Control method of server for personalized travel recommendation service

Abstract

A method of operation of a server providing a travel destination recommendation service is disclosed. The method of operation of the server according to the present disclosure includes the steps of: acquiring background information for each user, including the tendencies, preferred travel regions, and personal information of each of a plurality of users; generating and storing unit recommendation information based on the background information and travel destination review information for each of the plurality of users who have provided travel destination review information; and identifying at least one recommended travel destination for a target user based on the plurality of unit recommendation information and providing it to the target user.

Description

Technology Field

[0001] The present disclosure relates to a method of operation of a server providing a travel destination recommendation service, and more specifically, to a method of operation of a server that identifies and provides at least one recommended travel destination for a target user by comparing background information, including the target user's tendencies, preferred travel regions, and personal information, with unit recommendation information from a user who provided travel destination review information. Background Technology

[0002] Recently, as travel has established itself as a representative means of leisure and healing, the demand for services that efficiently recommend travel destinations tailored to individual tastes and preferences has been continuously increasing, and accordingly, various technologies for providing travel destination recommendation services exist.

[0003] However, existing travel recommendation services are limited to providing general recommendations based merely on popularity rankings or general statistical data. As they fail to adequately reflect individual user preferences or preferred travel destinations, they often fail to offer practical help to new users who lack the necessary data for reliable recommendations. Prior art literature

[0004] Registered Patent Publication No. 10-2721239 The problem to be solved

[0005] The purpose of the present disclosure is to provide a method of operation for a server that identifies a travel destination suitable for a user based on past travel destination review information of multiple users, based on the user's tendencies, preferred travel regions, and personal information, and provides it as a recommended travel destination.

[0006] The purposes of the present disclosure are not limited to those mentioned above, and other purposes and advantages of the present disclosure not mentioned may be understood from the following description and will be more clearly understood from the embodiments of the present disclosure. Furthermore, it will be readily apparent that the purposes and advantages of the present disclosure can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0007] A method of operation of a server providing a travel destination recommendation service according to one embodiment of the present disclosure comprises: acquiring background information for each user, including the tendencies, preferred travel regions, and personal information of each of a plurality of users; generating and storing unit recommendation information based on the background information and the travel destination review information for each of the plurality of users who have provided travel destination review information; and identifying at least one recommended travel destination for a target user based on the plurality of unit recommendation information and providing it to the target user.

[0008] At this time, the step of acquiring the background information for each user may include the step of acquiring the background information based on at least one user response obtained as a result of providing a plurality of query items to the user.

[0009] Additionally, the step of generating and storing the unit recommendation information may include: identifying at least one emotion keyword from the text included in the travel destination review information; identifying the user's emotional state for each of the travel destination review information based on the identified emotion keyword; and generating unit recommendation information that includes both the background information and the travel destination review information when the travel destination review information is identified as having a positive emotional state.

[0010] In this case, the step of identifying and providing the recommended travel destination to the target user may include, when the target user is a first user corresponding to a new user, the step of identifying at least one unit recommendation information among the plurality of unit recommendation information that matches the target user's background information, and the step of selecting a travel destination included in the travel destination review information that matches the identified unit recommendation information as the recommended travel destination.

[0011] At this time, the step of identifying at least one unit recommendation information that matches the background information of the target user may be characterized by generating virtual recommendation information that includes virtual travel destination review information that matches the positive emotional state in the background information of the target user, and identifying unit recommendation information that matches the virtual recommendation information.

[0012] Additionally, the step of identifying and providing the recommended travel destination to the target user may include, when the target user is a second user corresponding to an existing user, the step of identifying at least one unit recommendation information previously generated for the target user and the step of identifying a travel destination that matches the travel destination review information included in the identified unit recommendation information as the recommended travel destination.

[0013] Meanwhile, the step of generating and storing the unit recommendation information may include the step of obtaining a first vector in which the background information is vectorized, the step of obtaining a second vector in which the travel destination review information is vectorized, and the step of storing a third vector, in which the first vector and the second vector are combined, as the unit recommendation information.

[0014] In this case, the step of storing the third vector as the unit recommendation information may include the step of obtaining hash data converted according to a preset hash algorithm as the unit recommendation information. Effects of the invention

[0015] The present disclosure enables the recommendation of travel destinations more suitable for each user based on unit recommendation information that integrates the user's emotional state identifiable from existing user background information and travel destination review information, and to this end, travel destinations suitable for the user can be identified by utilizing travel destination review information based on a positive emotional state. Brief explanation of the drawing

[0016] FIG. 1 is a drawing for explaining that a server according to one embodiment of the present disclosure is connected to a plurality of user terminals, FIG. 2 is a flowchart for explaining the operation of a server according to one embodiment of the present disclosure, FIG. 3 is a diagram illustrating the operation of a server generating background information for each of a plurality of users according to one embodiment of the present disclosure, FIG. 4 is a flowchart illustrating the operation of a server according to an embodiment of the present disclosure to identify a user's emotional state regarding travel destination review information and generate unit recommendation information. FIG. 5 is a diagram illustrating an operation in which a server according to an embodiment of the present disclosure compares virtual recommendation information and unit recommendation information of a target user. FIG. 6 is a flowchart illustrating the operation of a server identifying a recommended travel destination for a second user according to one embodiment of the present disclosure, FIG. 7 is a flowchart illustrating the operation of a server storing unit recommendation information in the form of hash data according to one embodiment of the present disclosure, FIG. 8 is a drawing for explaining the configuration of a server according to one embodiment of the present disclosure. Specific details for implementing the invention

[0017] Before specifically describing the present disclosure, the method of description in the specification and drawings is described.

[0018] First, the terms used in this specification and claims have been selected based on general terms considering their functions in the various embodiments of this disclosure. However, these terms may vary depending on the intent of those skilled in the art, legal or technical interpretations, and the emergence of new technologies. Additionally, some terms have been arbitrarily selected by the applicant. Such terms may be interpreted according to the meanings defined in this specification; in the absence of specific definitions, they may be interpreted based on the overall content of this specification and common technical knowledge in the relevant field.

[0019] In addition, the same reference numbers or symbols described in each drawing attached to this specification represent parts or components that perform substantially the same function. For convenience of explanation and understanding, the same reference numbers or symbols are used to describe different embodiments. That is, even if components having the same reference number are all depicted in multiple drawings, the multiple drawings do not imply a single embodiment.

[0020] Additionally, in this specification and claims, terms including ordinal numbers, such as "first," "second," etc., may be used to distinguish between components. These ordinal numbers are used to distinguish identical or similar components from one another, and the meaning of the terms should not be limited by the use of such ordinal numbers. For example, the order of use or arrangement of components combined with such ordinal numbers should not be restricted by the number. If necessary, each ordinal number may be used interchangeably.

[0021] In this specification, singular expressions include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "consisting of" are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0022] In the embodiments of the present disclosure, terms such as "module," "unit," "part," etc. are used to refer to a component that performs at least one function or operation, and such component may be implemented in hardware or software, or in a combination of hardware and software. Additionally, a plurality of "modules," "units," "parts," etc. may be integrated into at least one module or chip and implemented as at least one processor, except where each needs to be implemented in specific individual hardware.

[0023] Furthermore, in the embodiments of the present disclosure, when a part is described as being connected to another part, this includes not only a direct connection but also an indirect connection through another medium. Additionally, the meaning that a part includes a certain component implies that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0024] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0025] FIG. 1 is a drawing for explaining that a server according to one embodiment of the present disclosure is connected to a plurality of user terminals.

[0026] According to FIG. 1, the server (100) can communicate with a plurality of user terminals (200).

[0027] The server (100) is configured to recommend a travel destination suitable for a user. Specifically, the server (100) can identify a travel destination suitable for a user who has requested a travel destination recommendation as a recommended travel destination based on information about multiple users who have traveled to the travel destination in the past, and provide it to the user.

[0028] The server (100) according to this may correspond to a server device or system including at least one computer. For example, the server (100) may correspond to a terminal device such as a desktop PC, laptop PC, tablet PC, or smartphone, but is not limited thereto.

[0029] The user terminal (200) is a terminal device of the user and is configured to provide at least one piece of information related to the user to the server (100) in order to receive a travel destination recommendation from the server (100), and to receive information related to the recommended travel destination from the server (100).

[0030] The user terminal (200) according to this may be various types of terminal devices capable of connecting to wired / wireless networks, such as servers, smartphones, tablet PCs, desktops, laptops, and wearable devices, but is not limited thereto.

[0031] At this time, multiple user terminals (200) can be connected to the server (100) via wired or wireless connection to perform communication, and multiple user terminals (200) can be connected to the server (100) simultaneously.

[0032] Alternatively, the user terminal (200) may be connected to the server (100) through a dedicated program, application, or web browser. For example, the user terminal (200), such as a smartphone, may provide user responses to the server (100) or receive information related to recommended travel destinations from the server (100) through an application or web browser connected to the server (100).

[0033] FIG. 2 is a flowchart for explaining the operation of a server according to one embodiment of the present disclosure.

[0034] According to FIG. 2, the server (100) can obtain background information for each of a plurality of users (S210).

[0035] Specifically, background information may be composed of personal information such as the user's gender and age, tendencies, preferred travel destinations, etc.

[0036] Here, the server (100) can generate user-specific background information by providing the user with at least one query item for each component (: personal information, tendencies, preferred travel destinations) that constitutes the background information.

[0037] In this regard, FIG. 3 is a diagram illustrating the operation of a server generating background information for each of a plurality of users according to one embodiment of the present disclosure.

[0038] According to FIG. 3, the server (100) can generate background information about the user by providing at least one query item.

[0039] Specifically, the server (100) can obtain information regarding the age and gender corresponding to the user's personal information based on the query items for personal information.

[0040] Additionally, the server (100) may provide at least one query item to identify the user's preferences, such as preferred color and preferred photo.

[0041] In the case of the embodiment of FIG. 3, the server (100) may provide at least one query item that allows one to select one of a plurality of colors to identify a preferred color.

[0042] Additionally, the server (100) may provide a query item that allows selecting one of the multiple images along with multiple images to identify a preferred photo.

[0043] Likewise, regarding preferred travel destinations, the server (100) may provide a query item to the user to select one of multiple options related to the travel destination, and may obtain the preferred travel destination based on the user's response to the query item.

[0044] Based on the user response to each query item obtained in this way, the server (100) can generate background information about the user.

[0045] For example, in the embodiment of FIG. 3, the server (100) can generate and obtain background information for the user as ‘32 years old, female, preferred color-2, preferred photo-5, preferred travel destination-6’.

[0046] And, the server (100) can generate and store unit recommendation information for each user who has provided travel destination review information among multiple users (S220).

[0047] Specifically, travel destination review information may include text corresponding to a user's review of a specific travel destination. In this case, information about the travel destination visited by the user may be included in the unit recommendation information, or it may be stored as separate information corresponding to the unit recommendation information.

[0048] Unit recommendation information may be implemented by including both the user's background information and the user's travel destination review information.

[0049] Multiple unit recommendation information can be generated and stored for each user or based on the travel destinations a user has visited.

[0050] And, the server (100) can identify at least one recommended travel destination for the target user based on multiple unit recommendation information (S230).

[0051] The target users may be users who requested travel destination recommendations.

[0052] In this case, the server (100) can identify a recommended travel destination suitable for the target user by comparing the information of the target user with the information of the target user and the information of the multiple unit recommendation information generated by the multiple users who provided past travel destination recommendation information.

[0053] Specifically, the server (100) can identify unit recommendation information that matches the background information of the target user among a plurality of unit recommendation information, and can identify the travel destination for the identified unit recommendation information as a recommended travel destination suitable for the target user.

[0054] When a recommended travel destination for a target user is identified, the server (100) can provide the identified recommended travel destination to the target user (S240).

[0055] At this time, the server (100) may generate unit recommendation information for all users who have provided travel destination review information, but may also generate unit recommendation information only for users who have provided positive travel destination review information.

[0056] In this regard, FIG. 4 is a flowchart illustrating the operation of a server according to one embodiment of the present disclosure to identify a user's emotional state regarding travel destination review information and generate unit recommendation information.

[0057] As illustrated in FIG. 4, the server (100) can identify at least one sentiment keyword from the text included in the travel destination review information (S410).

[0058] In one embodiment, the server (100) can identify at least one emotion keyword related to the user's emotions from the text included in the travel destination review information, such as 'really good', 'I want to come back', 'good. I think it would be okay to come back', 'average', 'not good', 'different from the photo, I won't come back'.

[0059] Here, the server (100) can identify the user's emotional state appearing in the travel destination review information based on the identified emotional keywords. For example, the server (100) can identify the user's emotional state as one of five emotional states: 'very positive', 'positive', 'neutral', 'negative', and 'very negative'.

[0060] And, the server (100) can generate unit recommendation information including travel destination review information identified as having a positive emotional state among multiple travel destination review information and background information that matches the travel destination review information (S420).

[0061] For example, the server (100) can identify only travel destination review information corresponding to the ‘very positive’ and ‘positive’ emotional states among the five emotional states as travel destination review information corresponding to the positive emotional state, and can generate unit recommendation information including background information matching each of the identified travel destination review information.

[0062] Meanwhile, the server (100) can perform the operation of identifying recommended travel destinations differently depending on the type of target user.

[0063] Specifically, the target user may be either a first user, who is a new user who has never previously provided travel destination review information to the server (100), or a second user, who is an existing user who has previously provided travel destination review information.

[0064] In this case, when the target user is identified as the first user, the server (100) can identify at least one unit recommendation information among a plurality of unit recommendation information that matches the target user's background information, and can select a travel destination that matches the travel destination review information included in the identified unit recommendation information as a recommended travel destination for the target user.

[0065] Specifically, the server (100) can identify unit recommendation information that matches the background information based on the similarity between the target user's background information and the unit recommendation information. For example, the server (100) can identify unit recommendation information that matches the background information as unit recommendation information where the similarity is greater than or equal to a preset threshold value (e.g., 0.9).

[0066] However, comparing the target user's background information with unit recommendation information may not yield accurate results due to the composition of the unit recommendation information.

[0067] This is because, since unit recommendation information is fundamentally composed of background information and travel review data (regarding positive emotional states) of other users, comparing unit recommendation information without the travel review data of the target user can lead to reduced matching reliability or the matching of inaccurate unit recommendation information due to differences in components.

[0068] Accordingly, for a clear comparison, it is necessary to generate information identical in composition to the unit recommendation information based on the target user's background information.

[0069] In this regard, FIG. 5 is a diagram illustrating the operation of a server according to one embodiment of the present disclosure comparing virtual recommendation information of a target user with unit recommendation information.

[0070] According to FIG. 5, the server (100) can generate virtual recommendation information based on background information of the target user corresponding to the first user and virtual travel destination review information.

[0071] Specifically, since the target user corresponding to the first user does not have a history of entering travel destination review information, the server (100) can generate virtual recommendation information corresponding to the same format as the unit recommendation information by generating virtual travel destination review information for the target user.

[0072] Here, the virtual travel destination review information may include text corresponding to a positive emotional state, similar to the travel destination review information described above.

[0073] To this end, the server (100) can generate virtual travel review information by generating virtual text corresponding to a positive emotional state through at least one generative model.

[0074] Specifically, the server (100) can communicate with an external server that stores various types of text generation models based on large language models such as ChatGPT, Gemini, and Claude, and can generate virtual travel destination review information by generating multiple texts that express a positive emotional state through the text generation models.

[0075] Alternatively, the server (100) may extract text included in the unit recommendation information from any unit recommendation information, and it is also possible to generate virtual travel destination review information based on the extracted text.

[0076] And, the server (100) can compare virtual recommendation information with multiple unit recommendation information to identify at least one unit recommendation information that matches the virtual recommendation information, and can identify a travel destination that matches the travel destination review information included in the identified unit recommendation information as a recommended travel destination for the target user.

[0077] Meanwhile, the target user may correspond to a second user who is an existing user, rather than the first user described above. In this case, the server (100) can identify one of the travel destinations that the past user has positively experienced as a recommended travel destination.

[0078] In this regard, FIG. 6 is a flowchart illustrating the operation of a server (100) according to one embodiment of the present disclosure identifying a recommended travel destination for a second user.

[0079] Referring to FIG. 6, the server (100) can identify at least one unit recommendation information previously generated for the target user when the target user is a second user (S610).

[0080] And, the server (100) can identify a travel destination that matches the travel destination review information included in the unit recommendation information as a recommended travel destination (S620).

[0081] Specifically, since the unit recommendation information previously generated for the target user is created as the target user provides travel destination review information that matches their past positive emotional state, the travel destinations based on the unit recommendation information may correspond to travel destinations that the target user has positively experienced in the past.

[0082] As a result, the server (100) can select and provide at least one of the travel destinations that the target user has experienced in the past as a recommended travel destination.

[0083] However, the method of operation of the server (100) according to the first user described above may also be performed for the second user. Specifically, when the server (100) receives user input from the second user recommending a new travel destination different from the travel destination previously experienced, the server (100) may perform the method of operation for the first user described above for the second user as well.

[0084] Here, the server (100) can identify recommended travel destinations by excluding unit recommendation information based on travel destination review information previously provided by the second user and the travel destinations based thereon from among a plurality of unit recommendation information.

[0085] For example, the server (100) can identify matching unit recommendation information and a corresponding travel destination by comparing a plurality of unit recommendation information, from which unit recommendation information matching the second user is excluded, with virtual recommendation information based on the second user's background information. Here, if the server (100) identifies that the identified travel destination is not a travel destination identifiable from the second user's unit recommendation information, it can identify the travel destination as a final recommended travel destination and provide it to the second user.

[0086] According to various embodiments of the present disclosure, when a server (100) identifies a unit recommendation information that matches the background information of a target user among a plurality of unit recommendation information, it can identify whether to provide the travel destination to the target user as a recommended travel destination by considering the distance between the travel destination that matches the unit recommendation information and the target user.

[0087] For example, instead of providing the travel destination identified through unit recommendation information directly to the target user as a recommended travel destination, the server (100) may identify the travel destination as a candidate travel destination and then determine whether to provide the candidate travel destination to the target user as a recommended travel destination based on the distance between the candidate travel destination and the target user.

[0088] In this case, the server (100) can determine whether to provide the candidate travel destination as a recommended travel destination to the target user by comparing the estimated travel period set according to the distance and the average value of the total travel period including the candidate travel destination for each of the multiple users who have traveled to the candidate travel destination.

[0089] Specifically, in the process of receiving travel destination review information from multiple users, the server (100) may additionally receive information about the total travel period (e.g., 2 nights and 3 days, 3 nights and 4 days, 4 nights and 5 days, etc.) that the user traveled to, including the travel destination.

[0090] Here, the server (100) can identify the average travel period of multiple users who have provided travel review information for each travel destination, based on information about the travel period obtained from one or more users for the same travel destination.

[0091] And, when the server (100) identifies a candidate travel destination based on unit recommendation information that matches the background information of the target user, it can calculate the distance value between the target user's location information obtained from the target user's user terminal and the candidate travel destination as the target distance.

[0092] At this time, there may be multiple segments for the distance value corresponding to the target distance, and there may be a pre-set estimated travel period for each segment.

[0093] In one embodiment, for the first section corresponding to a target distance of 0km or more and less than 100km, an estimated travel period of 1 night and 2 days or less, for the second section corresponding to 100km or more and less than 250km, an estimated travel period of 2 nights and 3 days or less, for the third section corresponding to 250km or more and less than 500km, an estimated travel period of 3 nights and 4 days or more, and for the fourth section corresponding to 500km or more, an estimated travel period of 4 nights and 5 days or more may be pre-set, but is not limited to the examples described above.

[0094] Here, the server (100) can identify whether to provide the candidate travel destination to the target user as a recommended travel destination by comparing the estimated travel period identified according to the size of the target distance with the average travel period that matches the candidate travel destination.

[0095] Specifically, the server (100) may provide the candidate travel destination to the target user as a recommended travel destination only if the average travel period for the candidate travel destination is less than or equal to the estimated travel period identified according to the size of the target distance.

[0096] This takes into account the fact that if the travel period is expected to be relatively shorter than the average travel period of users who provided travel reviews for the candidate destination, the target user may not be able to fully experience the destination as recommended by other users.

[0097] Accordingly, the server (100) can provide the candidate travel destination as a recommended travel destination to the target user only when it is determined that the travel period is sufficient for the duration that other users who have experienced the candidate travel destination have actually traveled.

[0098] Here, if the target user is an existing user, the server (100) can identify the number of times a travel destination within the same distance range as the candidate travel destination has been visited for a shorter travel period than the average travel period, based on the existing user's past travel destination recommendation information and travel period information. Then, if the number of times identified is greater than a preset number, the server (100) can provide the candidate travel destination as a recommended travel destination even if the expected travel period for the candidate travel destination is shorter than the average travel period.

[0099] According to the process described above, the server (100) can provide a recommended travel destination optimized for the target user by taking into account the distance between the user and the travel destination, the average travel duration of other users, and the user's travel tendencies.

[0100] Alternatively, the server (100) may determine whether to provide the candidate destination as a recommended destination to the target user by using the most frequent travel period, which is the travel period most frequently entered by multiple users for the candidate destination, instead of the average travel period described above.

[0101] Meanwhile, the server (100) may generate unit recommendation information in the form of hash data. In this case, the server (100) can identify unit recommendation information that matches the target user's background information (or virtual recommendation information) by comparing the hash data that matches the unit recommendation information with the hash data in which the target user's background information (or virtual recommendation information) is hashed.

[0102] In this regard, FIG. 7 is a flowchart illustrating the operation of a server storing unit recommendation information in the form of hash data according to one embodiment of the present disclosure.

[0103] According to FIG. 7, the server (100) can obtain a first vector in which background information is vectorized and a second vector in which travel destination review information is vectorized (S710).

[0104] Specifically, the first vector may correspond to the result of vectorizing the values ​​corresponding to each item constituting the background information.

[0105] For example, in the embodiment of FIG. 3, the server (100) can obtain a first vector in the form of [32, 1, 2, 5, 6]. In this case, each digit of the first vector corresponds to age, gender, selected preferred color, selected preferred image, and preferred travel region.

[0106] In addition, the second vector may correspond to the result of text included in travel destination review information being vectorized according to various known types of language embedding techniques.

[0107] And, the server (100) can obtain a third vector formed by combining the first vector and the second vector (S720). In this case, the third vector may be the result of simply combining the first vector segment and the second vector segment, but is not limited thereto.

[0108] And, the server (100) can store the hash data converted by the third vector according to the hash algorithm as unit recommendation information (S730).

[0109] A hash algorithm is an algorithm designed to map an input value of arbitrary length to a hash value of a fixed length. Generally, hash algorithms are widely used for purposes such as verifying data integrity, determining duplicates, and high-speed searching, as they can be computed at high speed regardless of the structure of the input value and produce a completely different hash value even with small changes to the input.

[0110] Since the third vector of the present disclosure is vector data having a multidimensional structure in the form of a combination of the first vector and the second vector, it can be hashed to efficiently compare unit recommendation information matched to the target user in terms of computational load and resource consumption.

[0111] To this end, the server (100) can obtain hash data in which a third vector is hashed based on various types of hash algorithms (e.g., SimHash, Locality-Sensitive Hashing (LSH), etc.) that output similar hash values ​​as vector values ​​are similar to each other, and subsequently, it is possible to identify a third vector that matches the target user's background information (or virtual recommendation information) and a unit recommendation information that matches the third vector according to the similarity with the hash data in which a vector corresponding to the target user's background information (or virtual recommendation information) is hashed.

[0112] Here, the server (100) may store all unit recommendation information in the form of hash data, but may also convert existing unit recommendation information stored in a non-hash data form into hash data depending on the number of unit recommendation information stored in a non-hash data form.

[0113] In this case, if there is a sufficient amount of stored multiple unit recommendation information, the server (100) can convert at least some of the multiple unit recommendation information into hash data and store it.

[0114] Specifically, if the number of stored unit recommendation information is greater than or equal to a preset threshold, the server (100) can group the unit recommendation information to create at least one target group.

[0115] For example, the server (100) can group multiple unit recommendation information that have the same travel destination included in the travel destination review information, thereby creating a target group composed of multiple unit recommendation information that shares the same travel destination.

[0116] Alternatively, the server (100) may create target groups by grouping multiple unit recommendation information based on various known types of clustering techniques, such as the K-means algorithm.

[0117] Here, the server (100) can calculate, for each target group, the ratio of the number of unit recommendation information constituting the target group to the total unit recommendation information.

[0118] And, if the server (100) identifies at least one target group in which the calculated ratio is greater than or equal to a preset threshold ratio, it can convert multiple unit recommendation information included in the target group identified as having a ratio greater than or equal to the threshold ratio into hash data.

[0119] On the other hand, if a target group exceeding a threshold ratio is not identified, the server (100) can convert all of the stored multiple unit recommendation information into hash data.

[0120] Accordingly, when a specific target group that occupies a relatively large amount of storage space by including a large amount of unit recommendation information is identified while there is a sufficient amount of stored unit recommendation information, the server (100) can reduce the capacity of the total storage space and increase the computational efficiency of the unit recommendation information included in the target group by converting the unit recommendation information for the target group into relatively lightweight hash data and storing it.

[0121] On the other hand, if multiple unit recommendation information is evenly distributed across the entire target group rather than a specific target group, the server (100) can convert all unit recommendation information into hash data and store it. As a result, the server (100) can reduce storage space and increase computational efficiency even when the computation for identifying recommended travel destinations for target users is not concentrated only on a specific target group due to the distribution ratio of unit recommendation information.

[0122] Furthermore, for target groups identified above a threshold ratio, the server (100) may generate and store a single representative hash data instead of converting all unit recommendation information constituting the target group into hash data and storing it. Through this, the server (100) may further increase capacity reduction and computational efficiency.

[0123] Specifically, the server (100) can calculate an average similarity based on the similarity between all unit recommendation information included in the target group, and if the average similarity is greater than or equal to a preset threshold value, it can generate and store representative hash data.

[0124] For example, the server (100) can obtain the average similarity by averaging all of the multiple cosine similarities calculated for a pair of vectors consisting of a third vector that matches each of the two unit recommendation information.

[0125] In addition, the server (100) may obtain representative hash data and store it instead of multiple unit recommendation information by hashing the average third vector obtained by averaging each third vector of all unit recommendation information included in the target group, hashing the third vector with the highest average value of similarity with other third vectors, or hashing the third vector corresponding to (or closest to the center point of) each target group identified within the vector space according to clustering techniques such as the K-means algorithm described above, but is not limited to the methods described above.

[0126] The operation of the server (100) that generates the aforementioned representative hash data is intended to prevent a decrease in computational efficiency and waste of storage space caused by the indexing process, etc., when unit recommendation information within a target group is similar to each other and has almost no differentiation.

[0127] FIG. 8 is a drawing for explaining the configuration of a server according to one embodiment of the present disclosure.

[0128] According to FIG. 8, the server (100) may include memory (110), a communication unit (120), and a processor (130).

[0129] The memory (110) is configured to store at least one instruction or data related to an operating system (OS) for controlling the overall operation of the components of the server (100) and the components of the server (100).

[0130] The memory (110) may include non-volatile memory such as ROM or flash memory, and may include volatile memory (110) composed of DRAM, etc. Additionally, the memory (110) may include at least one storage medium capable of storing data permanently or semi-permanently, such as a flash memory device, a hard disk drive (HDD), a solid state drive (SSD), a DVD, or a laser disc.

[0131] The memory (110) receives and stores travel destination review information about travel destinations experienced by users in the past from multiple users, and when a user response requesting a travel destination recommendation is received, it may include at least one instruction for identifying a travel destination suitable for the user based on the previously entered travel destination review information.

[0132] The communication unit (120) is configured for the server (100) to communicate with an external device, such as a user terminal (200) or an external server. At this time, the communication unit (120) may include circuits, modules, chips, etc., for performing communication using various wired or wireless communication methods. The communication unit (120) may also be connected to external devices through various networks.

[0133] Depending on the area or scale, a network may be a Personal Area Network (PAN), Local Area Network (LAN), Wide Area Network (WAN), etc., and depending on the openness of the network, it may be an Intranet, Extranet, or Internet, etc.

[0134] The communication unit (120) can be connected to external devices through various wireless communication methods such as LTE (long-term evolution), LTE-A (LTE Advance), 5G (5th Generation) mobile communication, CDMA (code division multiple access), WCDMA (wideband CDMA), UMTS (universal mobile telecommunications system), WiBro (Wireless Broadband), GSM (Global System for Mobile Communications), DMA (Time Division Multiple Access), WiFi (Wi-Fi), WiFi Direct, Bluetooth, BLE (Bluetooth Low Energy), NFC (near field communication), Zigbee, LoRa, etc.

[0135] Additionally, the communication unit (120) may be connected to external devices via wired communication methods such as Ethernet, an optical network, USB (Universal Serial Bus), and Thunderbolt.

[0136] In addition, the communication unit (120) may be configured to utilize various communication methods / technologies that are newly devised in the future.

[0137] In addition, the communication unit (120) is not limited to performing a communication connection in one way, but can perform communication connections in multiple ways, such as a wireless method and a wired method.

[0138] The processor (130) is configured to control the server (100) overall. Specifically, the processor (130) can perform operations according to various embodiments of the present disclosure by being connected to the memory (110) and executing at least one instruction stored in the memory (110).

[0139] For example, the processor (130) can control one or any combination of other components of the server (100) and can perform operations or data processing related to communication.

[0140] When a method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by a single processor or by a plurality of processors. For example, when a first operation, a second operation, and a third operation are performed by a method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first processor, or the first operation and the second operation may be performed by a first processor (e.g., a general-purpose processor) and the third operation may be performed by a second processor (e.g., an artificial intelligence dedicated processor).

[0141] The processor (130) may be implemented as a single-core processor including one core, or as one or more multicore processors including multiple cores (e.g., homogeneous multicore or heterogeneous multicore). When the processor is implemented as a multicore processor, each of the multiple cores included in the multicore processor may include internal processor memory such as on-chip memory, and a common cache shared by the multiple cores may be included in the multicore processor. Additionally, each of the multiple cores included in the multicore processor (or some of the multiple cores) may independently read and execute program instructions for implementing a method according to one embodiment of the present disclosure, or all (or some) of the multiple cores may be linked together to read and execute program instructions for implementing a method according to one embodiment of the present disclosure.

[0142] In this case, if the method according to one embodiment of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one of the plurality of cores included in a multi-core processor, or may be performed by a plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by the method according to one embodiment, the first operation, the second operation, and the third operation may all be performed by a first core included in a multi-core processor, or the first operation and the second operation may be performed by a first core included in a multi-core processor and the third operation may be performed by a second core included in a multi-core processor.

[0143] The processor (130) may include a general-purpose processor such as a CPU, AP, DSP (Digital Signal Processor), a graphics-dedicated processor such as a GPU, VPU (Vision Processing Unit), or an artificial intelligence-dedicated processor such as an NPU. An artificial intelligence-dedicated processor may be designed with a hardware structure specialized for training or utilizing a specific artificial intelligence model.

[0144] Meanwhile, the various embodiments described above may be implemented by combining two or more embodiments, provided that they do not conflict or contradict each other.

[0145] Meanwhile, the various embodiments described above may be implemented in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof.

[0146] According to hardware implementation, the embodiments described in this disclosure may be implemented using at least one of ASICs (Application Specific Integrated Circuits), DSPs (digital signal processors), DSPDs (digital signal processing devices), PLDs (programmable logic devices), FPGAs (field programmable gate arrays), processors, controllers, microcontrollers, microprocessors, and other electrical units for performing functions.

[0147] In some cases, the embodiments described herein may be implemented as the processor itself. In a software implementation, embodiments such as the procedures and functions described herein may be implemented as separate software modules. Each of the aforementioned software modules may perform one or more functions and operations described herein.

[0148] Meanwhile, computer instructions or computer programs for performing processing operations in electronic devices, such as robots and servers, according to the various embodiments of the present disclosure described above, may be stored on a non-transitory computer-readable medium. When such computer instructions or computer programs stored on the non-transitory computer-readable medium are executed by the processor of a specific device, the specific device described above performs the processing operations in the electronic device according to the various embodiments described above.

[0149] A non-transient computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, unlike media that store data for a short period of time such as registers, caches, and memory. Specific examples of non-transient computer-readable media include CDs, DVDs, hard disks, Blu-ray discs, USBs, memory cards, and ROMs.

[0150] Although preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above. It is understood that various modifications can be made by those skilled in the art without departing from the essence of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical spirit or perspective of the present disclosure. Explanation of the symbols

[0151] 1000 : Travel Destination Recommendation System 100: Server 110: Memory 120: Communications Department 130: Processor 200: User terminal

Claims

Claim 1 A method of operation of a server providing a travel destination recommendation service comprises: a step of acquiring background information for each user, including the tendencies, preferred travel regions, and personal information of each of a plurality of users; a step of generating and storing unit recommendation information based on the background information and the travel destination review information for each of the plurality of users who have provided travel destination review information; and a step of identifying at least one recommended travel destination for a target user based on the plurality of unit recommendation information and providing it to the target user; wherein the step of generating and storing unit recommendation information includes: a step of acquiring a first vector in which the background information is vectorized; and a step of acquiring a second vector in which the travel destination review information is vectorized. A method of operation of a server comprising: a step of storing a third vector, which is a combination of the first vector and the second vector, as unit recommendation information; wherein the step of storing the third vector as unit recommendation information comprises: a step of grouping the unit recommendation information to create at least one target group if the number of the stored unit recommendation information is greater than or equal to a preset threshold value; a step of calculating a ratio of the number of unit recommendation information constituting the target group to the unit recommendation information; a step of converting a plurality of unit recommendation information included in the identified target group into hash data if the calculated ratio is greater than or equal to a preset threshold ratio and a target group is identified; and a step of converting all of the unit recommendation information into hash data if the calculated ratio is greater than or equal to a preset threshold ratio and a target group is not identified. Claim 2 A method of operation of a server according to claim 1, wherein the step of acquiring background information for each user comprises the step of acquiring the background information according to at least one user response obtained as a result of providing a plurality of query items to the user. Claim 3 A method of operation of a server according to claim 1, wherein the step of generating and storing unit recommendation information comprises: identifying at least one emotion keyword from text included in the travel destination review information; identifying the user's emotional state for each of the travel destination review information based on the identified emotion keyword; and, when the travel destination review information is identified as having a positive emotional state, generating unit recommendation information including both the background information and the travel destination review information. Claim 4 A method of operation of a server according to claim 3, wherein the step of identifying and providing the recommended travel destination to the target user comprises: identifying at least one unit recommendation information among the plurality of unit recommendation information that matches the background information of the target user when the target user is a first user corresponding to a new user; and selecting a travel destination included in the travel destination review information that matches the identified unit recommendation information as the recommended travel destination. Claim 5 A method of operation of a server according to claim 4, wherein the step of identifying at least one unit recommendation information that matches the background information of the target user comprises generating virtual recommendation information that includes virtual travel destination review information that matches the positive emotional state in the background information of the target user, and identifying unit recommendation information that matches the virtual recommendation information. Claim 6 A method of operation of a server according to claim 3, wherein the step of identifying and providing the recommended travel destination to the target user comprises: identifying at least one unit recommendation information previously generated for the target user when the target user is a second user corresponding to an existing user; and identifying a travel destination that matches the travel destination review information included in the identified unit recommendation information as the recommended travel destination. Claim 7 delete Claim 8 delete

Images