members and their connections in the online connection network system, wherein, The data derived from the subject profile and used as input to the relevance machine learning model includes information related to the tracked interactions between the members and the connections between the members.

17. The system of claim 11, further comprising tracking and storing information relating to the members' connections and their respective status as subscribers to the premium service, wherein, The data derived from the connection profile and used as input to the relevance machine learning model includes information related to the tracked connections with the members and their respective status as subscribers to the premium service.

18. The system of claim 11, comprising: Tracking and storing information related to the interactions between members of the online connection network system and their respective connections; Tracking and storing information related to the behavior of members of the online connection network system who are subscribers to the advanced service within the online connection network system; as well as The relevance machine learning model is trained using the following information: information relating to the interactions between members of the online connection network system and their respective connections, and information relating to the behavior of members of the online connection network system who are subscribers to the advanced service.

19. The system of claim 11, wherein, The intent information indicates a job search within the online connection network system.

20. A machine-readable, non-transitory storage medium having machine-executable instruction data that causes the machine to perform operations including: Maintain member profiles in an online connected network system, the member profiles including body profiles representing members in the online connected network system, the body profiles being associated with connection profiles derived from the member profiles; Monitor the member's interactions with the online connection network system during the member's current login session; Based on the monitored interactions between the member and the online connection network system during the current login session, the intent information of the subject profile is identified; Using the intent information, along with data derived from the subject profile and data derived from the connection profile, as input to the relevance machine learning model, the relevance machine learning model is executed to generate a set of candidate profiles from the connection profiles, each profile from the candidate profile set having an associated relevance value indicating the strength of the connection between the profile and the subject profile. Based on the monitored interactions between the member and the online connection network system during the current login session, a resonant connection profile is selected from the candidate profile set; as well as A reference to the selected resonance connection profile, along with information about advanced services provided by the online connection network system, is included in the user interface.

Images