Method and appratus for analyzing traveler travel propensity based on artificial intelligence

Abstract

The present disclosure relates to a method for an electronic device to identify a user's travel tendency according to one embodiment and an electronic device to perform the same. A method for an electronic device to identify a user's travel tendency according to one embodiment may include: a step of providing a simulation including a plurality of queries for identifying the user's travel tendency; a step of acquiring response data including responses to the queries provided through the simulation; a step of transmitting the acquired response data to a server connected to the electronic device; a step of acquiring travel tendency content from the server, which is determined according to the tendency feature data output from a user travel tendency analysis artificial intelligence model that outputs tendency feature data representing the user's travel tendency when the response data is input; and a step of outputting the travel tendency content.

Description

Technology Field

[0001] The present disclosure relates to a method and apparatus for analyzing a traveler's travel tendencies based on artificial intelligence. More specifically, it relates to a method and apparatus for identifying a user's travel tendencies based on travel experience big data. Background Technology

[0002] With the spread of solo and spontaneous travel cultures, the demand for travel recommendation services based on travel tendencies and preferences is increasing. While general travel recommendation technologies may be suitable for situations involving high traffic and travel data, the travel industry is characterized by a low volume of new travelers and low traffic.

[0003] Therefore, although technologies utilizing conventional artificial intelligence to recommend travel content have been disclosed, they are not suitable for the travel industry with low traffic due to the difficulty in securing training data for accurate travel content recommendations. Furthermore, most travel recommendation technologies fail to build sufficient training databases due to low traffic, resulting in limitations in recommending travel content suitable for user preferences.

[0004] In addition, conventional travel recommendation technologies utilizing artificial intelligence have the problem that the objectivity and reliability of the training data used are not guaranteed, and not only is it impossible to perfectly consider various factors that affect travel, but there are also limitations in that they cannot reflect the phenomenon where a traveler's tendencies and preferences change depending on the travel season, type of companions, etc.

[0005] Therefore, in the travel industry with low traffic, there is a need to analyze users' travel preferences and develop travel content recommendation technologies suitable for those preferences. Prior art literature

[0006] Korean Registered Patent No. 2236546 The problem to be solved

[0007] According to one embodiment, a method for identifying a user's travel tendencies and an electronic device for performing the same may be provided.

[0008] According to one embodiment, a method for training an artificial intelligence model for analyzing a user's travel tendencies and an electronic device for performing the same may be provided. means of solving the problem

[0009] According to one embodiment, as a technical means for achieving the technical task described above, a method for an electronic device to identify a user's travel tendency may include: providing a simulation including a plurality of queries for identifying the user's travel tendency; acquiring response data including responses to the queries provided through the simulation; transmitting the acquired response data to a server connected to the electronic device; acquiring travel tendency content from the server, which is determined according to the tendency feature data output from a user travel tendency analysis artificial intelligence model that outputs tendency feature data representing the user's travel tendency when the response data is input; and outputting the travel tendency content.

[0010] According to another embodiment as a technical means for achieving the technical problem described above, an electronic device for identifying a user's travel tendency may be provided, comprising: a network interface; a memory for storing one or more instructions; and at least one processor for executing the one or more instructions; wherein the at least one processor, by executing the one or more instructions, provides a simulation including a plurality of queries for identifying the user's travel tendency, acquires response data including responses to the queries provided through the simulation, transmits the acquired response data to a server connected to the electronic device, and acquires travel tendency content determined according to the tendency feature data output from a user travel tendency analysis artificial intelligence model that outputs tendency feature data representing the user's travel tendency when the response data is input, and outputs the travel tendency content.

[0011] According to another embodiment as a technical means for achieving the technical task described above, a computer-readable recording medium may be provided that stores a program for performing a method, wherein the method comprises: providing a simulation including a plurality of queries for identifying the travel tendency of a user by an electronic device; obtaining response data including responses to the queries provided through the simulation; transmitting the obtained response data to a server connected to the electronic device; obtaining travel tendency content from the server, which is determined according to the tendency feature data output from a user travel tendency analysis artificial intelligence model that outputs tendency feature data representing the travel tendency of the user when the response data is input; and outputting the travel tendency content. Effects of the invention

[0012] According to one embodiment, by using an artificial intelligence model for analyzing user travel tendencies, the user's travel tendencies can be accurately identified with only a small number of questions.

[0013] According to one embodiment, the accuracy of an artificial intelligence model for analyzing traveler travel trends in a low-traffic travel industry sector can be improved.

[0014] According to one embodiment, the travel tendencies of travelers can be accurately identified based on the construction of training data. Brief explanation of the drawing

[0015] FIG. 1 is a diagram schematically illustrating the process of identifying a user's travel tendency by an electronic device for identifying a user's travel tendency according to one embodiment and a user's travel tendency analysis system including the same. FIG. 2 is a diagram illustrating the process of an electronic device according to one embodiment acquiring response data through simulation. FIG. 3 is a diagram illustrating user travel tendency content provided by an electronic device according to one embodiment. FIG. 4 is a flowchart of a method for an electronic device according to one embodiment to identify a user's travel tendency. FIG. 5 is a diagram illustrating the structure of an artificial intelligence model for analyzing user travel tendencies according to one embodiment. FIG. 6 is a diagram illustrating the input and output values ​​of an artificial intelligence model for analyzing user travel tendencies according to one embodiment. FIG. 7 is a flowchart illustrating a specific process in which an electronic device according to one embodiment transmits feedback information to a server. FIG. 8 is a flowchart of a method for an electronic device according to one embodiment to train an artificial intelligence model for analyzing user travel tendencies. FIG. 9 is a flowchart of a specific method for an electronic device according to one embodiment to build an artificial intelligence model for analyzing user travel tendencies. FIG. 10 is a flowchart of a specific method for an electronic device according to one embodiment to train an artificial intelligence model for analyzing user travel tendencies. FIG. 11 is a diagram showing an example of a user travel tendency variable used by an electronic device according to one embodiment. FIG. 12 is a block diagram of an electronic device according to one embodiment. FIG. 13 is a block diagram of an electronic device according to another embodiment. FIG. 14 is a block diagram of a server according to one embodiment. FIG. 15 is a flowchart illustrating a method for identifying a user's travel tendencies by having an electronic device and a server interact with each other according to one embodiment. Specific details for implementing the invention

[0016] The terms used in this specification will be briefly explained, and the present disclosure will be described in detail.

[0017] The terms used in this disclosure have been selected to be as widely used and general as possible, taking into account their functions within this disclosure; however, these terms may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant description of the invention. Therefore, terms used in this disclosure should be defined not merely by their names, but based on their meanings and the overall content of this disclosure.

[0018] When a part of a specification is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "...part" or "module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software.

[0019] Embodiments of the present disclosure are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present disclosure in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0020] FIG. 1 is a diagram schematically illustrating the process of identifying a user's travel tendency by an electronic device for identifying a user's travel tendency according to one embodiment and a user's travel tendency analysis system including the same.

[0021] According to one embodiment, the user travel tendency analysis system (10) acquires user response data, determines tendency feature data that identifies the user's travel tendency represented by the acquired user response data, and can output travel tendency content based on the tendency feature data. For example, the user travel tendency analysis system (10) can provide a user-customized travel recommendation service that analyzes the user's travel tendency, identifies characteristics of travel destinations acquired through big data, and recommends travel content by matching the identified characteristics of travel destinations with the user's travel tendency.

[0022] According to one embodiment, the user travel tendency analysis system (10) may include an electronic device (1000) and a server (2000). According to another embodiment, the user travel tendency analysis system (10) may include an electronic device (1000), a server (2000), and an electronic device (4000). Not limited to the examples described above, the user travel tendency analysis system (10) effectively analyzes the user's travel tendency through a simulation including a small amount of queries and can share the travel tendency content with another electronic device or a server connected to another electronic device.

[0023] Although the electronic device (1000) and the server (2000) are depicted separately in the present specification, it is obvious that the entire process of identifying a user's travel tendencies or at least part thereof may be performed by the electronic device (1000), the server (2000), or by the interaction between the electronic device (1000) and the server (2000). Furthermore, according to one embodiment, the electronic device (1000) may correspond to a server (2000) device used to provide a user-customized travel recommendation service.

[0024] According to one embodiment, the electronic device (1000) may provide travel tendency content (104) based on information obtained based on user input (120). According to one embodiment, the electronic device (1000) may obtain response data based on user input (102). According to another embodiment, the electronic device (1000) may obtain response identification information (e.g., SURVEY ID or survey identification information) that uniquely identifies the response data along with the response data, and user information (e.g., age information, gender information, phone number information, personal information consent confirmation information, marketing information reception confirmation information), and may obtain the response identification information and user information after obtaining the response data.

[0025] When response data is obtained, the electronic device (1000) can output travel tendency content (104) determined based on the obtained response data. According to one embodiment, the travel tendency content (104) may include a character image representing the user's travel tendency, a character name, a text sequence including a plurality of sentence sequences to explain the travel tendency, and link information for viewing the travel tendency content. However, it is not limited to the above-described example, and the travel tendency content (104) may further include other information to represent the user's travel tendency.

[0026] According to one embodiment, the electronic device (1000) can execute a travel tendency analysis service that analyzes the user's travel tendency at S112 by linking with a server (2000), execute a simulation to obtain predetermined response data at S114, obtain user input through the simulation at S116, and at S118 transmit and receive not only the obtained user input but also travel tendency content obtained from the server or tendency data used to determine the travel tendency content.

[0027] According to one embodiment, the electronic device (1000) may be connected to a server (2000) via a network (3000). The electronic device (1000) may also be connected to another electronic device (4000) via the network (3000). For example, the user travel tendency analysis system (10) may identify travel compatibility by matching travel tendency content for users who use a user-customized travel recommendation service. According to one embodiment, the electronic device (1000) may output various travel content linked based on the identified travel tendency content by being linked with another electronic device (4000).

[0028] According to one embodiment, the server (2000) may store an artificial intelligence model (120). Although not illustrated in FIG. 1, the electronic device (1000) may also store an artificial intelligence model (120) used to determine travel propensity content. According to one embodiment, the artificial intelligence model (120) may include at least one of an STTI network, a PREDICT network (cluster identification network), and a TRIFIT network, but is not limited thereto. According to one embodiment, the user travel propensity analysis artificial intelligence model (120) may include a neural network-based network that classifies user propensity feature data using one or more types of clusters capable of clustering propensity feature data at different levels.

[0029] According to one embodiment, when response data is input, the STTI network may output user travel tendency feature information (e.g., comprehensive travel tendency feature information, detailed travel tendency feature information) including feature values ​​for each user travel tendency variable, and the cluster identification network may include neural network-based networks that output identification information of the cluster to which the user travel tendency feature information belongs when user travel tendency feature information is input. According to one embodiment, the TRIFIT network may be a network that acquires social data including tourist places for place feature analysis and outputs travel place feature data when the acquired social data (122) is input.

[0030] According to one embodiment, the server (2000) can obtain response data (122) from the electronic device (1000) and determine tendency feature data (124) by inputting the obtained response data into the user travel tendency analysis artificial intelligence model (120). The server (2000) can generate travel tendency content (104) based on the tendency feature data (124). According to one embodiment, the server (2000) can generate travel tendency content using a module that generates travel tendency content when tendency feature data is input. The server (2000) can transmit the travel tendency content to the electronic device (1000). For example, the server (2000) can generate a plurality of clusters (125) by clustering user tendency feature data obtained from the artificial intelligence model (120), determine cluster identification information to which the user tendency feature data according to the response data belongs, and determine travel tendency content based on the determined cluster identification information.

[0031] FIG. 2 is a diagram illustrating the process of an electronic device according to one embodiment acquiring response data through simulation.

[0032] According to one embodiment, the electronic device (1000) may provide a simulation including a plurality of queries (210, 220) for identifying a user's travel tendency. According to one embodiment, the electronic device (1000) may provide a plurality of queries to which a predetermined number of responses according to a predetermined priority is assigned, acquire response data including responses to the queries, and transmit the acquired response data to a server. The simulation provided by the electronic device (1000) may not provide the next step of the query if the predetermined number of responses is not selected.

[0033] According to one embodiment, the electronic device (1000) may transmit to the server whenever response data obtained for each query provided through the simulation is obtained, or it may transmit the obtained queries together to the server. According to one embodiment, the electronic device (1000) may obtain dropout rate information regarding at least one of the time required to obtain responses to the queries and the number of respondents to the queries, and transmit the dropout rate information together with the response data to the server. The server (2000) may identify queries that the user dropped during the simulation process based on the dropout rate information. A user travel tendency analysis system (10) including at least one of the electronic device or the server may identify the user's dropout tendency based on the dropout rate information and change the content of the queries constituting the simulation based on the identified user's dropout tendency.

[0034] According to one embodiment, the electronic device (1000) provides queries and then outputs an interface for obtaining user information (240), and can obtain user information including at least one of gender information, age information, phone number information, information confirming consent to personal information, and information confirming receipt of marketing information through the interface. The electronic device (1000) can transmit the user information to a server (2000) along with response data.

[0035] According to one embodiment, the plurality of queries provided by the electronic device (1000) may be provided according to the order in which the actual journey proceeds. Additionally, the electronic device (1000) may determine context information (242) regarding the order of the journey based on the order in which the actual journey proceeds, and may additionally provide story content (241) according to the context information among the plurality of queries.

[0036] FIG. 3 is a diagram illustrating user travel tendency content provided by an electronic device according to one embodiment.

[0037] According to one embodiment, the user travel tendency content provided by the electronic device (1000) may include at least one of character information including the name (312) of a character representing the user's travel tendency and an image (310) of the character, a text sequence (320) describing the user's travel tendency, or link information for viewing the travel tendency content. According to another embodiment, the user travel tendency content may further include the user's detailed travel tendency and visual content for easily comparing the difference between the user's detailed travel tendency and the average travel tendency of a group. According to one embodiment, the user's detailed travel tendency may be determined based on a predetermined travel tendency variable (332, e.g., a comprehensive travel tendency variable, a detailed travel tendency variable, a specific detailed travel tendency variable, etc.).

[0038] According to one embodiment, a text sequence (320) describing a user's travel tendency may include a plurality of sentence sequences (322, 324). According to one embodiment, character information is determined based on comprehensive travel tendency cluster label information described below, and one or more sentence sequences or sentence sequences included in the text sequence may be determined based on specific detailed travel tendency cluster label information described below.

[0039] FIG. 4 is a flowchart of a method for an electronic device according to one embodiment to identify a user's travel tendency.

[0040] In S410, the electronic device (1000) may provide a simulation including multiple queries to identify the user's travel tendencies. The electronic device (1000) may not only provide a small number of queries, but also induce users to complete the simulation by having users respond to the simulation in the same order as they would travel in the actual travel sequence.

[0041] In S420, the electronic device (1000) can obtain response data including responses to the above-mentioned queries provided through simulation. Since the process by which the electronic device (1000) obtains the response data is as described in detail in FIG. 2, a detailed description is omitted. In S430, the electronic device (1000) can transmit the obtained response data to a server connected to the electronic device. For example, the electronic device (1000) may transmit user information and survey identification information (e.g., response identification information) for uniquely identifying the response data to the server along with the response data.

[0042] In S440, the electronic device (1000) can obtain travel tendency content from the server, which is determined according to the tendency feature data output from a user travel tendency analysis artificial intelligence model that outputs tendency feature data representing the user's travel tendency when response data is input. According to another example, the electronic device (1000) may also directly determine the user travel tendency content by pre-storing the user travel tendency analysis artificial intelligence model and inputting response data into the pre-stored user travel tendency analysis artificial intelligence model.

[0043] Additionally, although not illustrated in FIG. 4, the electronic device (1000) may provide feedback queries to obtain feedback on travel tendency content and obtain Likert scales for said feedback queries as feedback information on said travel tendency content. According to one embodiment, the electronic device (1000) or the server (2000) may change the content of the simulation based on the obtained feedback information, or retrain the user travel tendency analysis AI model by modifying and updating the weights of certain layers within the user travel tendency analysis AI model or STTI network.

[0044] Hereinafter, the process of determining travel tendency content obtained by the electronic device (1000) from the server will be explained in detail. According to one embodiment, the server (2000) may input response data transmitted from the electronic device into a pre-trained user travel tendency analysis artificial intelligence model. According to one embodiment, the user travel tendency analysis artificial intelligence model may include at least one of an STTI network or a cluster identification network.

[0045] According to one embodiment, when response data is input, the STTI network can output user travel tendency feature information including feature values ​​for each of the user's travel tendency variables. According to one embodiment, the STTI network may include neural network-based numerical computation networks that output detailed travel tendency feature information including feature values ​​for detailed travel tendency variables among the user's travel tendency variables, and comprehensive travel tendency feature information including feature values ​​for comprehensive travel tendency variables representing some of the detailed travel tendency variables.

[0046] According to one embodiment, when user travel tendency feature information output from an STTI network is input, a cluster identification network (e.g., a PREDICT model) may output user travel tendency cluster label information to identify the cluster to which the user travel tendency feature information belongs according to the response data among a plurality of clusters representing the user's travel tendency. According to one embodiment, the cluster identification network may be referred to as a PREDICT model. According to one embodiment, the cluster identification network may include neural network-based numerical computation networks that output cluster label information indicating whether the user travel tendency feature information output from the STTI network belongs to which cluster among a plurality of clusters.

[0047] More specifically, a cluster identification network according to one embodiment may include neural network-based identification networks that output comprehensive travel tendency cluster label information and specific detailed travel tendency cluster label information. For example, a neural network-based identification network that outputs comprehensive travel tendency cluster label information may output comprehensive travel tendency cluster label information that identifies one cluster to which user travel tendency feature information according to response data belongs, among comprehensive travel tendency clusters regarding comprehensive travel tendency arranged in a multidimensional space defined based on comprehensive travel tendency variables.

[0048] In addition, a neural network-based identification network that outputs specific detailed travel tendency cluster label information according to one embodiment can output specific detailed travel tendency cluster label information that identifies one cluster to which user travel tendency feature information according to the response data belongs among the detailed travel tendency clusters regarding the detailed travel tendency, which are generated for each comprehensive travel tendency cluster and arranged in a multidimensional space defined based on specific detailed travel tendency variables.

[0049] According to one embodiment, the comprehensive travel tendency clusters can be generated by clustering user travel tendency characteristic information at a first level in a multidimensional space that includes each of the comprehensive travel tendency variables as a reference axis. Additionally, according to one embodiment, specific detailed travel tendency clusters can be generated by clustering each user travel tendency characteristic information corresponding to the comprehensive travel tendency clusters at a second level in a multidimensional space defined based on specific detailed travel tendency variables. The user travel tendency analysis artificial intelligence model used by the electronic device (1000) or server (2000) according to the present disclosure can accurately identify the user's travel tendency by classifying the user travel tendency characteristic information using two different types of clusters.

[0050] For example, an electronic device (1000) or a server (2000) can generate first type clusters (e.g., comprehensive travel tendency clusters) for clustering user travel tendency feature information at a first level based on specific comprehensive travel tendency variables representing specific detailed travel tendency variables, and determine the number of comprehensive travel tendency clusters by applying a clustering algorithm (e.g., GMM) to comprehensive travel tendency feature information including feature values ​​for each comprehensive travel tendency variable. The electronic device (1000) or the server (2000) determines comprehensive travel cluster label information (e.g., identification information indicating whether it belongs to a specific comprehensive travel tendency cluster) by clustering user travel tendency feature information at a first level using the comprehensive tendency clusters according to the determined number of comprehensive travel tendency clusters.

[0051] For example, an electronic device (1000) or a server (2000) can determine the number of specific detailed travel tendency clusters by applying a clustering algorithm (e.g., GMM) to specific detailed travel tendency feature information that includes feature values ​​of specific detailed travel tendency variables among the specific travel tendency variables, where the degree of discrimination of user travel tendency is identified as being above a threshold. The electronic device (1000) or the server (2000) determines specific detailed travel tendency cluster label information (e.g., identification information indicating whether it belongs to a specific detailed travel tendency cluster) by using the specific detailed travel tendency clusters according to the determined number of specific detailed travel tendency clusters and clustering the user travel tendency feature information belonging to each comprehensive tendency cluster again to a second level. An electronic device (1000) using a user travel tendency analysis artificial intelligence model that performs such clustering can improve the identification accuracy of user travel tendency, unlike conventional user travel tendency analysis.

[0052] FIG. 5 is a diagram illustrating the structure of an artificial intelligence model for analyzing user travel tendencies according to one embodiment.

[0053] FIG. 6 is a diagram illustrating the input and output values ​​of an artificial intelligence model for analyzing user travel tendencies according to one embodiment.

[0054] With reference to FIGS. 5 and 6, the structure and operation of the user travel tendency analysis artificial intelligence model used by the electronic device (1000) will be explained in detail.

[0055] According to one embodiment, the user travel tendency analysis artificial intelligence model (610) may include at least one of an STTI network (630) or a cluster identification network (640). When response data (612) is input to the user travel tendency analysis artificial intelligence model (610), the model may output tendency feature data (622) representing the user's travel tendency. According to one embodiment, the response data (612) may include response identification information (614) and user information (616). According to one embodiment, the tendency feature data (622) may include user travel tendency feature information (624) containing characteristic values ​​for each user travel tendency variable, and user travel tendency cluster label information (626).

[0056] According to one embodiment, the response identification information (614) may include information that uniquely identifies response data containing responses to queries provided through a simulation. According to one embodiment, the response identification information may identify each response to each query, or it may include information for uniquely identifying response data containing responses to each query or response data obtained by completing one simulation. According to one embodiment, the user information (616) may include personal information of the user, such as the user's gender, age, and phone number.

[0057] According to one embodiment, user travel tendency characteristic information (624) may include detailed travel tendency characteristic information including characteristic values ​​for each detailed travel tendency variable and comprehensive travel tendency characteristic information including characteristic values ​​for each comprehensive travel tendency variable. According to one embodiment, user travel tendency cluster label information (626) may include comprehensive travel tendency cluster label information identifying one cluster among comprehensive travel tendency clusters regarding comprehensive travel tendency arranged in a multidimensional space defined based on comprehensive travel tendency variables, and specific detailed travel tendency cluster label information identifying one cluster among detailed travel tendency clusters regarding detailed travel tendency arranged in a multidimensional space defined based on specific detailed travel tendency variables. According to one embodiment, detailed travel tendency clusters may be generated for each comprehensive travel tendency cluster, but are not limited thereto.

[0058] Referring to FIG. 5, an STTI network (630) used by an electronic device (1000) is illustrated. According to one embodiment, when response data is input into the STTI network model (630), among the travel tendency variables, detailed travel tendency variables (541) (V 11 ~V nn A detailed travel tendency variable numerical computation network (632) that outputs detailed travel tendency feature information including ) star feature values, and comprehensive travel tendency variables (545) (G) representing some detailed travel tendency variables among the travel tendency variables. 1, It may include a comprehensive travel tendency variable numerical calculation network (634) that outputs comprehensive travel tendency feature information including feature values ​​for G2, G3, G4, G5, G6).

[0059] According to one embodiment, the STTI network (630) may include an input layer (510) when response data is input, an STTI layer (520) that outputs feature values ​​for each user travel tendency variable through numerical operation on the response data, and an output layer (530) that outputs comprehensive travel tendency feature information including feature values ​​for each comprehensive travel tendency variable when detailed travel tendency feature information including feature values ​​for each user travel tendency variable is input. However, it is not limited to the example described above.

[0060] According to one embodiment, the input layer (510) can perform a process of preprocessing response data. According to one embodiment, the STTI layer (520) can perform numerical operations to convert the response data into travel tendency variables (V). According to one embodiment, the output layer (530) can identify a preset number (e.g., 6) of category groups by grouping the travel variables (V), and output variables for each identified category group and a predetermined feature value (e.g., sequence) corresponding thereto.

[0061] According to one embodiment, the input and output values ​​of each layer within the STTI network model may be provided in a predetermined sequence form (or vector). Additionally, according to one embodiment, the input and output values ​​of each layer within the STTI network model may be provided in a predetermined vector form. Boxes (540, 542) in FIG. 5 represent the correlations of each travel tendency variable, and variable (544) may represent a variable classified into six category groups. The STTI network model according to the present disclosure may be trained in an unsupervised manner.

[0062] According to another example, the STTI network (630) may include neural network-based numerical computation networks that, when training response data is input during the training phase of the user travel tendency analysis artificial intelligence model, output training detailed travel tendency feature information including feature values ​​for each detailed travel tendency variable among the user's travel tendency variables, and training comprehensive travel tendency feature information including feature values ​​for each comprehensive travel tendency variable representing some of the detailed travel tendency variables.

[0063] According to one embodiment, the cluster identification network (640) may include a comprehensive travel tendency cluster identification network (642) and a specific detailed travel tendency cluster identification network (644). According to another example, the cluster identification network (60) may include learning comprehensive travel tendency cluster label information that identifies one cluster to which learning user travel tendency feature information according to the learning response data belongs among comprehensive travel tendency clusters regarding comprehensive travel tendency arranged in a multidimensional space defined based on comprehensive travel tendency variables, and learning specific detailed travel tendency cluster label information that is generated for each comprehensive travel tendency cluster and outputs one cluster to which learning user travel tendency feature information according to the learning response data belongs among detailed travel tendency clusters regarding detailed travel tendency in a multidimensional space defined based on specific detailed travel tendency variables.

[0064] For example, the cluster identification network (640) can obtain the output value of the STTI network and output user travel tendency cluster label information based on the obtained output value. More specifically, the cluster identification network (640) can obtain user travel tendency feature information including detailed travel tendency feature information and comprehensive travel tendency feature information output from the STTI network, and output user travel tendency cluster label information to identify the location of the cluster to which the obtained user travel tendency feature information belongs.

[0065] According to one embodiment, the comprehensive travel tendency cluster identification network (642) may output comprehensive travel tendency cluster label information that identifies one cluster to which user travel tendency feature information output from the STTI network belongs as response data is input among the comprehensive travel tendency clusters. According to another example, the comprehensive travel tendency cluster identification network may obtain comprehensive travel tendency feature information, an average data set per comprehensive travel tendency cluster, and a standard deviation data per comprehensive travel tendency cluster as inputs, and output comprehensive travel tendency cluster label information according to the obtained input values.

[0066] According to one embodiment, the specific detailed travel tendency cluster identification network (644) may output specific detailed travel tendency cluster label information that identifies one cluster to which user travel tendency feature information output from the STTI network belongs as response data is input, among the detailed travel tendency clusters regarding the detailed travel tendency that are arranged in a multidimensional space defined based on specific detailed travel tendency variables among the detailed travel tendency variables for which the degree of discrimination of user travel tendency is determined to be above a threshold. According to another example, the specific detailed travel tendency cluster identification network (644) may obtain specific detailed travel tendency feature information (information including feature values ​​for specific detailed travel tendency variables among the detailed travel tendency variables for which the degree of discrimination of travel tendency is determined to be above a threshold), an average data set for each detailed travel tendency cluster, and standard deviation data for each detailed travel tendency cluster as inputs, and output specific detailed travel tendency cluster label information according to the obtained input values.

[0067] According to one embodiment, the STTI network, cluster identification network, or TRIFIT network model described herein may be a CNN (Convolutional Neural Network), DNN (Deep Neural Network), RNN (Recurrent Neural Network), RBM (Restricted Boltzmann Machine), DBN (Deep Belief Network), BRDNN (Bidirectional Recurrent Deep Neural Network), or Deep Q-Network, but is not limited thereto.

[0068] Hereinafter, the travel tendency variables (650) described in the present specification will be explained in detail. According to one embodiment, the user travel tendency variable (650) may include at least one of the comprehensive travel tendency variables (652), detailed travel tendency variables (654), or specific detailed travel tendency variables (656). For example, the detailed travel tendency variables (542) may include variables defined through a brainstorming process of factors that can influence travel using travel situation scenario data. The travel tendency variables used by the electronic device (1000) may have their correlations with situational behavior types determined in advance through simulation. The comprehensive travel tendency variables (652) may include one or more variables representing specific detailed travel tendency variables.

[0069] For example, the comprehensive travel tendency variables (G, 652) may include one or more detailed travel tendency variables (V, 654), and the detailed travel tendency variables may be dependent on or included in the comprehensive travel tendency variables. According to one embodiment, the electronic device (1000) may change the variables used for user travel tendency analysis by adding or deleting them based on the distribution pattern of feature values ​​for each comprehensive travel tendency variable and detailed travel tendency variable as the output value of the user travel tendency analysis artificial intelligence model, if an issue lacking discriminability is identified by the distribution pattern showing a form concentrated on one side, or if an issue lacking discriminable diversity is identified by the distribution pattern showing a form that is uniform or distributed in a normal distribution pattern.

[0070] According to one embodiment, the specific detailed travel tendency variable (S, 656) may include certain detailed travel tendency variables among the detailed travel tendency variables in which the degree of differentiation of user travel tendency is identified as being above a threshold. According to one embodiment, the specific detailed travel tendency variable may include certain detailed travel tendency variables among the detailed travel tendency variables included in the comprehensive travel tendency variables in which the degree of differentiation of user travel tendency is identified as being above a threshold. According to one embodiment, at least one specific detailed travel tendency variable may be assigned to each comprehensive travel tendency variable, but is not limited thereto.

[0071] FIG. 7 is a flowchart illustrating a specific process in which an electronic device according to one embodiment transmits feedback information to a server.

[0072] In S710, the electronic device (1000) may provide feedback queries to obtain feedback on travel tendency content. In S720, the electronic device (1000) may obtain Likert scales for the feedback queries as feedback information on travel tendency content. In S730, the electronic device (1000) may transmit the feedback information to a server. According to one embodiment, the server (2000) or the electronic device (1000) may retrain at least one layer or at least one neural network-based network within the user travel tendency analysis artificial intelligence model by modifying and updating the weights based on the feedback information.

[0073] FIG. 8 is a flowchart of a method for an electronic device according to one embodiment to train an artificial intelligence model for analyzing user travel tendencies.

[0074] The method of training the user travel tendency analysis artificial intelligence model described in FIG. 8 may be performed by an electronic device (1000) or by a server (2000). In S810, the electronic device (1000) may build a user travel tendency analysis artificial intelligence model such that when predetermined design response data is input, design tendency feature data is output, based on the correlation between the behavioral type for each travel situation and the travel tendency variables regarding the user's travel tendency.

[0075] According to one embodiment, the electronic device (1000) may acquire design response data regarding behavioral types by travel situation for analyzing the user's travel tendency, and may construct a user travel tendency analysis artificial intelligence model such that when design response data is input based on the correlation between behavioral types by travel situation and travel tendency variables regarding the user's travel tendency, design tendency feature data is output. According to one embodiment, the design response data may include responses to questions obtained through a predetermined simulation targeting users via a survey prize event.

[0076] According to one embodiment, the operation of an electronic device (1000) constructing a user travel tendency analysis artificial intelligence model may include determining input data and output of the user travel tendency analysis artificial intelligence model, defining a training data system, and defining the structure of a neural network-based network within the user travel tendency analysis artificial intelligence model. In S820, the electronic device (1000) may train the user travel tendency analysis artificial intelligence model so that the boundaries of the clusters to which training tendency feature data, obtained by inputting training response data into the constructed user travel tendency analysis artificial intelligence model, belong become clear.

[0077] For example, the operation of an electronic device (1000) training an artificial intelligence model for analyzing user travel tendencies may include modifying and updating weights within the model through machine learning operations to provide a user-customized travel recommendation service based on a structure and input / output relationship determined during the construction phase.

[0078] FIG. 9 is a flowchart of a specific method for an electronic device according to one embodiment to build an artificial intelligence model for analyzing user travel tendencies.

[0079] In S910, the electronic device (1000) can construct an STTI network that outputs design user travel tendency feature information including feature values ​​for each user travel tendency variable when design response data is input. In S920, the electronic device (1000) can construct a cluster identification network that outputs design user travel tendency cluster label information that identifies the cluster to which the design user travel tendency feature information belongs among a plurality of clusters representing the user's travel tendency when design user travel tendency feature information is input. In S930, the electronic device (1000) can construct a neural network-based numerical computation network including the STTI network and the cluster identification network as the user travel tendency analysis artificial intelligence model.

[0080] In S940, the electronic device (1000) can modify the user travel tendency variables used in constructing the user travel tendency analysis artificial intelligence model by deleting or adding them based on the distribution pattern of the user travel tendency characteristic information for design. For example, if the electronic device (1000) determines that an issue lacking discriminability has occurred when the identified distribution pattern of the user travel tendency characteristic information for design is determined to be denser than a threshold relative to the reference space, it can change the list of user travel tendency variables used in constructing the user travel tendency analysis artificial intelligence model.

[0081] Additionally, according to one embodiment, the electronic device (1000) identifies the distribution pattern of user travel tendency characteristic information for design purposes, and if the identified distribution pattern is identified as all showing a uniform distribution pattern or distributed in a normal distribution pattern, it determines that an issue lacking discernible diversity has occurred and may change the list of user travel tendency variables used in constructing the user travel tendency analysis artificial intelligence model. In S950, the electronic device (1000) may reconstruct the user travel tendency analysis artificial intelligence model based on the changed user travel tendency variables. The electronic device (1000) according to the present disclosure can identify the user's travel tendency more finely and accurately by repeating S940 to S950.

[0082] FIG. 10 is a flowchart of a specific method for an electronic device according to one embodiment to train an artificial intelligence model for analyzing user travel tendencies.

[0083] In S1010, the electronic device (1000) can acquire learning response data. In S1020, the electronic device (1000) can acquire learning user travel tendency feature information, including the learning detailed travel tendency feature information and the learning comprehensive travel tendency feature information, from the STTI network by inputting the learning response data into the STTI network.

[0084] In S1030, the electronic device (1000) can determine the number of comprehensive travel tendency clusters for clustering the learning user travel tendency feature information according to a first level by applying a clustering algorithm (e.g., GMM, Gaussian Mixture Model) to the learning comprehensive travel tendency feature information. According to one embodiment, the clustering algorithm may be an unsupervised learning algorithm that groups individual data according to the same Gaussian distribution.

[0085] For example, the electronic device (1000) can determine the number of comprehensive travel tendency clusters for accurately classifying user travel tendency feature information at a first level based on at least one of the Silhouette score, the Davis Bouldin score, or the AIC (Akaike Information Criterion) / BIC (Bayesian Information Criterion). The electronic device (1000) trains the user travel tendency analysis AI model by modifying and updating weights within the user travel tendency analysis AI model so that clustering proceeds based on the determined number of comprehensive travel tendency clusters.

[0086] In S1040, when the number of comprehensive travel tendency clusters is determined, the electronic device (1000) can determine the number of specific detailed travel tendency clusters for clustering the learning user travel tendency feature information according to a second level by applying a clustering algorithm to the learning specific detailed travel tendency feature information, which includes the feature values ​​of the specific detailed travel tendency variables among the learning detailed travel tendency feature information, based on the determined number of comprehensive travel tendency clusters. The electronic device (1000) trains the user travel tendency analysis artificial intelligence model by modifying and updating the weights within the user travel tendency analysis artificial intelligence model so that detailed (e.g., according to the second level) clustering proceeds for each comprehensive travel tendency cluster based on the determined number of specific detailed travel tendency clusters.

[0087] For example, the electronic device (1000) can determine the number of specific detailed travel tendency clusters for accurately classifying user travel tendency feature information at a second level based on at least one of the Silhouette score, the Davis Bouldin score, or the AIC (Akaike Information Criterion) / BIC (Bayesian Information Criterion). Since the number of specific detailed travel tendency clusters is determined after the number of comprehensive travel tendency clusters is determined, the optimal number of specific detailed travel tendency clusters for classifying travel tendency feature information according to user response data by comprehensive travel tendency cluster may vary depending on the number of comprehensive travel tendency clusters.

[0088] According to one embodiment, the clusters used by the electronic device (1000) may include a comprehensive travel tendency cluster type and a specific detailed travel tendency cluster type, but are not limited thereto. The cluster (e.g., cluster) characteristics used by the electronic device (1000) may include the mean value and standard deviation of user travel tendency characteristic information based on response data included in the cluster. According to another example, the cluster characteristics may further include a Gaussian function (e.g., a normal distribution function) defined for each cluster in addition to the mean value and standard deviation.

[0089] In S1050, the electronic device (1000) can train the user travel tendency analysis artificial intelligence model so that the learning user travel tendency feature information is clustered based on the number of clusters according to the determined total travel tendency cluster number and the number of clusters according to the specific detailed travel tendency cluster number.

[0090] Additionally, although not illustrated in FIG. 10, according to one embodiment, the electronic device (1000) can acquire new response data different from the training response data. Additionally, the electronic device (1000) can acquire new tendency feature data from the user travel tendency analysis AI model by inputting the acquired new response data into the trained user travel tendency analysis AI model. The electronic device (1000) can identify whether there is a change in the cluster characteristics of the new tendency feature data group including the acquired new tendency feature data and the training tendency feature data. For example, the electronic device (1000) can identify a change in cluster characteristics based on the average value, standard deviation value, and the amount of change of the normal distribution function for each cluster, according to the addition of tendency feature data (e.g., travel tendency feature information including feature values ​​for each travel variable) according to the new response data.

[0091] When a change in cluster characteristics is identified, the electronic device (1000) can retrain the artificial intelligence model by repeating the above-described process S1030 to S1050 again to change the number of comprehensive travel tendency clusters and the number of specific detailed travel tendency clusters again, and by modifying and updating the weights within the user travel tendency analysis artificial intelligence model so that user travel tendency feature information according to the response data is clustered according to the first level and the second level based on the comprehensive travel tendency clusters according to the changed number of comprehensive travel tendency clusters and specific detailed travel tendency clusters according to the number of specific detailed travel tendency clusters.

[0092] As the electronic device (1000) according to the present disclosure repeats the process S1030 to S1050, the general travel tendency clusters used by the user travel tendency analysis AI model to classify travel tendency feature information based on user response data and the specific detailed travel tendency clusters generated for each of the general travel tendency clusters become further apart, and the travel tendency feature information within each cluster can be further clustered. According to another example, as the electronic device (1000) repeats the process S1030 to S1050, the boundaries between the general travel tendency clusters and the specific detailed travel tendency clusters can become clearer. The electronic device (1000) can modify and update the weights of the user travel tendency analysis AI model so that the boundaries between the clusters become clearer. Additionally, although not shown in FIG. 10, the electronic device (1000) can prevent cluster gaps from occurring for classifying response data based on clustering by repeating the construction and learning process for the user travel tendency analysis AI model at a certain number of training response data or at a predetermined interval.

[0093] FIG. 11 is a diagram showing an example of a user travel tendency variable used by an electronic device according to one embodiment.

[0094] Referring to figures (1002) and (1004) in FIG. 11, examples of user travel tendency variables used by an electronic device are illustrated. The user travel tendency variables used by the electronic device (1000) or server (2000) to identify user travel tendency may include at least one of a comprehensive travel tendency variable type, a detailed travel tendency variable type, or a specific detailed travel tendency variable type. According to one example, the travel tendency variable (1003) illustrated in figure (1002) and the travel tendency variable (1005) illustrated in figure (1004) may be travel tendency variables corresponding to the detailed travel tendency variable type, but are not limited thereto.

[0095] FIG. 12 is a block diagram of an electronic device according to one embodiment.

[0096] FIG. 13 is a block diagram of an electronic device according to another embodiment.

[0097] As illustrated in FIG. 12, an electronic device (1000) according to one embodiment may include a processor (1300), a network interface (1500), and a memory (1700). However, not all of the illustrated components are essential components. The electronic device (1000) may be implemented with more components than those illustrated, or with fewer components.

[0098] For example, as illustrated in FIG. 13, the electronic device (1000) may further include a user input interface (1100), an output unit (1200), a sensing unit (1400), a network interface (1500), an A / V input unit (1600), and a memory (1700) in addition to a processor (1300), a network interface (1500), and a memory (1700).

[0099] The user input interface (1100) refers to a means for a user to input data for controlling an electronic device (1000). For example, the user input interface (1100) may include a key pad, a dome switch, a touch pad (contact capacitive method, pressure resistive method, infrared sensing method, surface ultrasonic conduction method, integral tension measurement method, piezo effect method, etc.), a jog wheel, a jog switch, etc., but is not limited thereto.

[0100] The user input interface (1100) can obtain user input for the user to select responses to the simulation. According to another example, the user can obtain user input for selecting travel content and user input for proceeding with an order payment service. The output unit (1200) can output an audio signal, a video signal, or a vibration signal, and the output unit (1200) may include a display unit (1210), an audio output unit (1220), and a vibration motor (1230).

[0101] The display unit (1210) includes a screen for displaying information processed by the electronic device (1000). Additionally, the screen can display information regarding traveler tendencies, travel location characteristics, and travel tendency content determined by the electronic device (1000). The sound output unit (1220) outputs audio data received from the network interface (1500) or stored in the memory (1700). Additionally, the sound output unit (1220) outputs sound signals related to functions performed by the electronic device (1000) (e.g., call signal reception sound, message reception sound, notification sound).

[0102] The processor (1300) typically controls the overall operation of the electronic device (1000). For example, the processor (1300) can generally control the user input interface (1100), output unit (1200), sensing unit (1400), network interface (1500), A / V input unit (1600), etc. by executing programs stored in memory (1700). Additionally, the processor (1300) can perform the functions of the electronic device (1000) described in FIGS. 1 to 11 by executing programs stored in memory (1700).

[0103] According to one embodiment, at least one processor (1300) can execute one or more instructions to provide a simulation including a plurality of queries for identifying a user's travel tendency, acquire response data including responses to the queries provided through the simulation, transmit the acquired response data to a server connected to the electronic device, acquire travel tendency content determined according to the tendency feature data output from a user travel tendency analysis artificial intelligence model that outputs tendency feature data representing the user's travel tendency when the response data is input, and output the travel tendency content.

[0104] According to one embodiment, at least one processor (1300) can perform at least one or all of the user travel tendency identification processes described in FIGS. 1 to 11.

[0105] According to one embodiment, at least one processor (1300) can construct a user travel tendency analysis artificial intelligence model based on the correlation between travel tendency variables regarding behavioral types by travel situation and the user's travel tendency, such that design tendency feature data is output when predetermined design response data is input, and can train the user travel tendency analysis artificial intelligence model so that the boundaries of the clusters to which the training tendency feature data obtained by inputting training response data into the constructed user travel tendency analysis artificial intelligence model become clear.

[0106] According to one embodiment, the processor (1300) may obtain information about an AI model for analyzing user travel tendencies that has already been learned from the server (2000), and may modify and update the weights regarding the layers and nodes within the AI ​​model for analyzing user travel tendencies and the connection strengths of the layers based on the learning data.

[0107] The sensing unit (1400) can detect the state of the electronic device (1000) or the state of the surroundings of the electronic device (1000) and transmit the detected information to the processor (1300). The sensing unit (1400) can sense specification information of the electronic device (1000), temperature, humidity, atmospheric pressure information, etc., regarding the space to be monitored.

[0108] For example, the sensing unit (1400) may include at least one of a magnetic sensor (1410), an acceleration sensor (1420), a temperature / humidity sensor (1430), an infrared sensor (1440), a gyroscope sensor (1450), a position sensor (e.g., GPS) (1460), a barometric pressure sensor (1470), a proximity sensor (1480), and an RGB sensor (illuminance sensor) (1490), but is not limited thereto. Since the function of each sensor can be intuitively inferred by a person skilled in the art from its name, a detailed description is omitted.

[0109] The network interface (1500) may include one or more components that enable the electronic device (1000) to communicate with another device (not shown) and a server (2000). The other device (not shown) may be a computing device such as the electronic device (1000) or a sensing device, but is not limited thereto. For example, the network interface (1500) may include a wireless communication interface (1510), a wired communication interface (1520), and a mobile communication unit (1530). The wireless communication interface (1510) may include a short-range wireless communication unit, a Bluetooth communication unit, a Bluetooth Low Energy (BLE) communication unit, a Near Field Communication unit, a Wi-Fi (WLAN) communication unit, a Zigbee communication unit, an infrared (IrDA, infrared Data Association) communication unit, a Wi-Fi Direct (WFD) communication unit, an ultra-wideband (UWB) communication unit, but is not limited thereto.

[0110] The wired communication interface (1520) may include at least one wired interface for exchanging data with an external device connected to the electronic device via wired communication. The mobile communication unit (1520) transmits and receives wireless signals with at least one of a base station, an external terminal, and a server on a mobile communication network. Here, the wireless signal may include various forms of data such as voice call signals, video call call signals, or text / multimedia message transmission and reception.

[0111] The A / V (Audio / Video) input unit (1600) is for inputting audio or video signals and may include a camera (1610) and a microphone (1620), etc. The camera (1610) can obtain image frames, such as still images or video, through an image sensor in video call mode or shooting mode. Images captured through the image sensor can be processed through a processor (1300) or a separate image processing unit (not shown).

[0112] The microphone (1620) receives an external acoustic signal and processes it into electrical voice data. For example, the microphone (1620) can receive an acoustic signal from an external device or a user. The microphone (1620) can receive voice input from a user. The microphone (1620) can use various noise removal algorithms to remove noise generated during the process of receiving the external acoustic signal.

[0113] The memory (1700) can store a program for processing and controlling the processor (1300), and can also store data that is input to or output from the electronic device (1000). Additionally, the memory (1700) can store information about the user travel tendency analysis artificial intelligence model, language model, neural network-based model, STTI network model, cluster identification network, and TRIFIT network model used by the electronic device (1000).

[0114] For example, the memory (1700) may store weight values ​​regarding layers, nodes, and connection strengths of at least one neural network model. Additionally, the electronic device (1000) may further store training data generated by the electronic device (1000) to train the neural network model. Additionally, the memory (1700) may further store information regarding the operating environment of cameras or servers connected to the electronic device.

[0115] The memory (1700) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk.

[0116] Programs stored in memory (1700) can be classified into multiple modules according to their function, for example, UI module (1710), touch screen module (1720), notification module (1730), etc.

[0117] The UI module (1710) can provide the electronic device (1000) with a UI, GUI, etc. for analyzing travel trends, travel location features, and providing travel content. The touch screen module (1720) can detect touch gestures on the user's touch screen and transmit information regarding the touch gestures to the processor (1300). In some embodiments, the touch screen module (1720) can recognize and analyze touch codes. The touch screen module (1720) may be configured as separate hardware including a controller.

[0118] The notification module (1730) can generate a signal to notify the occurrence of an event of the electronic device (1000). For example, it can provide a notification sound when user feedback regarding travel content provided by the electronic device (1000) is obtained or when notification content regarding travel tendencies is provided. Examples of events according to one embodiment include receiving a call signal, receiving a message, inputting a key signal, and a schedule notification. The notification module (1730) may output a notification signal in the form of a video signal through the display unit (1210), may output a notification signal in the form of an audio signal through the sound output unit (1220), or may output a notification signal in the form of a vibration signal through the vibration motor (1230).

[0119] FIG. 14 is a block diagram of a server according to one embodiment.

[0120] According to one embodiment, the server (2000) may include a network interface (2100), a database (2200), and a processor (2300). The configuration of the server (2000) shown in FIG. 14 may correspond to the configuration of the electronic device (1000) described in FIG. 12 and FIG. 13. The network interface (2100) may correspond to the network interface (not shown) of the electronic device (1000) described above. For example, the network interface (2100) may obtain response data, response identification information, and user information from the electronic device (1000), and transmit travel tendency feature data, user travel tendency feature information, user travel tendency cluster label information, and travel tendency content to the electronic device. According to another embodiment, the network interface (2100) may receive information about an artificial intelligence model learned by the electronic device, or information about a neural network model (e.g., weight values ​​regarding layers and connection strengths between layers). According to another embodiment, the network interface (2100) may transmit to the electronic device (1000) information regarding the layers of an artificial neural network and the nodes included in the layers, or weight values ​​regarding the connection strengths of the layers within the neural network, as information regarding the user travel tendency analysis artificial intelligence model trained by the server.

[0121] In addition, according to one embodiment, the database (2200) may correspond to the memory described above in FIGS. 12 and 13. For example, the database (2200) may store information such as user travel experience data, travel tendency content, travel location feature data, and traveler tendency feature data obtained from the electronic device (1000).

[0122] According to one embodiment, the processor (2300) can control the overall operation of the server (2000). For example, the processor (2300) can perform all or at least part of the operation of identifying user travel preferences and user-customized travel recommendation services described in FIG. 1 to 13 by controlling the network interface (2100) and the database (2200) in conjunction with the electronic device (1000).

[0123] FIG. 15 is a flowchart illustrating a method for identifying a user's travel tendencies by having an electronic device and a server interact with each other according to one embodiment.

[0124] In S1502, the server (2000) can train an artificial intelligence model for analyzing user travel tendencies. In S1504, the electronic device (1000) can provide a simulation including predetermined queries. In S1506, the electronic device (1000) can obtain response data obtained through the simulation. In S1508, the electronic device (1000) can transmit the obtained response data (e.g., including response identification information, survey identification information, and user information) to the server. According to one embodiment, when the electronic device (1000) obtains response data for each query, it can sequentially transmit each of the obtained response data to the server (2000).

[0125] At S1510, the server (2000) can input response data into a user travel tendency analysis artificial intelligence model. At S1512, the server (2000) can obtain tendency feature data by inputting response data into the user travel tendency analysis artificial intelligence model. At S1514, the server (2000) can determine travel tendency content including at least one of character information, a text sequence describing the user's travel tendency, or link information for viewing travel tendency content based on the tendency feature data. At S1516, the server (2000) can transmit the travel tendency content to an electronic device (1000). At S1518, the electronic device (1000) can output the travel tendency content. The user travel tendency identification method described in FIG. 15 can be performed by a user travel tendency analysis system (10).

[0126] A method for identifying a user's travel tendencies and a method for an electronic device to train an artificial intelligence model for analyzing a user's travel tendencies according to the present disclosure may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software.

[0127] Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0128] Although embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concept of the present invention as defined in the following claims also fall within the scope of the present invention.

Claims

Claim 1 A method for an electronic device to identify a user's travel tendency comprises: a step of providing a simulation including a plurality of queries for identifying the user's travel tendency; a step of acquiring response data including responses to the queries provided through the simulation; a step of transmitting the acquired response data to a server connected to the electronic device; a step of acquiring travel tendency content from the server, which is determined according to the tendency feature data output from a user travel tendency analysis AI model that outputs tendency feature data representing the user's travel tendency when the response data is input; and a step of outputting the travel tendency content. The method further comprises, prior to the step of providing the simulation, a step of training the user travel tendency analysis AI model using training response data; and, when new response data different from the training response data used to train the user travel tendency analysis AI model is acquired, a step of identifying new tendency feature data from the new response data; and a step of identifying whether there is a change in the cluster characteristics of a group of new tendency feature data including the new tendency feature data and training tendency feature data according to the training response data, following the addition of the new tendency feature data. and if the change in the cluster characteristics is identified, prior to the step of providing the simulation, a step of retraining the user travel propensity analysis artificial intelligence model;The user travel tendency analysis artificial intelligence model includes, when the response data is input, a detailed travel tendency variable numerical computation network that outputs detailed travel tendency characteristic information including feature values ​​for each detailed travel tendency variable for the user's travel tendency variables, and a comprehensive travel tendency variable numerical computation network that outputs comprehensive travel tendency characteristic information including feature values ​​for each comprehensive travel tendency variable representing some detailed travel tendency variables among the detailed travel tendency variables, and an STTI network that identifies user travel tendency characteristic information at different levels; A cluster identification network comprising: a comprehensive travel tendency cluster identification network that, when user travel tendency feature information output from the STTI network is input, identifies one of the comprehensive travel tendency clusters, which are first-type clusters arranged in a multidimensional space including the comprehensive travel tendency variables as reference axes through first-level clustering; and a specific detailed travel tendency cluster identification network that outputs specific detailed travel tendency cluster label information, which is generated for each comprehensive travel tendency cluster and, through second-level clustering for each user travel tendency feature information corresponding to the comprehensive travel tendency clusters, identifies one of the specific detailed travel tendency clusters, which are second-type clusters arranged in a multidimensional space defined based on specific detailed travel tendency variables composed of some of the detailed travel tendency variables.The step of retraining the user travel tendency analysis AI model includes, when the cluster characteristic change is identified, reapplying a clustering algorithm to the new tendency feature data group to redetermine the number of comprehensive travel tendency clusters, which are the first type of cluster, and the number of specific detailed travel tendency clusters, which are the second type of cluster, and modifying and updating the weights of the user travel tendency analysis AI model so that the user travel tendency feature information is clustered based on the redetermined number of comprehensive travel tendency clusters and the number of specific detailed travel tendency clusters, thereby retraining the user travel tendency analysis AI model. A method comprising: a number of comprehensive travel tendency clusters, wherein the number of comprehensive travel tendency clusters is determined by applying a clustering algorithm to comprehensive travel tendency feature information including feature values ​​for each comprehensive travel tendency variable; wherein the specific detailed travel tendency clusters, which are the second type of cluster, are generated for each comprehensive travel tendency cluster based on the number of comprehensive travel tendency clusters, and are placed in a multidimensional space defined based on specific detailed travel tendency variables among the detailed travel tendency variables included in the comprehensive travel tendency variables, wherein the degree of user travel tendency discrimination is identified as being above a threshold; and wherein the number of specific detailed travel tendency clusters, which are the second type of cluster, is determined by applying a clustering algorithm to specific detailed travel tendency feature information including feature values ​​for the specific detailed travel tendency variables. Claim 2 A method according to claim 1, wherein the step of acquiring response data comprises: acquiring user information regarding at least one of the user's gender, age, and phone number; and acquiring survey identification information for identifying responses included in the acquired response data. Claim 3 The method of paragraph 2 comprises: providing feedback queries to obtain feedback on the travel tendency content; obtaining a Likert scale for the feedback queries as feedback information on the travel tendency content; and transmitting the feedback information to the server. Claim 4 The method according to claim 2, wherein the step of acquiring the response data further comprises: acquiring dropout rate information regarding at least one of the time required to acquire responses to the queries and the number of respondents to the queries; and the step of transmitting the response data to the server comprises: transmitting the dropout rate information to the server together with the response data. Claim 5 delete Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 A method according to claim 1, wherein the travel tendency content comprises character information including the name and image of a character representing the user’s travel tendency, a text sequence describing the user’s travel tendency, and link information for viewing the travel tendency content. Claim 11 A method according to claim 10, wherein the character information is determined based on the comprehensive travel tendency cluster label information, and one or more sentence sequences included in the text sequence are determined based on the specific detailed travel tendency cluster label information. Claim 12 An electronic device for identifying a user's travel tendencies comprises: a network interface; a memory for storing one or more instructions; and at least one processor for executing the one or more instructions. The method comprises, wherein at least one processor, by executing one or more instructions, provides a simulation including a plurality of queries for identifying the user's travel tendencies, acquires response data including responses to the queries provided through the simulation, transmits the acquired response data to a server connected to the electronic device, and acquires travel tendency content determined according to the tendency feature data output from a user travel tendency analysis AI model that outputs tendency feature data representing the user's travel tendencies when the response data is input, from the server, and, by executing one or more instructions, prior to providing the simulation, trains the user travel tendency analysis AI model using training response data, and if new response data different from the training response data used to train the user travel tendency analysis AI model is acquired, identifies new tendency feature data from the new response data, identifies whether there is a change in the cluster characteristics of a group of new tendency feature data including the new tendency feature data and training tendency feature data according to the training response data due to the addition of the new tendency feature data, and if the change in cluster characteristics is identified, prior to the step of providing the simulation, The above-mentioned user travel tendency analysis AI model is retrained, and the above-mentioned user travel tendency analysis AI model, when the above-mentioned response data is input, has a detailed travel tendency variable numerical computation network that outputs detailed travel tendency feature information including feature values ​​for each detailed travel tendency variable for the above-mentioned user travel tendency variables, and among the above-mentioned detailed travel tendency variables,An STTI network for identifying user travel tendency feature information at different levels, including a numerical computation network for comprehensive travel tendency variables that outputs comprehensive travel tendency feature information including feature values ​​for each comprehensive travel tendency variable representing some detailed travel tendency variables; and a cluster identification network comprising, when user travel tendency feature information output from the STTI network is input, a comprehensive travel tendency cluster identification network that identifies one of comprehensive travel tendency clusters, which are first type clusters arranged in a multidimensional space including the comprehensive travel tendency variables as reference axes through first level clustering, and a specific detailed travel tendency cluster label network that outputs specific detailed travel tendency cluster label information, which is generated for each comprehensive travel tendency cluster and identifies one of specific detailed travel tendency clusters, which are second type clusters arranged in a multidimensional space defined based on specific detailed travel tendency variables composed of some detailed travel tendency variables among the detailed travel tendency variables, through second level clustering for each user travel tendency feature information corresponding to the comprehensive travel tendency clusters. The method includes, wherein when a change in the clustering characteristic is identified, the at least one processor reapplies a clustering algorithm to the new propensity feature data group to re-determine the number of comprehensive travel tendency clusters, which are the first type of cluster, and the number of specific detailed travel tendency clusters, which are the second type of cluster, and retrains the user travel tendency analysis AI model by modifying and updating the weights of the user travel tendency analysis AI model so that the user travel tendency feature information is clustered based on the re-determined number of comprehensive travel tendency clusters and the number of specific detailed travel tendency clusters.The number of the above-mentioned comprehensive travel tendency clusters is determined by applying a clustering algorithm to comprehensive travel tendency feature information including feature values ​​for each of the above-mentioned comprehensive travel tendency variables, and the special detailed travel tendency clusters, which are the second type of clusters, are generated for each comprehensive travel tendency cluster based on the number of the above-mentioned comprehensive travel tendency clusters, and are placed in a multidimensional space defined based on special detailed travel tendency variables among the detailed travel tendency variables included in the above-mentioned comprehensive travel tendency variables, wherein the degree of user travel tendency discrimination is identified as being above a threshold, and the number of the special detailed travel tendency clusters, which are the second type of clusters, is determined by applying a clustering algorithm to special detailed travel tendency feature information including feature values ​​for the special detailed travel tendency variables. Claim 13 A method for an electronic device to identify a user's travel tendency comprises: a step of providing a simulation including a plurality of queries for identifying the user's travel tendency; a step of acquiring response data including responses to the queries provided through the simulation; a step of transmitting the acquired response data to a server connected to the electronic device; a step of acquiring travel tendency content from the server, which is determined according to the tendency feature data output from a user travel tendency analysis AI model that outputs tendency feature data representing the user's travel tendency when the response data is input; and a step of outputting the travel tendency content. The method further comprises, prior to the step of providing the simulation, a step of training the user travel tendency analysis AI model using training response data; and, when new response data different from the training response data used to train the user travel tendency analysis AI model is acquired, a step of identifying new tendency feature data from the new response data; and a step of identifying whether there is a change in the cluster characteristics of a group of new tendency feature data including the new tendency feature data and training tendency feature data according to the training response data, following the addition of the new tendency feature data. and if the change in the cluster characteristics is identified, prior to the step of providing the simulation, a step of retraining the user travel propensity analysis artificial intelligence model;The user travel tendency analysis artificial intelligence model includes, when the response data is input, a detailed travel tendency variable numerical computation network that outputs detailed travel tendency characteristic information including feature values ​​for each detailed travel tendency variable for the user's travel tendency variables, and a comprehensive travel tendency variable numerical computation network that outputs comprehensive travel tendency characteristic information including feature values ​​for each comprehensive travel tendency variable representing some detailed travel tendency variables among the detailed travel tendency variables, and an STTI network that identifies user travel tendency characteristic information at different levels; A cluster identification network comprising: a comprehensive travel tendency cluster identification network that, when user travel tendency feature information output from the STTI network is input, identifies one of the comprehensive travel tendency clusters, which are first-type clusters arranged in a multidimensional space including the comprehensive travel tendency variables as reference axes through first-level clustering; and a specific detailed travel tendency cluster identification network that outputs specific detailed travel tendency cluster label information, which is generated for each comprehensive travel tendency cluster and, through second-level clustering for each user travel tendency feature information corresponding to the comprehensive travel tendency clusters, identifies one of the specific detailed travel tendency clusters, which are second-type clusters arranged in a multidimensional space defined based on specific detailed travel tendency variables composed of some of the detailed travel tendency variables.The step of retraining the user travel tendency analysis AI model includes, when the cluster characteristic change is identified, reapplying a clustering algorithm to the new tendency feature data group to redetermine the number of comprehensive travel tendency clusters, which are the first type of cluster, and the number of specific detailed travel tendency clusters, which are the second type of cluster, and modifying and updating the weights of the user travel tendency analysis AI model so that the user travel tendency feature information is clustered based on the redetermined number of comprehensive travel tendency clusters and the number of specific detailed travel tendency clusters, thereby retraining the user travel tendency analysis AI model. A computer-readable recording medium storing a program for performing a method characterized by including, wherein the number of comprehensive travel tendency clusters is determined by applying a clustering algorithm to comprehensive travel tendency feature information including feature values ​​for each comprehensive travel tendency variable, and wherein the specific detailed travel tendency clusters, which are the second type of cluster, are generated for each comprehensive travel tendency cluster based on the number of comprehensive travel tendency clusters, and are placed in a multidimensional space defined based on specific detailed travel tendency variables among the detailed travel tendency variables included in the comprehensive travel tendency variables, wherein the degree of user travel tendency discrimination is identified as being above a threshold, and wherein the number of specific detailed travel tendency clusters, which are the second type of cluster, is determined by applying a clustering algorithm to specific detailed travel tendency feature information including feature values ​​for the specific detailed travel tendency variables.

Images