Lease management server performing marketing activities using customized lease banner advertisements for website users and operating method thereof

Abstract

A rental management operation server is disclosed, configured to provide banner advertisements for advertising rental properties posted on a website. The rental management operation server comprises a property information storage unit configured to store information about rental properties, a website information storage unit configured to store information about websites, an optimal property determination unit configured to determine an optimal rental property among rental properties that matches the attributes of each website, and a banner advertisement management unit configured to provide banner advertisements for advertising the determined optimal rental property. The optimal property determination unit determines the optimal rental property using a pre-supervised neural network, wherein the neural network is supervised using data on the operation results of banner advertisements for various rental properties posted on multiple websites as ground truth data, and data on the site characteristics of the corresponding websites and the property characteristics of the rental properties as problem data.

Description

Technology Field

[0001] Embodiments of the present invention relate to a rental management operation server that performs marketing activities using rental banner advertisements customized for website users, and a method of operating the same. Background Technology

[0002] With the recent increase in single-person households and the diversification of residential forms, the size of the rental market is continuously expanding, and consequently, the number of rental management companies providing professional rental management services is also steadily increasing. In line with these changes, there is a growing need for the role of rental management to expand beyond simple rent collection and complaint handling to include more active rental support functions. In particular, despite the growing importance of marketing activities to proactively attract tenants driven by landlords' demand to reduce vacancy risks and secure stable revenue, existing rental management systems often remain limited to a passive brokerage role in tenant management, failing to meet the actual needs of landlords. The problem to be solved

[0003] The objective of the present invention, which is to solve the above-mentioned problems, is to provide a rental management operation server that performs marketing activities using rental banner advertisements customized for website users, and a method for operating the same. means of solving the problem

[0004] A rental management operation server configured to provide banner advertisements for advertising rental properties posted on a website according to embodiments of the present invention comprises a property information storage unit configured to store information about rental properties, a website information storage unit configured to store information about websites, an optimal property determination unit configured to determine an optimal rental property that matches the attributes of each website among the rental properties, and a banner advertisement management unit configured to provide banner advertisements for advertising the determined optimal rental property, wherein the optimal property determination unit determines the optimal rental property using a neural network that has been supervised and learned in advance, and the neural network is supervised and learned using data on the operation results of banner advertisements for various rental properties posted on multiple websites as correct data, and data on the site characteristics of the corresponding websites and the property characteristics of the rental properties as problem data. Effects of the invention

[0005] According to embodiments of the present invention, the embodiments of the present invention have the effect of enabling marketing activities for supplying tenants.

[0006] According to embodiments of the present invention, by determining an optimal rental property corresponding to the preferences of users of a website through the attributes or characteristics of various websites and providing information about the determined optimal rental property as a banner advertisement, it is possible to perform more effective tenant marketing. Brief explanation of the drawing

[0007] FIG. 1 shows a rental management system according to embodiments of the present invention. FIG. 2 shows a rental management operation server according to embodiments of the present invention. FIG. 3 is a drawing for explaining a banner advertisement according to embodiments of the present invention. FIG. 4 is a diagram illustrating the operation of an optimal product determination unit according to embodiments of the present invention. FIG. 5 is a diagram illustrating a site characteristic vector according to embodiments of the present invention. FIG. 6 is a diagram illustrating a property characteristic vector according to embodiments of the present invention. FIG. 7 is a diagram showing the operation of a rental management operation server according to embodiments of the present invention. FIG. 8 is a diagram illustrating the operation of a recommended listing marketing unit according to embodiments of the present invention. Specific details for implementing the invention

[0008] The present invention is susceptible to various modifications and may have various embodiments; specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. Similar reference numerals have been used for similar components in the description of each drawing.

[0009] Terms such as first, second, A, B, etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of a plurality of related described items or any of a plurality of related described items.

[0010] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0011] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to specify the presence 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.

[0012] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0013] The server referred to in the present invention may be constructed as a server performing at least one of the roles of a web server, a database server, and a mobile server; for example, it may display processed results on a webpage via an online network or receive necessary input data through a website. Here, a webpage should be understood as a page that includes text, images, sound, and video, as well as a page where software for performing specific tasks, such as a web application, is loaded. Furthermore, the server may perform at least one of the functions of a web application server, a web server, a mobile server, and a database server on a single physical server, or it may be composed of and operated by multiple physically separated servers. However, it is not limited thereto, and the type of server can be varied to a level obvious to a person skilled in the art.

[0015] Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

[0016] FIG. 1 illustrates a rental management system according to embodiments of the present invention. Referring to FIG. 1, the rental management system (10) includes a rental management operation server (100) and provides services to a lessor (LL) and a lessee (USR) using the rental management operation server (100).

[0017] The rental management system (10) is entrusted with the management of rental properties by the lessor (LL) and provides overall rental management services for the rental properties. According to embodiments, the rental management system (10) provides various services for rental properties, such as tenant supply, move-in / contract management, move-out / vacancy management, facility supervision, and sale / purchase consulting. Furthermore, the rental management system (10) may also provide services such as proposals for the construction of rental properties in specific areas through market research on various regions, even before the construction of rental properties. For example, the lessor (LL) can register their rental properties on the rental management operation server (100) and receive overall rental management services for the registered rental properties. At this time, the rental management operation server (100) may provide information related to services for rental properties to the lessor (LL)'s terminal.

[0018] Additionally, the rental management system (10) can recommend rental properties suitable for a user (USR), who is a potential tenant, and thereby facilitate the supply of tenants to the landlord (LL). That is, the rental management system (10) can improve the likelihood of concluding a rental contract by providing information about the rental property to a user (USR) who is likely to be interested in the registered rental property.

[0019] According to embodiments of the present invention, a rental management operation server (100) can determine a type of rental property (i.e., an optimal rental property) that matches the type of users of various websites on the internet. Through this, the rental management operation server (100) can enable banner advertisements displaying information about the optimal rental property to be posted and operated on each website. Accordingly, users of each website can easily check advertisements for rental properties that suit their preferences. As a result, this can reduce the vacancy rate of the landlord.

[0020] FIG. 2 illustrates a rental management operation server according to embodiments of the present invention. Referring to FIG. 2, the rental management operation server (100) includes a property information storage unit (110), a website information storage unit (120), an optimal property determination unit (130), and a banner advertisement management unit (140).

[0021] The rental management operation server (100) is a device having computational processing capabilities, and may be, for example, a computing device (e.g., a server) including a processor and memory, but is not limited thereto.

[0022] The property information storage unit (110) stores information about rental properties managed or to be managed by the rental management operation server (100). According to embodiments, the property information storage unit (110) may store information about various rental properties, such as the region, size, type, rent, deposit, and contract period.

[0023] The property information storage unit (110) may store information about a rental property transmitted from the lessor's (LL) terminal, or may store information about a rental property transmitted from a third party's terminal. In this case, the third party may be an employee managing the rental property.

[0024] The website information storage unit (120) can store information about various websites online. According to embodiments, the website information storage unit (120) can store information about websites where banner advertisements for rental properties managed or to be managed by the rental management operation server (100) will be posted. According to embodiments, the website information storage unit (120) can store information about the category, regional dependency, return visit rate, and banner location on each website.

[0025] Additionally, the website information storage unit (120) may collect and / or store data regarding the behavior of users who have visited the website. For example, data regarding the behavior of users after their visit may be collected through a third-party cookie technique, but is not limited thereto.

[0026] Additionally, the website information storage unit (120) can store data regarding the content (text and / or images) included in each website. For example, the website information storage unit (120) can store information regarding the types and frequencies of keywords listed in each website by crawling each website.

[0027] For example, the website information storage unit (120) may be the website of the counterparty that has entered into an advertising contract for a banner advertisement managed by the rental management operation server (100).

[0028] The optimal listing determination unit (130) can determine the optimal rental listing that matches the banner advertisement corresponding to each website among the rental listings managed by the rental management operation server (100). According to embodiments, the optimal listing determination unit (130) can determine the optimal rental listing suitable for the preferences or needs of the users of each website for each website. Information regarding the determined optimal rental listing can be advertised on the website in the form of a banner advertisement.

[0029] That is, according to the embodiments of the present invention, by determining an optimal rental property corresponding to the preferences of the users of a website through the attributes or characteristics of each website and providing information about the determined optimal rental property as a banner advertisement, it is possible to perform more effective tenant marketing.

[0030] The banner advertisement management unit (140) can manage banner advertisements posted or to be posted on each website. According to embodiments, the banner advertisement management unit (140) can enable banner advertisements corresponding to the optimal rental listing determined by the optimal rental listing determination unit (130) to be posted on each website. According to embodiments, the banner advertisement management unit (140) can transmit the banner advertisement of the optimal rental listing to a server operating the corresponding website.

[0031] In this specification, the term "banner advertisement for an optimal rental listing" refers to an object that enables visual verification of information regarding an optimal rental listing. A banner advertisement may be posted at a designated location on a website. Users of the website may obtain information regarding an optimal rental listing through the banner advertisement, and furthermore, may access a listing page that posts information regarding the optimal rental listing by clicking on the banner advertisement. In this specification, the term "creating a banner advertisement" means creating data corresponding to an image or text and / or a hyperlink that constitutes the banner advertisement.

[0032] At this time, the banner ad management unit (140) may directly generate a banner ad corresponding to the optimal rental listing, or select a banner ad corresponding to the optimal rental listing from among the banner ads stored. For example, it may obtain information corresponding to the optimal rental listing from among the information of rental listings stored in the listing information storage unit (110) and generate a banner ad corresponding to the obtained optimal rental listing. For example, the banner ad management unit (140) may generate an image and text representing information about the optimal rental listing and generate a banner ad using the image and text, but is not limited thereto.

[0033] The banner ad management unit (140) can receive information regarding the operational performance of banner ads posted on each website. For example, the operational performance of a banner ad may include the click-through rate of the banner ad and user activity on the listing page linked to the banner ad.

[0034] FIG. 3 is a diagram illustrating a banner advertisement according to embodiments of the present invention. Referring to FIG. 3, a predetermined website (WS) is shown. The website (WS) is an online space hosted by a predetermined operating server and contains various data. A user accesses the website (WS) through an electronic device such as a user terminal and can visually view the website (WS) through a display (display device) connected to the user terminal. The following description is based on the website (WS) that the user visually views.

[0035] The area where the website (WS) is displayed includes a content area (CA) where certain content (text, images, etc.) is displayed and a banner advertisement area (BA) where banner advertisements are displayed. The content area (CA) is an area that displays data intended to be displayed on the website, such as text or images, and the banner advertisement area (BA) may be an area where banner advertisements (AD) managed by a rental management operation server (100) according to embodiments of the present invention are displayed. The banner advertisement area (BA) may be placed in a certain area of ​​the website (WS), and embodiments of the present invention are not limited to that location.

[0036] FIG. 4 is a diagram illustrating the operation of an optimal property determination unit according to embodiments of the present invention. Referring to FIG. 4, the optimal property determination unit (130) inputs an input vector (VIN) into a neural network (131) that has been supervised learning in advance and can obtain an output vector (VOUT). To this end, the neural network (131) can be supervised learning in advance.

[0037] The input vector (VIN) includes a site characteristic vector related to the characteristics of the website and a property characteristic vector related to the characteristics of the rental properties advertised through the banner ads on that website. The output vector (VOUT) represents the performance (advertising performance, operational performance) of the banner ads on that website.

[0038] Here, the training data may be actual data collected (or observed) over a predetermined period. According to embodiments of the present invention, the neural network (131) may be trained using training data based on the results of banner advertisements for rental listings actually conducted on various websites over a predetermined period. According to embodiments, the neural network (131) may be trained in the following manner: training is performed by configuring the results of banner advertisements for various rental listings posted on various websites as correct data, and the site characteristic vectors for the corresponding websites and the listing characteristic vectors for the rental listings as problem data.

[0039] The neural network (131) is trained in advance with such training data, and when an input vector for any website and rental property is input, it outputs the operational performance (i.e., expected) of the banner advertisement for the website and rental property as an output vector (VOUT). The neural network (131) trained in this manner is utilized by the optimal property determination unit (130).

[0040] When the optimal property determination unit (130) determines a website for banner advertising (e.g., a target website), it calculates a site characteristic vector for the website and calculates a property characteristic vector for rental properties requiring current tenant advertising, and then combines them to generate input vectors (VIN). The optimal property determination unit (130) determines an output vector (VOUT) corresponding to the input vectors (VIN), that is, input vectors with high operational performance based on operational performance, i.e., optimal input vectors. Subsequently, the optimal property determination unit (130) can determine at least one rental property among the rental properties with high operational performance as the optimal rental property.

[0041] The neural network (131) may include an input layer (131a), a hidden layer (131b), and an output layer (131c). The input layer (131a) may be composed of a number of input nodes equal to the number of components (i.e., dimensions) of the input vector (VIN).

[0042] The input layer (131a) can transmit an input vector (VIN) to the hidden layer (131b). According to embodiments, the input layer (131a) may generate an intermediate vector by applying one or more connection strength values ​​corresponding to each of the input nodes and transmit the generated intermediate vector to the hidden layer (131b). One or more connection strength values ​​may be set to arbitrary initial values ​​and then continuously updated through supervised learning.

[0043] The hidden layer (131b) learns the characteristics of the input vector (VIN) (or intermediate vector) transmitted from the input layer (131a) and, as a result of the learning, can output a characteristic vector corresponding to the input vector (VIN). For example, the characteristic vector may be a value that reflects the relationship between the input vectors (VIN).

[0044] According to embodiments, the hidden layer (131b) includes a plurality of hidden nodes and can transmit a feature vector generated by applying one or more connection strengths corresponding to each of the hidden nodes to an input transmitted to the input layer (131a) to the output layer (131c). At this time, the initial values ​​of the one or more connection strength values ​​corresponding to each of the hidden nodes included in the hidden layer (131b) are set to arbitrary values ​​and can be updated as training data is continuously supervised.

[0045] The output layer (131c) determines the output vector (VOUT) by applying an activation function to the feature vector received from the hidden layer (131b). At this time, the artificial neural network (131) is trained by comparing the output vector (VOUT) obtained from the output layer (131c) according to the input result of the training input data with the paired training output data. For example, the artificial neural network (131) can be supervised learning by continuously updating the connection strength values ​​of each node based on a loss function so that the loss function value between the output vector (VOUT), which is the predicted value of the training model, and the training output data is minimized.

[0046] FIG. 5 is a diagram illustrating a site characteristic vector according to embodiments of the present invention. Referring to FIG. 5, the site characteristic vector (SPV) may have values ​​related to each attribute of a website as components. For example, the components of the site characteristic vector (SPV) represent the category, location-basedness, return visit rate, banner location, and lease relevance of the website.

[0047] The categories of a website indicate the field or nature of the website and may include classifications such as IT, portal, parenting, and politics.

[0048] The geographical basis of a website indicates whether it is created to target a specific region, and it can be regionally based or nationally based. For example, a community website for a specific region might be regionally based.

[0049] The return rate of a website is a value indicating the extent to which visitors return to the website, and it can be calculated in various ways. For example, the return rate may be calculated as the proportion of total visitors who have visited two or more times within a certain period, or as the number of times a single user has visited during a specific period, but it is not limited to these methods.

[0050] The banner location on a website refers to the position where banner advertisements are displayed on the website, and can be classified as left, right, top, or bottom, but is not limited thereto.

[0051] The lease relevance of a website is an indicator representing the degree to which the website is related to a lease, and is based on the extent to which the content of the website visited by users who visited the website (i.e., the 'target website') prior to visiting the website (i.e., the 'previous website') was related to the lease, and the distance between the currently visited website and the previous website.

[0052] For example, the lease relevance for a website can be calculated according to the following mathematical formula 1.

[0053]

[0054] Here, R is the lease relevance for the website (i.e., the target website), a is a positive constant between 0 and 1, CR is the lease content relevance of the website, and HCR is the lease content relevance of a previous website visited by users who visited the website before visiting the website.

[0055] Here, the relevance of leased content to the website can be calculated according to Equation 2 below.

[0056]

[0057] Here, CR is the lease content relevance for the website, and f k is the frequency of the keyword k related to lease on websites, N is the number of sample websites, and df k... is the number of websites among the sample websites that contain at least a predetermined standard number of keywords k. And K is the entire set of keywords k related to lease. For example, keywords k may be 'jeonse', 'monthly rent', 'moving', etc., but are not limited thereto and may be defined in a dictionary format.

[0058] Meanwhile, the relevance of the leased content of the previous website can be calculated according to the mathematical formula 3 below.

[0059]

[0060] Here, HCR is the relevance of leased content on previous websites visited by users who visited the target website prior to visiting the target website, and CR j is the lease content relevance of the j-th previous website, and J is the total number of previous websites. b is a positive constant, and s j is the distance between the target website and the j-th previous website.

[0061] Here, s j represents the number of visits taken to visit the target website from the j-th previous website; if the visit was made directly from the j-th previous website to the target website, s j becomes 1.

[0062] In other words, the relevance of leased content from adjacent previous websites is reflected relatively strongly, whereas the relevance of leased content from previous websites visited multiple times (i.e., distant) is reflected relatively less.

[0063] Meanwhile, if the number of previous websites visited by users visiting the website is large, the overall relevance may be low. In this case, the relevance of the leased content of the previous websites can be calculated according to Equation 4, which further refines Equation 3.

[0064]

[0065] Here, T is a universality index representing the universality of the target website, and is a positive integer greater than or equal to 0.

[0066] Site Feature Vectors (SPVs) can be generated by embedding values ​​corresponding to the aforementioned website attributes. In this case, the embedding method may vary depending on the characteristics of each field. For example, fields with real values, such as return visit rates or lease relevance, may have their values ​​embedded directly as components of the vector; however, for discrete (or categorical) values, such as categories, location-basedness, or banner placement, values ​​transformed in an appropriate manner may be embedded as components of the vector.

[0067] FIG. 6 is a diagram illustrating a property characteristic vector according to embodiments of the present invention. Referring to FIG. 6, the property characteristic vector (UPV) may have values ​​related to the attributes of each rental property as components. For example, the components of the rental property vector (RUV) may represent the proximity, size, type, and rent of the rental property.

[0068] Here, the proximity of a rental property refers to the relative distance between the area where the rental property is located and the user's access area. For example, the distance between two areas can be expressed in four stages: 'close', 'average', 'far', and 'very far', but is not limited to these.

[0069] The floor area of ​​a rental property refers to the exclusive area of ​​the property. For example, if the exclusive area of ​​the rental property is 17m² 2 Less than, 17 m 2 More than 33 m 2 Whether less than, 33 m 2 Over 59 m 2 Whether less than, 59 m 2 Over 84 m 2 It may indicate whether it is less than, but is not limited to this, and may also indicate a specific equilibrium value.

[0070] The type of rental property refers to the type of residence of the property, which can indicate whether it is an apartment, villa, officetel, etc.

[0071] The rent of a rental property indicates the level of rent of the said rental property, and can indicate whether the rent of the rental property is lower, average, or higher than the average rent of surrounding rental properties. In this case, the range of rental properties considered when calculating the average rent may be defined as properties within a specified distance from the said rental property. Here, the specified range may be based on two subway stations or a radius of 2 km, but is not limited thereto.

[0072] A Property Feature Vector (UPV) can be generated by embedding values ​​corresponding to the attributes of the aforementioned rental properties. In this case, the embedding method may vary depending on the characteristics of each field. For example, fields that reflect high or low values, such as proximity, size, or rent, can be embedded as components of the vector while maintaining the relative magnitudes of the values; however, in the case of categorical values ​​such as type, values ​​transformed in an appropriate manner can be embedded as components of the vector.

[0073] FIG. 7 illustrates the operation of a rental management operation server according to embodiments of the present invention. Referring to FIG. 7, the rental management operation server (100) calculates a site attribute vector for a given website (S110). According to embodiments, the rental management operation server can calculate a site attribute vector for a website where a banner advertisement is to be posted.

[0074] The rental management operation server (100) calculates a property characteristic vector for rental properties (S120). According to embodiments, the rental management operation server (100) can calculate a property characteristic vector for each rental property that requires tenant advertising.

[0075] The rental management operation server (100) calculates the operational performance of each banner advertisement for each rental listing on the website using a site attribute vector and a listing characteristic vector (S130). According to embodiments, the rental management operation server (100) can calculate the operational performance of each banner advertisement for each rental listing on the website by inputting into a pre-trained neural network (131). This has been explained with reference to FIG. 4.

[0076] The rental management operation server (100) determines the optimal rental property to be advertised on the website based on the operational performance of each banner advertisement for the rental property on the website (S140). According to the embodiments, the rental management operation server (100) may determine a rental property with operational performance above a predetermined standard as the optimal rental property, but is not limited thereto.

[0077] The rental management operation server (100) generates a banner advertisement for an optimal rental property (S150). According to embodiments, the rental management operation server (100) may generate text and / or images that constitute a banner advertisement for a determined optimal rental property. Additionally, the rental management operation server (100) may provide the generated banner advertisement, or related data, to an operation server corresponding to the website (or an ad management server that manages advertisements for the website) so that the banner advertisement is posted on the website.

[0079] FIG. 8 is a diagram illustrating the hardware configuration of a rental management operation server according to embodiments of the present invention. The electronic device (300) of FIG. 8 represents the rental management operation server (100) described with reference to FIG. 1 to 7.

[0080] Referring to FIG. 8, the electronic device (300) may include at least one processor (310) and a memory (320) that stores instructions that instruct the at least one processor (310) to perform at least one operation.

[0081] The above at least one operation is interpreted to include at least one of the operations of the aforementioned electronic device (300) or the operations of the functional part, and a specific description is omitted to prevent redundant explanation.

[0082] Here, at least one processor (310) may mean a central processing unit (CPU), a graphics processing unit (GPU), or a dedicated processor on which methods according to embodiments of the present invention are performed.

[0083] The memory (320) may be composed of at least one of a volatile storage medium and a non-volatile storage medium. For example, the memory (320) may be composed of at least one of a read-only memory (ROM) and a random access memory (RAM).

[0084] Additionally, the electronic device (300) may include a transceiver (330) that performs communication via a wireless network. Additionally, the electronic device (300) may further include an input interface device (340), an output interface device (350), a storage device (360, which may be referred to interchangeably with internal storage), etc. Each component included in the electronic device (300) may be connected by a bus (370) to communicate with one another.

[0085] The methods according to the present invention 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 alone or in combination. The program instructions recorded on the computer-readable 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.

[0086] Examples of computer-readable media may include hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions may 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. The aforementioned hardware devices may be configured to operate as at least one software module to perform the operation of the present invention, and vice versa.

[0087] In addition, the above-described method or device may be implemented by combining all or part of its configuration or function, or by implementing it separately.

[0088] Although the present invention has been described above with reference to preferred embodiments, those skilled in the art will understand that various modifications and changes can be made to the invention without departing from the spirit and scope of the invention as described in the following claims.

Claims

Claim 1 A rental management operation server configured to provide banner advertisements for advertising rental properties posted on a website, comprising: a property information storage unit configured to store information about rental properties; a website information storage unit configured to store information about websites; and an optimal property determination unit configured to determine, among the rental properties, an optimal rental property that matches the attributes of each website. The system includes a banner ad management unit configured to provide banner ads for advertising the determined optimal rental property, wherein the optimal property determination unit determines the optimal rental property using a pre-supervised neural network, wherein the neural network is supervised learning using data on the operation results of banner ads for various rental properties posted on multiple websites as ground truth data, and data on the site characteristics of the corresponding websites and the property characteristics of the rental properties as problem data, wherein the property information storage unit stores information on the location, size, type, and rent level of rental properties, and the website information storage unit stores information on the category, location-basedness, return visit rate, banner location, and content of the websites, and wherein the optimal property determination unit calculates a site characteristic vector for the target website where the banner ad is to be posted, calculates a property characteristic vector for the rental properties requiring advertising, and inputs an input vector including the site characteristic vector and the property characteristic vector into the neural network to calculate the expected operation performance of banner ads for rental properties on the target website, and determines the optimal rental property among the rental properties requiring advertising based on the calculated operation performance. Determined, wherein the above-mentioned site characteristic vector has the category, location-basedness, return visit rate, banner location, and lease relevance of the above-mentioned target website as components, and the above-mentioned lease relevance is an indicator representing the degree to which the above-mentioned target website is related to a lease, and is determined according to the following mathematical formula 1, [Mathematical Formula 1] (In the above Equation 1, R is the lease relevance to the target website, a is a positive constant between 0 and 1, CR is the lease content relevance of the target website, and HCR is the lease content relevance of a previous website, which is a website visited by a user who visited the target website before visiting the target website) The lease content relevance of the target website is determined according to the following Equation 2, [Equation 2] (In the above mathematical formula 2, CR is the lease content relevance to the above target website, and f k is the frequency of the keyword k related to lease on websites, N is the number of sample websites, and df k is the number of websites among the sample websites that contain at least a predetermined standard number of keyword k, and K is the entire set of keywords k predefined in relation to lease) lease management operation server. Claim 2 delete Claim 3 delete

Images