Method and system for operating user matching service using identifier
The method and system enhance user matching services by assigning identifiers based on suitability and managing resources dynamically, improving matching accuracy and protecting personal information through activity data separation.
Patent Information
- Application Number
- KR1020260097856
- Authority / Receiving Office
- KR · KR
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2026-05-29
- Publication Date
- 2026-11-11
- Estimated Expiration
- 2046-05-29
AI Technical Summary
Existing user matching services face challenges in assigning suitable identifiers to new participants, managing identifier lifespan, and ensuring compatibility between personal information protection and data usability.
A method and system that assign identifiers based on suitability calculations using activity data, dynamically manage identifier resources, and separate personal information from activity data to enhance matching accuracy and privacy.
This approach allows for refined identifier profiles that improve matching criteria over time, manage identifier lifespan effectively, and protect personal information while utilizing activity data efficiently.
Smart Images

Figure 112026065533565-PAT00001_ABST
Abstract
Description
Technology Field
[0001] The present disclosure relates to a method and system for operating a user matching service using a fitness-based identifier. Background Technology
[0002] The following description merely provides background information related to the present embodiment and does not constitute prior art.
[0003] A user matching service may be a service that supports the formation of relationships, interactions, or matching among multiple users. For example, it may be a collective term for couple matching services, blind date platforms, social networking services (SNS), metaverse-based relationship formation services, or matching content in the form of broadcast programs.
[0004] User matching services may assign users an identifiable name, such as a unique account or nickname, and provide matching content between users based on their profile information. User profiles may include basic information such as gender, age, occupation, place of residence, and portrait, as well as personal preference information such as hobbies, tendencies, and interests. In some services, self-introduction text written by the user, or images or videos of the user, may be included as part of the profile.
[0005] User matching services may utilize methods to enhance matching results by calculating similarity between profile information entered by users to extract matching candidates, or by combining various signals such as analysis results of portrait photos, users' current location information, behavior logs, and message exchange patterns between users.
[0006] In addition, some dating services utilize artificial intelligence technology to learn users' preferences and provide features that automatically generate and recommend date plans based on the learning results, or assist users in practicing conversation or matching through conversation simulations with virtual AI characters. The problem to be solved
[0007] The present disclosure aims to provide a method for assigning a suitable identifier to a new participant based on activity data accumulated and stored in identifier units, and for updating the profile of the assigned identifier into a form that can be utilized for subsequent matching.
[0008] The present disclosure aims to provide a method for dynamically managing the lifespan of limited identifier resources based on accumulated activity data.
[0009] The present disclosure aims to provide a method that can achieve the compatibility of personal information protection and data usability by managing users' personal information and activity data separately.
[0010] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem
[0011] According to one aspect of the present disclosure, a method for operating a user matching service using a suitability-based identifier, performed by a server comprising at least one processor, comprises: receiving user information of a participant from a user terminal; calculating a suitability between a profile of each identifier and user information based on a plurality of identifiers included in an identifier set and the user information; determining an identifier corresponding to the participant based on the calculated suitability; assigning the determined identifier to the participant; collecting activity data of the participant assigned the determined identifier; and updating the profile of the determined identifier based on the collected activity data, wherein the updated profile is used for subsequent suitability calculation.
[0012] According to another aspect of the present disclosure, a user matching service operating system using a suitability-based identifier comprises: a user terminal; and a server that communicates with the user terminal and includes at least one processor and at least one memory that stores instructions, wherein when the instructions are executed by the at least one processor, the processor performs the following steps: receiving user information of a participant from the user terminal; calculating a suitability between a profile of each identifier and user information based on a plurality of identifiers included in a set of identifiers and the user information; determining an identifier corresponding to the participant based on the calculated suitability; assigning the determined identifier to the participant; collecting activity data of the participant assigned the determined identifier; and updating the profile of the determined identifier based on the collected activity data, wherein the updated profile is used for subsequent suitability calculation.
[0013] According to another aspect of the present disclosure, an identifier data management method performed by a server comprising at least one processor comprises: a step of storing a profile and a status value corresponding to each of a plurality of identifiers included in an identifier set; a step of collecting activity data of a participant assigned an identifier; a step of storing activity data of a plurality of participants corresponding to the assigned identifier so as to be distinguished and accumulated by the session identification value based on the assigned identifier and the session identification value representing the session in which the participant participates; a step of updating the profile and the identifier evaluation value of the assigned identifier based on the accumulated stored activity data; and a step of updating the status value of the assigned identifier based on the updated identifier evaluation value, wherein the updated profile is used for subsequent identifier assignment. Effects of the invention
[0014] According to a disclosed embodiment, by assigning an identifier to a participant based on the degree of fit between the identifier profile and the participant's user information, a participant corresponding to the accumulated data can be assigned to the same identifier. Through assignment based on the degree of fit, activity data of a sample group with consistent characteristics can be accumulated under the same identifier, and the identifier profile derived from the accumulated activity data can have statistical characteristic values of a consistent trend.
[0015] According to a disclosed embodiment, an identifier profile is updated based on collected activity data, and the updated profile is reused for subsequent suitability calculations, thereby forming a self-reinforcing structure in which assignment and accumulation are repeated in each round. As activity data accumulates, the identifier profile can become more refined, and the refined profile can be used as a criterion for assigning identifiers to participants in subsequent rounds, so that the matching criteria can be improved as rounds accumulate.
[0016] According to one disclosed embodiment, in the early stages of operation when an identifier profile is not formed, an identifier is assigned based on seed attributes or the operator's initial criteria, and after activity data is accumulated beyond a threshold amount and a profile is formed, an identifier can be assigned based on suitability. Through the stepwise transition of assignment criteria, identifier assignment can be performed even in the initial situation where accumulated reference data is absent, while transitioning to data-based assignment after data is accumulated.
[0017] According to one disclosed embodiment, the profile of an assigned identifier may be provided as an initial operational reference value for a new participant, and as the new participant's activity data accumulates, the reflection weight of the initial operational reference value may decrease and the reflection weight of the new participant's actual activity data may increase. Through the adjustment of weights, the profile of the identifier may not be fixed as a permanent attribute of the new participant but may act as a temporary correction value, thereby allowing the unique characteristics of the new participant to be gradually reflected.
[0018] According to a disclosed embodiment, activity data of multiple participants can be accumulated and distinguished by the round identification value based on assigned identifiers and round identification values. By accumulating activity data of different participants for each round in a many-to-one manner under the same identifier, data can be aggregated by identifier unit while reusing a limited number of identifiers.
[0019] According to a disclosed embodiment, the profile and identifier evaluation value of an identifier are updated based on accumulated stored activity data, and the status value of an identifier can be updated based on the updated identifier evaluation value. Through the updating of the status value based on the identifier evaluation value, the lifespan of a limited identifier resource can be dynamically managed based on the accumulated activity data, and identifiers with low assignment values can be excluded from the assignment target, or identifiers with restored assignment values can be returned to the assignment target.
[0020] According to a disclosed embodiment, activity data of multiple participants is accumulated in a many-to-one manner under the same identifier, thereby enabling de-identification where it is difficult to identify a specific participant based solely on the identifier; additionally, the correspondence between the identifier and the participant's real name information can be stored in a storage area separate from the activity data. By combining the many-to-one accumulation structure and the separate storage structure, the utilization of activity data and the protection of the participant's personal information can be achieved simultaneously.
[0021] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing
[0022] FIG. 1 is a block diagram schematically showing the configuration of a user matching service operating system according to a disclosed embodiment. FIG. 2 is a schematic diagram illustrating a suitability calculation module according to a disclosed embodiment. FIG. 3 is a schematic diagram illustrating a many-to-one cumulative data storage method according to a disclosed embodiment. FIG. 4 is a schematic flowchart illustrating a self-reinforcing closed-loop operation according to a disclosed embodiment. FIG. 5 is a schematic diagram showing the configuration of an exemplary computing device that can be used to implement the devices and methods according to the disclosed embodiments. Specific details for implementing the invention
[0023] Some embodiments of the present disclosure are described in detail below with reference to exemplary drawings. It should be noted that in assigning reference numerals to the components of each drawing, the same components are given the same reference numeral whenever possible, even if they are shown in different drawings. Furthermore, in describing the present disclosure, if it is determined that a detailed description of related known components or functions could obscure the essence of the present disclosure, such detailed description is omitted.
[0024] In describing the components of the embodiments according to the present disclosure, symbols such as first, second, i), ii), a), b), etc., may be used. These symbols are intended only to distinguish the components from other components, and the essence, order, or sequence of the components is not limited by the symbols. When a part in the specification is described as 'comprising' or 'having' a component, this means that, unless explicitly stated otherwise, it does not exclude other components but may include additional components.
[0025] The detailed description set forth below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present disclosure and is not intended to represent the only embodiment in which the present disclosure can be practiced.
[0026] In this disclosure, the term "identifier" may refer to an identification name that can be repeatedly assigned to different participants of different rounds or sessions within matching content provided by a user matching service. The identifier may have an identifier profile calculated based on the activity data of multiple participants to whom the identifier is assigned. In this sense, the identifier in this specification may also be referred to as a content character identifier.
[0027] In the present disclosure, the 'user matching service' may be a service that supports the formation of relationships, mutual selection, interaction, or matching among multiple users.
[0028] In the present disclosure, "content" may refer to a progress environment or event unit within a user matching service where a participant is assigned an identifier to engage in activities and such activities are recorded as data. Content may be operated in units of episodes, sessions, seasons, or events. Content may include, but is not limited to, matching content in the form of broadcast programs, offline matching programs, real-time interaction events, in-game collaboration events, metaverse-based interaction events, or live streaming-based participation events.
[0029] FIG. 1 is a block diagram schematically showing the configuration of a user matching service operating system according to a disclosed embodiment.
[0030] Referring to FIG. 1, the user matching service operating system (100) may include one or more of a user terminal (110), a server (120), or an operator terminal (130).
[0031] One or more participants may participate in each content round of the user matching service. Here, a round may refer to a unit period or unit session in which the user matching service is conducted. Multiple participants may, for example, transmit their user information to the server (120) through their respective user terminals (110), or they may transmit user information to the server (120) by sharing the same user terminal (110). The method of inputting or transmitting user information is not limited to any one method.
[0032] The server (120) may include one or more of a fitness calculation module (210), an identifier determination module (220), an activity data collection module (230), an identifier evaluation value calculation module (240), an identifier state management module (250), a cumulative profile storage module (260), an identifier set storage module (270), or an identity mapping storage module (280). A detailed description of the operation and interrelationships of each module will be provided later.
[0033] The server (120) can assign an identifier to a participant based on user information received from a user terminal (110). The user terminal (110) can receive an identifier assignment result or a matching result from the server (120). A participant assigned an identifier can participate in various content provided by the user matching service, and the server (120) can collect activity data and accumulate and store the activity data for each content round. The server (120) can update the identifier profile based on the accumulated activity data.
[0034] The user terminal (110) is a terminal used by a participant and can transmit user information to the server (120) or receive an identifier assignment result or a matching result from the server (120).
[0035] The operator terminal (130) is a terminal used by the operator of the user matching service and can transmit evaluations, operation settings, or operation commands entered by the operator to the server (120).
[0036] FIG. 2 is a schematic diagram illustrating a suitability calculation module according to a disclosed embodiment.
[0037] Referring to FIG. 2, the suitability calculation module (210) can receive user information (2100) from a user terminal (110) and an identifier profile (2200) from a cumulative profile storage module (260) as input data. The suitability calculation module (210) can calculate a suitability (2300) for each identifier based on the received input data and can transmit the calculated suitability (2300) for each identifier to the identifier determination module (220). The identifier determination module (220) can determine an identifier to be assigned to a participant based on the suitability (2300) for each identifier by referring to the identifier information (2400) stored in the identifier set storage module (270), and can assign the determined identifier (2500) to the participant.
[0038] Here, the identifier set storage module (270) can store a plurality of identifiers included in the identifier set, a status value for each identifier, and a seed attribute for each identifier, and the cumulative profile storage module (260) can store activity data accumulated for each identifier and an identifier profile (2200) derived from the accumulated activity data.
[0039] First, the input data received by the suitability calculation module (210) is described.
[0040] User information (2100) may be information that a participant inputs to participate in a user matching service. User information (2100) may include, for example, one or more of pre-survey information, preference information, inclination information, role tags, self-introduction information, selected behavioral characteristics, interaction style information, or content operation suitability information.
[0041] Preliminary survey information may be survey responses intended to verify the participant's basic personal details or matching conditions, and may include, for example, responses regarding the participant's age group, residential area, occupation, educational background, or marital history.
[0042] Preference information may be information regarding the partner or matching conditions preferred by the participant, and may include, for example, input regarding the age range, physical characteristics, type of occupation, or hobby area of the preferred partner.
[0043] Disposition information may be information regarding a participant's personality, values, or relationship formation style, and may include, for example, one or more of personality type test results (e.g., MBTI results), degree of introversion or extraversion, values, tendency to initiate conversation during the relationship formation process, tendency to express emotions, preference for the speed of relationship progression, or sensitivity to the other person's reaction.
[0044] Role tags may include roles that a participant chooses to perform within the content or role identification tags assigned to the participant by the operator. Role tags may include various types of tags, for example, mood leader, active mood maker, mediator, competition inducer, majority preference inducer, participant with high selection concentration, conflict inducer, interest inducer, observer, strategic participant, emotion-focused participant, leader participant, supportive participant, active interaction participant, cautious analyst, or cautious interaction participant.
[0045] Self-introduction information may include introductory information in the form of text, images, or videos freely entered by the participant.
[0046] The characteristics of choice behavior may be information regarding a participant's choice behavior during the relationship formation process, and may include, for example, one or more of the following: concentration on the object of interest, possibility of changing the object of choice, possibility of mutual selection, possibility of forming multiple objects of interest, or possibility of behavioral change based on the result of the choice.
[0047] Interaction style information may be information regarding a participant's interaction pattern and may include, for example, one or more of the following: frequency of conversation initiation, duration of conversation, preference for one-on-one interaction, level of participation in multi-party interaction, frequency of questioning, frequency of expression of empathy, tendency to avoid conflict, or tendency to face conflict.
[0048] Content operation suitability information may be information regarding suitability that a participant may possess in terms of content operation, and may include, for example, one or more of the following: potential to induce conversation, potential to induce a change in relationship, potential to generate an emotional response, importance of editing, potential to induce an external response, or content contribution.
[0049] The identifier profile (2200) is information corresponding to each identifier included in the set of identifiers, and may be in the form of a multidimensional profile vector that includes as components statistical characteristic values calculated from the activity data of multiple participants to whom the identifier is assigned, such as mean value, variance value, quantile value, frequency value, ratio value, trend value, selection pattern value, or response pattern value.
[0050] The identifier profile (2200) may further include a reaction change pattern derived from the activity data of past participants who have been assigned the identifier. The reaction change pattern may include, for example, one or more of external reaction changes according to the progression of rounds, reaction changes before and after a selection event, periods of increased interaction, periods of concentrated interest, or reaction changes before and after the occurrence of a matching result.
[0051] The identifier profile (2200) may further include interaction style information of past participants to whom the identifier was assigned, and information on the type of counterpart that was matched or interacted with the identifier in the past.
[0052] The specific method for calculating and updating the identifier profile (2200) will be described in more detail later in the description of the cumulative profile storage module (260).
[0053] Next, the operation of the suitability calculation module (210) is described.
[0054] The suitability calculation module (210) can calculate the suitability (2300) between user information (2100) and identifier profile (2200) for each identifier. The suitability (2300) may be a quantitative value representing the degree of correspondence between the characteristics of a participant and the character of an identifier, and may be, for example, a normalized value between 0 and 1. The suitability (2300) may be calculated based on one or more of the similarity, distance value, weighted sum score, condition matching rate, or output value of a classification model between user information (2100) and identifier profile (2200).
[0055] According to one embodiment, the fit calculation module (210) can convert user information (2100) and identifier profile (2200) into multidimensional vectors, respectively, and then calculate the similarity between the two vectors as the fit (2300). For example, the fit calculation module (210) can calculate one or more of cosine similarity, Jaccard similarity, or Pearson correlation coefficient between the two vectors. Cosine similarity can be calculated by dividing the inner product of the two vectors by the product of the norms of each vector, Jaccard similarity can be calculated by dividing the size of the intersection of the two sets by the size of the union, and Pearson correlation coefficient can be calculated by dividing the covariance of the two vectors by the product of the standard deviations of each vector.
[0056] According to another embodiment, the fitness calculation module (210) can calculate a distance value between user information (2100) and an identifier profile (2200), and calculate the fitness (2300) by normalizing the calculated distance value such that the fitness (2300) is higher as the calculated distance value is smaller. For example, the fitness calculation module (210) can calculate one or more of the Euclidean distance, Manhattan distance, or Mahalanobis distance between two vectors.
[0057] According to another embodiment, the suitability calculation module (210) can calculate the suitability (2300) by summing the degree of match for each item of user information (2100) and identifier profile (2200) by multiplying them by a pre-set weight. For example, the degree of match between the tendency items of user information (2100) and the tendency items of identifier profile (2200) can be multiplied by a weight of 0.4, the degree of match for preference items by a weight of 0.3, and the degree of match for pre-survey items by a weight of 0.3, and the sum can be calculated as the weighted sum score. The weight for each item can be adjusted by input received from the operator terminal (130).
[0058] According to another embodiment, the suitability calculation module (210) can calculate the ratio of items among the predefined condition items that the user information (2100) satisfies as the condition matching rate and use it as the suitability (2300). For example, if the identifier profile (2200) of a specific identifier has three condition items, such as “propensity to induce competition,” “frequency of high emotional expression,” and “pattern of conflict in relationships with multiple participants,” and the user information (2100) satisfies two of these conditions, the condition matching rate for the identifier can be calculated as approximately 0.67.
[0059] According to another embodiment, the fit calculation module (210) can calculate the fit (2300) using a classification model that receives user information (2100) as input and outputs the likelihood of fit for each identifier. The classification model may include, for example, one or more of a logistic regression model, a support vector machine, a decision tree, a random forest, or an artificial neural network model. The classification model is pre-trained with past matching result data of a user matching service and can output a fit probability for each identifier when user information (2100) is input. The fit calculation module (210) can use the output probability value of the classification model as the fit (2300).
[0060] According to another embodiment, the suitability calculation module (210) may calculate the suitability (2300) in both directions by additionally considering the suitability between the participant's own characteristics and the identifier profile (2200), as well as the suitability between the participant's preference conditions and the past interaction target types included in the identifier profile (2200). For example, the suitability calculation module (210) may calculate a first suitability between the participant's user information (2100) and the identifier profile (2200), and a second suitability between the participant's preference information and the past matching or interaction target type information included in the identifier profile (2200), respectively, and then calculate the final suitability (2300) by weighted summing the first suitability and the second suitability.
[0061] Next, the operation of the identifier determination module (220) is described.
[0062] The identifier determination module (220) can determine the identifier (2500) to be assigned to the participant based on the suitability (2300) for each identifier received from the suitability calculation module (210). For example, the identifier determination module (220) can select the identifier having the highest suitability among the suitability (2300) for each identifier as the determined identifier (2500). In another embodiment, the identifier determination module (220) may select any one of the identifiers having a suitability greater than or equal to a preset threshold among the suitability (2300) for each identifier as the determined identifier (2500) based on randomness or priority by an operator. The determined identifier (2500) can be assigned to the participant, and the result of assigning the identifier can be transmitted to the user terminal (110).
[0063] Meanwhile, during the initial operation of the user matching service, activity data may not be sufficiently accumulated for some of the identifiers included in the identifier set, so an identifier profile (2200) may not be formed. For identifiers for which an identifier profile (2200) has not been formed, the identifier determination module (220) may assign the identifier to the participant based on one or more of the seed attribute previously assigned to the identifier or the initial criteria received from the operator terminal (130). The seed attribute may be stored for each identifier in the identifier set storage module (270).
[0064] Here, the seed attribute may be an initial attribute value assigned in advance when an identifier is added to a set of identifiers. The seed attribute may include, for example, an initial profile value corresponding to a character concept pre-set by the operator for each identifier. For example, for an identifier with the concept of 'lively mood maker,' initial propensity values such as extraversion 0.8 and activity 0.9 may be assigned as the seed attribute, and for an identifier with the concept of 'prudent analyst,' initial propensity values such as extraversion 0.3 and analytical ability 0.8 may be assigned as the seed attribute. For identifiers for which an identifier profile (2200) has not been formed, the suitability calculation module (210) can calculate the suitability (2300) with user information (2100) by using the seed attribute as input data to replace the identifier profile (2200).
[0065] The operator initial criteria may be assignment rules directly set by the operator through the operator terminal (130). The operator initial criteria may include, for example, an explicit rule to preferentially assign a specific identifier to a participant having a specific type of user information, or a time-based rule to assign only a specific identifier during a specific period.
[0066] When activity data is accumulated in an identifier exceeding a preset threshold amount and an identifier profile (2200) is formed, the identifier determination module (220) can switch the assignment criteria for the identifier from assignment based on seed attributes or operator initial criteria to assignment based on suitability.
[0067] The activity data collection module (230) can collect activity data that occurs while a participant assigned an identifier is active in content provided by the user matching service. The activity data collection module (230) can, for example, receive activity data corresponding to the participant's input from a user terminal (110), automatically collect activity data from the system log of the user matching service, or receive input data from an operator from an operator terminal (130). The activity data collection module (230) can transmit the collected activity data to one or more of the identifier evaluation value calculation module (240) or the cumulative profile storage module (260).
[0068] Activity data may include, for example, one or more of quantitative inputs that can be collected from system logs or operator input values received from an operator through an operator terminal (130).
[0069] Quantitative inputs may include, for example, one or more of external response indicators, participant activity indicators, or matching result indicators.
[0070] External reaction indicators may be indicators representing external reactions to a participant or identifier. External reaction indicators may include, for example, one or more of the following: real-time vote counts, like counts, mention frequency, viewer reaction figures, or external evaluation scores.
[0071] Participant activity metrics may be indicators representing activities performed by a participant within the content. Participant activity metrics may include, for example, one or more of the following: the number of interactions with other participants, session duration, number of conversations initiated, number of responses, number of participations in events occurring within the content, the rate of one-on-one conversations, or the rate of participation in multi-party conversations.
[0072] The matching result indicator may be an indicator representing the matching result for a participant. The matching result indicator may include, for example, one or more of the following: the number of times a participant was selected by another participant, the number of times a participant made a selection to another participant, whether mutual selection occurred, or whether a final match was successful.
[0073] The operator input value may be an evaluation or tag entered by the operator through the operator terminal (130). The operator input value may include, for example, one or more of an operator evaluation value, a relationship change tag, or an editing importance tag.
[0074] The operator rating value may be an evaluation score assigned by an operator to a participant or identifier. For example, the operator rating value may be a quantitative evaluation by an operator regarding a participant's content contribution, degree of character manifestation, or matching authenticity.
[0075] Relationship change tags may be tags that indicate the point in time when the relationship between participants within the content changed, or the nature of the relationship change. For example, a relationship change tag may be assigned at the point when the relationship between a specific pair of participants transitioned from the liking stage to the conflict stage, or from the conflict stage to the reconciliation stage.
[0076] Edit importance tags can be tags that indicate the importance of activity data from a content operation perspective. For example, edit importance tags can indicate whether specific activity data corresponds to a major event in the content, an event likely to induce viewer immersion, or a highlight of the content.
[0077] Operator input values can be used as auxiliary data to supplement quantitative input automatically collected from system logs.
[0078] The activity data collection module (230) can transmit the collected activity data to one or more of the identifier evaluation value calculation module (240) or the cumulative profile storage module (260), along with an identifier assigned to the participant in whom the activity data occurred and a round identification value indicating the round in which the activity occurred. Through this, the activity data can be distinguished as corresponding to which identifier and which round, and subsequently processed.
[0079] The identifier evaluation value calculation module (240) can calculate an identifier evaluation value for each identifier based on activity data received from the activity data collection module (230). The identifier evaluation value calculation module (240) can transmit the calculated identifier evaluation value to one or more of the identifier status management module (250) or the cumulative profile storage module (260).
[0080] The identifier evaluation value may be an indicator that quantitatively represents how high the level of response, interaction, or character an identifier forms within the content. The identifier evaluation value can be calculated, for example, based on how many responses the participant assigned the identifier elicited from other participants or spectators, how active the interaction generated, or how distinct the character was displayed within the content.
[0081] For example, if a participant assigned a specific identifier is repeatedly selected by multiple participants, has a high frequency of interaction, or has high viewer response rates, the identifier evaluation value of that identifier may be calculated as high. Conversely, if there is almost no interaction or low response inducement within the content, the identifier evaluation value of that identifier may be calculated as low.
[0082] That is, the identifier evaluation value may be an indicator value that quantitatively represents the contribution to activity within the content or the degree of change in the identifier profile, and in some embodiments, it may be a score representing the activity score or the degree of expression of character of the identifier. The identifier evaluation value may be, for example, a value normalized from 0 to 1 or a score from 0 to 100.
[0083] The identifier evaluation value calculation module (240) can calculate the identifier evaluation value by applying a pre-set weight to each indicator item included in the activity data and summing them. According to one embodiment, the identifier evaluation value calculation module (240) can sum the values by multiplying one or more items among the external reaction indicator, the participant activity indicator, the matching result indicator, or the operator input value by a pre-set weight. For example, the identifier evaluation value calculation module (240) can calculate the identifier evaluation value for each identifier by summing the values by multiplying the external reaction indicator by a weight of 0.3, the participant activity indicator by a weight of 0.3, the matching result indicator by a weight of 0.3, and the operator input value by a weight of 0.1.
[0084] The identifier evaluation value calculation module (240) can receive weight parameters from the operator terminal (130) and can adjust the weights applied to each item of the activity data based on the received weight parameters. For example, the operator can perform weight adjustments through the operator terminal (130), such as increasing the weight applied to external reaction indicators or decreasing the weight applied to matching result indicators according to the direction of operation of the content. In another embodiment, the weights may be dynamically adjusted according to the progress round, time zone, or stage of operation of the content. Additionally, the weight for the operator input value may be set to 0, in which case the identifier evaluation value may be calculated based on quantitative input automatically collected from the system log.
[0085] The identifier evaluation value calculation module (240) may normalize each indicator item included in the activity data and then perform weighted summation. Normalization may be performed based on one or more of the number of participants per round, exposure time, number of event occurrences, or total amount of collectible activity data. For example, the identifier evaluation value calculation module (240) may normalize the external response indicator by a ratio to the maximum value of the external response indicator per round to convert it into a form comparable between rounds, and then apply weights to the normalized indicators and sum them.
[0086] The calculated identifier evaluation value is transmitted to the identifier state management module (250) and can be used as an input for updating the identifier state value. The state value update operation by the identifier state management module (250) will be described later.
[0087] Additionally, the identifier evaluation value is also transmitted to the cumulative profile storage module (260) and can be managed as activity information accumulated by identifier. The accumulated identifier evaluation value can be used as a part of the identifier profile (2200) or as time series data representing the trend of activity by identifier according to the progress of the round.
[0088] Here, the identifier evaluation value may be used as an internal processing value for state transitions of the identifier resource or updates of the identifier profile (2200). The matching result may be determined by a separate matching logic, and the identifier evaluation value may be used for the management of the identifier resource itself independently of such matching logic.
[0089] FIG. 3 is a schematic diagram illustrating a many-to-one cumulative data storage method according to a disclosed embodiment.
[0090] Referring to FIG. 3, the cumulative profile storage module (260) can accumulate and store activity data records (330) based on a composite key (300) including an identifier key (310) representing an identifier and a round identification value (320), and can calculate and store an identifier profile (2200) for each identifier from the accumulated activity data records (330).
[0091] Here, the identifier key (310) is an identifier that can be repeatedly assigned to different participants in each round by being stored in the identifier set storage module (270), and the round identification value (320) may be an identification value that distinguishes the unit round in which the user matching service is conducted. The activity data record (330) may be a data record in which activity data collected by the activity data collection module (230) is structured according to the identifier key (310) and the round identification value (320).
[0092] The composite key (300) is a key that includes an identifier key (310) corresponding to an identifier and a round identification value (320) together, so that multiple round activity data records (330) corresponding to the same identifier can be stored separately from each other by the round identification value (320).
[0093] For example, as illustrated in FIG. 3, for the same identifier ID_Popular, in the first round, the identifier ID_Popular is assigned to the first participant, and the activity data record (330) of the first participant can be stored under the composite key (300) of (ID_POPULAR, R1). Additionally, in the second round (R2), the same identifier ID_POPULAR is assigned to the second participant, and the activity data record (330) of the second participant can be stored under the composite key (300) of (ID_POPULAR, R2), and in the third round (R3), the same identifier ID_POPULAR is assigned to the third participant, and the activity data record (330) of the third participant can be stored under the composite key (300) of (ID_POPULAR, R3). In this way, the activity data records (330) of different participants can be accumulated in a many-to-one manner for each round under a single identifier.
[0094] From this, the activity data records (330) of multiple participants who were assigned the same identifier can be distinguished from one another by the round identification value (320), and can be aggregated by the identifier to produce an identifier profile (2200).
[0095] The cumulative profile storage module (260) can calculate an identifier profile (2200) for each identifier based on the accumulated activity data records (330). The identifier profile (2200) may be in the form of a multidimensional profile vector that includes, for example, one or more components of an average value, variance value, quantile value, frequency value, ratio value, trend value, selection pattern value, or response pattern value calculated from the activity data of a plurality of participants to whom the corresponding identifier is assigned.
[0096] The average value may be, for example, the average value of each item, such as external response indicators, participant activity indicators, or matching result indicators, for multiple participants assigned the same identifier. The variance value may be, for example, the variance between rounds or between participants of the activity data by item. The quantile value may be a value representing the distribution characteristics of the activity data, such as, for example, the 25th or 75th percentile value. The frequency value may be, for example, the ratio of the number of rounds in which a specific event (e.g., a mutual selection event) occurred. The ratio value may be, for example, the ratio of the number of rounds with successful matches to the total number of rounds. The trend value may be, for example, a slope value representing the trend of increase or decrease of activity data indicators over the course of the rounds. The selection pattern value may be, for example, a pattern value regarding what type of other participant the participant assigned the corresponding identifier selected. The response pattern value may be, for example, a pattern value of the response shown by the participant assigned the corresponding identifier to a specific event.
[0097] The identifier profile (2200) may further include one or more of the interaction style information, reaction change patterns, or past matching / interaction target type information of past participants who were assigned the identifier.
[0098] The cumulative profile storage module (260) can update the identifier profile (2200) whenever a new activity data record (330) is accumulated. The update of the identifier profile (2200) can be performed in one or more of the following ways:, for example, by updating the cumulative average, by applying a round weight to reflect the influence of the recent round more significantly, or by using a moving average method.
[0099] Additionally, the cumulative profile storage module (260) may support two-sided lookups based on an identifier and a round identification value (320). According to one embodiment, the cumulative profile storage module (260) may take an identifier as input and aggregate and return all round activity data records (330) corresponding to the identifier on an identifier-by-identifier basis, and the returned aggregated data may be used for calculating or updating an identifier profile (2200). According to another embodiment, the cumulative profile storage module (260) may take an identifier and a specific round identification value (320) together as input and extract and return only the activity data records (330) of the corresponding round on a round-by-round basis, and the returned extracted data may be used for analysis of a specific round or content operation.
[0100] The generated or updated identifier profile (2200) is transmitted to the suitability calculation module (210) and can be used to calculate the suitability (2300) per identifier for new participants in subsequent rounds. This feedback flow is described in more detail later in the description of FIG. 4.
[0101] The identifier status management module (250) can manage the status value of an identifier. The identifier status management module (250) can update the status value of an identifier based on one or more of the identifier evaluation value received from the identifier evaluation value calculation module (240) or the number of unused rounds for each identifier. The identifier status management module (250) can reflect the updated status value in the identifier set storage module (270), and the identifier determination module (220) can determine the identifier (2500) to be assigned to a new participant by referring to the status value stored in the identifier set storage module (270).
[0102] The status value of the identifier can be, for example, active, standby, inactive, or reactivation candidate.
[0103] The active state may be a state in which the identifier can be assigned to a new participant in the current or subsequent round. The identifier determination module (220) may select an identifier in the active state from the set of identifiers as a candidate for the identifier (2500) to be assigned to a new participant.
[0104] A waiting state may be a state in which the assignment of the corresponding identifier is temporarily suspended or restricted. A waiting state may be applied to identifiers whose evaluation value is not low enough to be completely excluded from the assignment target, but for which the assignment frequency needs to be adjusted for a certain period. Identifiers in a waiting state may be temporarily excluded from the assignment target of the identifier determination module (220).
[0105] An inactive state may be a state in which the corresponding identifier is excluded from the assignment target. An identifier in an inactive state may, in principle, be excluded from the assignment target of the identifier determination module (220). That is, unlike a waiting state which is a temporary hold state, an inactive state may be an exclusion state in principle.
[0106] A reactivation candidate state may be an intermediate state from an inactive state where the possibility of reactivation is being reviewed. Identifiers for reactivation candidate states may be assigned to some participants under pre-set constraints.
[0107] The identifier state management module (250) can transition the state value of the identifier based on various conditions. Below, an embodiment of each state transition operation is described.
[0108] Transition from an active state to an inactive state may be performed, for example, when the identifier evaluation value of the identifier is below a preset threshold value, or when the increase in the identifier evaluation value stagnates for more than a preset threshold number of cycles. For example, an identifier state management module (250) may transition the state value of an identifier from active to inactive if the identifier evaluation value of an identifier is maintained below a threshold value (e.g., 0.3) for three cumulative cycles.
[0109] Transition from an active state to a standby state may be performed, for example, when the number of unused iterations of the identifier is greater than or equal to a preset threshold value, or when an operator’s command to hold assignment is entered through the operator terminal (130). For example, the identifier state management module (250) may transition the status value of an identifier from active to standby if the identifier has not been assigned for more than a preset threshold number of iterations (e.g., 3 times) consecutively.
[0110] The transition from a standby state to an active state may be performed, for example, when a standby release condition is satisfied. The standby release condition may include, for example, the elapsed time of being maintained in a standby state, the occurrence of a shortage of assignable identifier resources, or the input of an operator's active return command through the operator terminal (130).
[0111] Transition from an inactive state to a reactivation candidate state may be performed when any one of the following is satisfied:, for example, an operator's approval input via the operator terminal (130), the elapsed waiting period maintained in an inactive state, or a change in external conditions. Here, a change in external conditions may include, for example, a change in the operation policy of the user matching service, the introduction of a new round operation direction, or the occurrence of a shortage of assignable identifier resources. As an example, the identifier state management module (250) may transition the status value of an identifier from inactive to a reactivation candidate state when a review approval input is received from the operator terminal (130) for an identifier that has been maintained in an inactive state for a pre-set period (e.g., 5 rounds).
[0112] Transition from a reactivation candidate state to an active state may be performed, for example, when an identifier of a reactivation candidate state is assigned to a participant under pre-set constraints, and the identifier evaluation value calculated from activity data collected for said identifier satisfies pre-set criteria conditions. Here, constraints may include, for example, a limit on the number of participants that can be assigned, a limit on the number of times that can be assigned, or conditions for operator admission. As an example, the identifier state management module (250) may transition the status value of said identifier from reactivation candidate to active if the identifier evaluation value calculated after the reactivation candidate identifier has been assigned only once is greater than or equal to a threshold value (e.g., 0.5).
[0113] Input through the operator terminal (130) can be used as an auxiliary condition to supplement automatic state transitions based on an identifier evaluation value or the number of unused cycles.
[0114] The status value updated by the identifier status management module (250) can be reflected in the identifier set storage module (270), and the identifier determination module (220) can select only the identifiers in an active state as candidates for assignment by referring to the status value stored in the identifier set storage module (270) when assigning identifiers in a subsequent round. Through this, identifiers in an inactive or waiting state among the identifier sets can be automatically excluded from the assignment targets, and identifiers in a reactivation candidate state can be assigned restrictively under restriction conditions.
[0115] Meanwhile, the identifier state management module (250) may expand the identifier set by adding a new identifier to the identifier set storage module (270). The addition of a new identifier can be performed, for example, by the operator’s input of a new identifier registration through the operator terminal (130), and the added new identifier can be stored in the identifier set storage module (270) along with a seed attribute and included in the assignment target in a subsequent round.
[0116] Through the above state transition operations, the lifespan of limited identifier resources can be dynamically managed based on accumulated activity data.
[0117] The identity mapping storage module (280) can store a correspondence relationship between an identifier and the participant's real name information. Here, the participant's real name information may include, for example, one or more of the participant's real name, identity verification information, contact information, or identifiable personal identification information.
[0118] The identity mapping storage module (280) may be provided in a storage area that is logically or physically separated from the cumulative profile storage module (260). In one embodiment, the identity mapping storage module (280) and the cumulative profile storage module (260) may be physically separated by being placed on different physical servers or different database instances. In another embodiment, the identity mapping storage module (280) and the cumulative profile storage module (260) may be logically separated by being separated into different logical partitions or areas with different access control policies applied, even if they are provided on the same physical storage medium.
[0119] Additionally, the identity mapping storage module (280) may be configured to be separated from the cumulative profile storage module (260) in terms of access rights, encryption keys, or access interfaces. For example, access rights to the identity mapping storage module (280) may be granted to a different user or role than access rights to the cumulative profile storage module (260). Furthermore, data stored in the identity mapping storage module (280) may be encrypted with a different encryption key than the data stored in the cumulative profile storage module (260), and access interfaces (e.g., APIs) for the two storage modules may be implemented separately.
[0120] The identifier determination module (220) can transmit the result of assigning a determined identifier (2500) to a participant to the identity mapping storage module (280), and the identity mapping storage module (280) can store the correspondence relationship between the determined identifier (2500) and the participant's real name information. Meanwhile, activity data generated while the participant is active in the user matching service is stored in the cumulative profile storage module (260) under a composite key (300) including an identifier key and a round identification value (320), so the participant's real name information may not be directly combined with the activity data itself.
[0121] According to this separate storage structure, the participant's real name information may not be directly exposed during the process of analyzing activity data or operating content. Additionally, even if unauthorized access to the cumulative profile storage module (260) occurs, the real name information may not be directly exposed unless additional access is made to the identity mapping storage module (280), thereby limiting the scope of impact of unauthorized access.
[0122] Furthermore, since the identifier is repeatedly assigned to different participants in each round, the activity data of multiple participants is accumulated in a many-to-one manner under the same identifier in the cumulative profile storage module (260), so that a de-identification effect can occur in which it is difficult to identify a specific participant based on the identifier alone. By combining the separate storage structure and the many-to-one accumulation structure in this way, the de-identification of the activity data itself and the separation of access paths to real-name information can be achieved together.
[0123] In one embodiment, the user matching service operating system (100) may further include an identity information disclosure scope control module. The identity information disclosure scope control module is a module that controls access to the identity mapping storage module (280) and can control the scope of disclosure of real name information stored in the identity mapping storage module (280) when a preset disclosure condition is satisfied.
[0124] The disclosure conditions may include, for example, the fulfillment of mutual consent inputs between participants, the occurrence of a matching success event, the elapsed of a certain number of rounds, or an operator's disclosure consent input through the operator terminal (130). For example, the identity information disclosure scope control module may mutually disclose real name information for two participants only when a final match or a pre-set matching success event occurs between two participants, and the two participants perform an input agreeing to mutual real name disclosure through the user terminal (110). In another embodiment, the identity information disclosure scope control module may allow access to the identity mapping storage module (280) only when there is an operator's disclosure consent input through the operator terminal (130).
[0125] The identity information disclosure scope control module may be an optional component of the user matching service operating system (100).
[0126] FIG. 4 is a schematic flowchart illustrating a self-reinforcing closed-loop operation according to a disclosed embodiment.
[0127] Referring to FIG. 4, the user matching service operating system (100) can form a self-reinforcing closed loop by repeatedly performing suitability-based identifier assignment (S410), activity data collection (S420), many-to-one cumulative storage based on a composite key (300) (S430), and identifier profile update (S440) in each round.
[0128] The suitability-based identifier assignment (S410) may be an operation of calculating the suitability (2300) between the user information (2100) of a new participant and the identifier profile (2200) for each identifier, and assigning an identifier (2500) determined based on the calculated suitability (2300) to the new participant. The suitability-based identifier assignment (S410) may be performed by a suitability calculation module (210) and an identifier determination module (220).
[0129] Activity data collection (S420) may be an action of collecting activity data that occurs while a participant, whose identifier has been assigned by the suitability-based identifier assignment (S410), is active in the user matching service. Activity data collection (S420) may be performed by an activity data collection module (230).
[0130] The many-to-one cumulative storage (S430) based on the composite key (300) may be an operation of storing activity data collected by the activity data collection (S420) as an activity data record (330) in the cumulative profile storage module (260) based on a composite key (300) that includes an identifier key representing an identifier and a round identification value (320). Through the many-to-one cumulative storage (S430) based on the composite key (300), activity data records (330) of different participants for each round may be accumulated in a many-to-one manner under the same identifier.
[0131] The identifier profile update (S440) may be an operation of updating the identifier profile (2200) corresponding to the identifier based on the activity data record (330) accumulated by the composite key (300)-based many-to-one cumulative storage (S430). The identifier profile update (S440) may be performed by the cumulative profile storage module (260).
[0132] The identifier profile (2200) updated by the identifier profile update (S440) can be reverted as input data for the suitability-based identifier assignment (S410) in a subsequent round and used as a standard for calculating the suitability (2300) for new participants in the subsequent round. Thus, a self-reinforcing closed loop can be formed that returns from the suitability-based identifier assignment (S410) to the suitability-based identifier assignment (S410), through activity data collection (S420), composite key (300)-based many-to-one cumulative storage (S430), and identifier profile update (S440).
[0133] According to this self-reinforcing closed-loop structure, as activity data accumulates, the identifier profile (2200) can become more refined, and the refined identifier profile (2200) can be used to determine the identifier to be assigned to a new participant in a subsequent round. Additionally, since the activity data of the participant assigned through fit screening is accumulated under the same identifier, the consistency of the characteristics of the sample group accumulated under the identifier can be improved, and as a result, the identifier profile (2200) can have statistical characteristic values that show a consistent trend.
[0134] Additionally, the identifier profile (2200) may be provided as an initial operational reference value for a new participant to whom an identifier is assigned in a subsequent round. That is, at the time an identifier is assigned to a new participant, the identifier profile (2200) of the assigned identifier may be used as an initial operational reference value to determine one or more of the exposure conditions, operational priority, or interaction induction conditions for the new participant.
[0135] Here, the initial operation reference value can be used as a temporary correction standard from immediately after an identifier is assigned to a new participant until sufficient activity data for the new participant is accumulated. If the amount of activity data collected for a new participant exceeds a preset standard amount, the user matching service operation system (100) can decrease the reflection weight of the initial operation reference value and increase the reflection weight of the new participant's actual activity data.
[0136] An example of weight reduction and weight increase is described as follows. A user matching service operating system (100) may define a weight function with the accumulated amount of activity data for a new participant as a variable. The weight function may be defined such that, for example, as the accumulated amount increases, the weight for the initial operation reference value decreases monotonically and the weight for the new participant's actual activity data increases monotonically. For example, the weight function may be defined such that when the accumulated amount is 0, the weight for the initial operation reference value is 1 and the weight for the new participant's actual activity data is 0, and when the accumulated amount reaches a preset threshold amount, the weight for the initial operation reference value is 0 and the weight for the new participant's actual activity data is 1. The sum of the two weights may be normalized so that, for example, it always remains at 1. The form of the weight function may be implemented in various forms, such as linear decrease / increase, exponential decrease / increase, or step decrease / increase.
[0137] According to this weight reduction and weight increase mechanism, the identifier profile (2200) is not fixed as a permanent attribute of the new participant, but can only function as a temporary correction value until the new participant's actual activity data is accumulated. Thus, even in a situation where reference data accumulated for the new participant is absent, initial operating conditions based on a prior value formed through fit selection can be determined, while the new participant's actual characteristics can be reflected after the new participant's unique activity data has been sufficiently accumulated.
[0138] Hereinafter, embodiments of various content environments to which the present invention can be applied are described.
[0139] According to one embodiment, a user matching service operating system (100) may be applied to a couple matching service. The couple matching service may be an online or offline linked service that recruits multiple participants per round and provides interaction, selection, or matching results between participants.
[0140] In this embodiment, a new participant may input preliminary survey information, preference information, tendency information, or self-introduction information through their user terminal (110) and transmit it to the server (120). The suitability calculation module (210) calculates the suitability (2300) between the input user information (2100) and the identifier profile (2200) for each identifier, and the identifier determination module (220) may determine and assign an identifier (2500) to be assigned to the new participant based on the calculated suitability (2300).
[0141] A participant assigned an identifier can perform activities such as exchanging messages, video calls, expressing interest, or making selections with other participants in the couple matching service, and an activity data collection module (230) can collect the corresponding activity data. The collected activity data can be accumulated and stored in a cumulative profile storage module (260) under a composite key (300) of an identifier key and a round identification value (320), and an identifier profile (2200) can be updated from the accumulated activity data record (330). The updated identifier profile (2200) can be reused as a standard for calculating suitability (2300) when a new participant is recruited in a subsequent round.
[0142] The matching result may be notified to the participants through the user terminal (110), and if the two participants agree to mutual real-name disclosure, the real-name information stored in the identity mapping storage module (280) may be disclosed through the identity information disclosure scope control module. Meanwhile, the matching result may be calculated based on one or more of the selection input between participants, mutual approval input, operator input, or separate matching logic, and may not be directly determined by the identifier evaluation value.
[0143] In addition, in this embodiment, the matching type of the user matching service may be any one of 2-person matching, N-person matching, same-sex matching, or opposite-sex matching, and is not limited to any one.
[0144] According to another embodiment, the user matching service operating system (100) may be applied to a content environment in which a plurality of users engage through a repeatable identifier and activity data is accumulated in said identifier. This content environment may include, for example, one or more of matching content in the form of a game, metaverse, live streaming, social platform, virtual space, offline matching program, or broadcast program.
[0145] In one embodiment applied to a game environment, the identifier may be a character identifier assigned to a character within the game, and the identifier profile (2200) may include statistical characteristic values regarding the play patterns or collaboration patterns of multiple users who have passed through the character.
[0146] In one embodiment applied to a metaverse or virtual space environment, the identifier may be an identifier assigned to an avatar in the metaverse or a persona in the virtual space, and the identifier profile (2200) may include statistical characteristic values regarding the interaction patterns of multiple users using the avatar or persona.
[0147] In one embodiment applied to a live streaming or social platform environment, the identifier may be an identifier assigned to a user slot within a streaming channel or social platform, and the identifier profile (2200) may include statistical characteristic values regarding the content production patterns or viewer response patterns of multiple users who have used the slot.
[0148] In one embodiment applied to an offline matching program environment, the identifier may be a pseudonym or identification label assigned to a participant in an offline matching program, and the identifier profile (2200) may include statistical characteristic values regarding the activity patterns of a plurality of participants assigned the said pseudonym or identification label.
[0149] According to another embodiment, the user matching service operating system (100) can be applied to matching content in the form of a broadcast program.
[0150] In this embodiment, the identifier may be a pseudonym or character label assigned to a broadcast program performer. For example, a content operator may pre-register a pseudonym identifier to be assigned to a performer for each episode in a set of identifiers, and an identifier determination module (220) may determine a pseudonym identifier to be assigned to a performer based on the suitability (2300) between the user information (2100) of a new performer and the identifier profile (2200).
[0151] The pseudonym identifier determined by the identifier determination module (220) may be notified to the performer in various ways. In one embodiment, the pseudonym identifier may be notified to the performer in digital form through the user terminal (110). In another embodiment, the pseudonym identifier may be provided to the performer in the form of a physical or visual label containing the pseudonym identifier. The manner in which the pseudonym identifier is not notified to the performer is not limited to any one of these.
[0152] In this embodiment, the external response indicators of the activity data may be specified as the number of real-time votes from broadcast viewers, comment frequency, fluctuations in viewership ratings, or viewer response figures. The operator input values may be specified as the evaluation values of broadcast producers, tags indicating changes in relationships between performers (e.g., transition from a favorable stage to a conflict stage), or tags indicating the importance of broadcast editing (e.g., whether it corresponds to a key scene of the content).
[0153] When broadcast episodes are repeated and activity data accumulates under the same pseudonym identifier, the identifier profile (2200) corresponding to the same pseudonym identifier can be updated in a direction that exhibits a specific activity pattern or reaction pattern as episodes progress, thereby forming a character at the identifier level. When a pseudonym identifier is assigned to a new performer in a subsequent episode, the updated identifier profile (2200) can be reused as a standard for calculating the suitability (2300).
[0154] The above embodiments are merely illustrative of the applicability of the present disclosure, and the applicable content of the present disclosure is not limited to any one.
[0155] FIG. 5 is a schematic diagram showing the configuration of an exemplary computing device that can be used to implement the devices and methods according to the disclosed embodiments.
[0156] Referring to FIG. 5, the computing device (50) may include some or all of memory (510), a processor (520), storage (530), an input / output interface (540), and a communication interface (550). The computing device (50) may be a stationary computing device such as a desktop computer or server, as well as a mobile computing device such as a laptop computer or smartphone. The computing device (50) may include any specialized hardware accelerator capable of processing operations on an artificial intelligence model in an efficient manner. For example, the computing device (50) may include a graphic processing unit (GPU), a tensor processing unit (TPU), or a neural processing unit (NPU).
[0157] Memory (510) may store a program that enables the processor (520) to perform a method or operation according to various embodiments of the present disclosure. For example, the program may include a plurality of instructions executable by the processor (520), and the aforementioned method or operation may be performed by executing the plurality of instructions by the processor (520). Memory (510) may be a single memory or multiple memories. In this case, information required to perform a method or operation according to various embodiments of the present disclosure may be stored in a single memory or divided and stored in multiple memories. If memory (510) is composed of multiple memories, the multiple memories may be physically separated. Memory (510) may include at least one of volatile memory and non-volatile memory. Volatile memory includes Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc., and non-volatile memory includes flash memory, etc.
[0158] The processor (520) may include at least one core capable of executing at least one instruction. The processor (520) may execute instructions stored in memory (510). The processor (520) may be a single processor or multiple processors.
[0159] Storage (530) retains stored data even when power supplied to the computing device (50) is cut off. For example, storage (530) may include non-volatile memory and may include storage media such as magnetic tape, optical disc, or magnetic disc. A program stored in storage (530) may be loaded into memory (510) before being executed by the processor (520). Storage (530) may store a file written in a programming language, and a program generated from the file by a compiler, etc., may be loaded into memory (510). Storage (530) may store data to be processed by the processor (520) and / or data processed by the processor (520).
[0160] The input / output interface (540) may provide an interface with input devices such as a keyboard, mouse, etc. and / or output devices such as a display device, printer, etc. The speaker may trigger the execution of a program by the processor (520) through the input device and / or check the processing result of the processor (520) through the output device.
[0161] The communication interface (550) can provide access to an external network. The computing device (50) can communicate with other devices through the communication interface (550).
[0162] Memory (510), processor (520), storage (530), input / output interface (540), or communication interface (550) can communicate with each other via a system bus. The system bus can provide a data transmission path between components within the computing device (50). In one embodiment, the system bus may support PCI (Peripheral Component Interconnect), PCIe (PCI Express), or other bus protocols.
[0163] Each component of the device or method according to the present invention may be implemented in hardware or software, or in a combination of hardware and software. Additionally, the function of each component may be implemented in software, and a microprocessor may be implemented to execute the function of the software corresponding to each component.
[0164] Various embodiments of the systems and techniques described herein may be realized as digital electronic circuits, integrated circuits, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include being implemented as one or more computer programs executable on a programmable system. A programmable system comprises a storage system, at least one input device, and at least one programmable processor (which may be a special-purpose processor or a general-purpose processor) coupled to receive data and instructions from and transmit data and instructions to at least one output device. Computer programs (which are also known as programs, software, software applications, or code) include instructions for the programmable processor and are stored on a "computer-readable recording medium."
[0165] Computer-readable recording media include all types of recording devices in which data that can be read by a computer system is stored. Such computer-readable recording media may be non-volatile or non-transitory media such as ROM, CD-ROM, magnetic tape, floppy disk, memory card, hard disk, magneto-optical disk, and storage device, and may also include transitory media such as data transmission media. Additionally, computer-readable recording media may be distributed across networked computer systems, and computer-readable code may be stored and executed in a distributed manner.
[0166] Not all blocks illustrated in the block diagrams of this specification are essential components, and some blocks included in other embodiments may be added, changed, or deleted. The components illustrated in the block diagrams represent functionally distinct elements, and one or more components may be implemented in a form that integrates with one another in an actual physical environment. It will be readily understood by those skilled in the art that the relative positions of the components may change in response to the performance or structure of the system.
[0167] Although the flowcharts and timing diagrams in this specification describe each process as being executed sequentially, this is merely an illustrative explanation of the technical concept of one embodiment of the present disclosure. In other words, a person skilled in the art to which one embodiment of the present disclosure belongs may modify and adapt the flowcharts and timing diagrams in various ways, such as changing the order described in the flowcharts and timing diagrams or executing one or more of the processes in parallel, without departing from the essential characteristics of one embodiment of the present disclosure; therefore, the flowcharts and timing diagrams are not limited to a chronological order.
[0168] The above description is merely an illustrative explanation of the technical concept of the present embodiment, and a person skilled in the art to which the present embodiment belongs would be able to make various modifications and variations within the scope of the essential characteristics of the present embodiment. Accordingly, the present embodiments are intended to explain, not limit, the technical concept of the present embodiment, and the scope of the technical concept of the present embodiment is not limited by these embodiments. The scope of protection of the present embodiment shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of the present embodiment.
Claims
Claim 1 A method for operating a user matching service using a suitability-based identifier, performed by a server including at least one processor, comprising: a step of storing a profile and a status value corresponding to each of a plurality of identifiers included in an identifier set; a step of receiving user information of a participant from a user terminal; a step of calculating a suitability between the profile of each identifier and the user information based on the plurality of identifiers included in the identifier set and the user information; a step of determining an identifier corresponding to the participant based on the calculated suitability; a step of assigning the determined identifier to the participant; a step of collecting activity data of the participant assigned the determined identifier; a step of storing activity data of a plurality of participants corresponding to the determined identifier so that the data is accumulated and distinguished by the session identification value based on a composite key comprising an identifier key representing the determined identifier and a session identification value representing the session in which the participant participates; and a step of updating the profile and identifier evaluation value of the determined identifier based on the accumulated stored activity data. A method for operating a user matching service using a suitability-based identifier, comprising a process of updating the status value of the determined identifier based on the updated identifier evaluation value, wherein the updated profile is used for subsequent suitability calculation. Claim 2 A method for operating a user matching service using a suitability-based identifier, wherein, in claim 1, the identifier is a content character identifier that can be repeatedly assigned to different participants of different rounds in a user matching service, and the profile is calculated based on the activity data of multiple participants to whom the identifier is assigned. Claim 3 A method for operating a user matching service using a suitability-based identifier, wherein, in claim 1, the user information includes one or more of pre-survey information, preference information, propensity information, role tags, self-introduction information, selection behavior characteristics, interaction style information, or content operation suitability information. Claim 4 A method for operating a user matching service using a fitness-based identifier, wherein the process of calculating the fitness is based on one or more of the similarity, distance value, weighted sum score, condition matching rate, or output value of a classification model between the user information and the profile. Claim 5 A method for operating a user matching service using a suitability-based identifier, wherein the activity data includes one or more of an external response indicator, a participant activity indicator, a matching result indicator, or an operator input value, in accordance with claim 1. Claim 6 A method for operating a user matching service using a suitability-based identifier, wherein, in claim 1, the process of calculating the suitability includes the process of calculating the suitability for an active identifier among a plurality of identifiers included in the set of identifiers. Claim 7 A method for operating a user matching service using a suitability-based identifier according to claim 1, wherein the process of determining the identifier determines the identifier based on one or more of a seed attribute previously assigned to the identifier or an initial standard received from an operator terminal when the profile is not formed on the identifier, and determines the identifier based on the suitability when activity data is accumulated on the identifier in an amount greater than a standard amount and the profile is formed. Claim 8 A method for operating a user matching service using a suitability-based identifier, wherein, in claim 1, at the time of assigning the determined identifier to the participant, the profile of the determined identifier is provided as an initial operational reference value for determining one or more of exposure conditions, operational priorities, or interaction induction conditions for the participant. Claim 9 A method for operating a user matching service using a suitability-based identifier, wherein, in claim 8, when the amount of activity data collected for the participant exceeds a reference amount, the reflection weight of the initial operation reference value is reduced and the reflection weight of the participant's activity data is increased. Claim 10 A method for operating a user matching service using a suitability-based identifier according to claim 1, further comprising the process of storing the correspondence relationship between the identifier and the real name information of the participant in an identity mapping storage module, wherein the identity mapping storage module is provided in a storage area that is logically or physically separated from the cumulative profile storage module in which the activity data is stored. Claim 11 A user matching service operating system utilizing a suitability-based identifier comprises: a user terminal; and a server that communicates with the user terminal and includes at least one processor and at least one memory for storing instructions, wherein when the instructions are executed by the at least one processor, the processor comprises: a process of storing a profile and a status value corresponding to each of a plurality of identifiers included in an identifier set; a process of receiving user information of a participant from the user terminal; a process of calculating a suitability between the profile of each identifier and the user information based on the plurality of identifiers included in the identifier set and the user information; a process of determining an identifier corresponding to the participant based on the calculated suitability; a process of assigning the determined identifier to the participant; a process of collecting activity data of the participant assigned the determined identifier; a process of storing activity data of a plurality of participants corresponding to the determined identifier so that the data is accumulated and distinguished by the session identification value based on a composite key including an identifier key representing the determined identifier and a session identification value representing the session in which the participant participates; and a process of updating the profile and identifier evaluation value of the determined identifier based on the accumulated stored activity data. A user matching service operating system using a suitability-based identifier, wherein the process of updating the status value of the determined identifier is performed based on the updated identifier evaluation value, and the updated profile is used for subsequent suitability calculation. Claim 12 An identifier data management method performed by a server comprising at least one processor, comprising: a process of storing a profile and a status value corresponding to each of a plurality of identifiers included in an identifier set; a process of collecting activity data of a participant assigned an identifier; a process of storing activity data of a plurality of participants corresponding to the assigned identifier so that the data is distinguished by the session identification value and accumulated based on a composite key comprising an identifier key representing the assigned identifier and a session identification value representing the session in which the participant participates; a process of updating the profile and identifier evaluation value of the assigned identifier based on the accumulated stored activity data; and a process of updating the status value of the assigned identifier based on the updated identifier evaluation value, wherein the updated profile is used for subsequent identifier assignment. Claim 13 A method for managing identifier data according to claim 12, wherein the profile is a multidimensional vector comprising one or more of the mean value, variance value, quantile value, frequency value, ratio value, trend value, selection pattern value, or response pattern value as components. Claim 14 delete Claim 15 In claim 12, the process of updating the status value is to transition the status value of the assigned identifier to an inactive state when the identifier evaluation value is below a reference value, or when the increase of the identifier evaluation value stagnates for more than a reference number of cycles. Claim 16 In claim 12, the process of updating the status value is an identifier data management method that, for an identifier in an inactive state, transitions the status value of the identifier to a reactivation candidate state when one or more of the following are satisfied: an operator's approval input, the elapsed waiting period maintained in an inactive state, or a change in external conditions. Claim 17 In claim 16, the process of updating the state value is an identifier data management method in which, when the identifier evaluation value calculated from activity data collected after the identifier of the reactivation candidate state is assigned to a participant under a preset restriction condition satisfies a reference condition, the state value of the identifier is transferred to an active state. Claim 18 An identifier data management method according to claim 12, further comprising the process of selecting the identifier as a target for assignment when the status value of the assigned identifier is in an active state, and excluding the identifier from the target for assignment when the status value is in an inactive state. Claim 19 In claim 12, the process of updating the status value is an identifier data management method that updates the status value based on one or more of the identifier evaluation value or the number of unused iterations of the assigned identifier.
Citation Information
Patent Citations
System for protecting personal data
US20120110677A1
How to create a user profile and identify suggestions for the user's next choice
JP2005536814A
Game system, game device, article for game and program
JP2018114326A
Device for personalized curation using persona matching and method thereof
KR1020210121706A
System and method for dis-identifying sensitive information and associated records
US20050283620A1
