JP7430205B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

Conventionally, as a form of information distribution using networks such as the Internet, search processing is performed based on arbitrary search conditions specified by the user, and properties (for example, goods, real estate, etc.) obtained by the search processing are There is a known technology for listing items based on criteria and providing them to users. Furthermore, there is a known technology for classifying properties by extracting positive keywords from user reviews and the like (for example, see Patent Document 1).

JP2012-79247A

However, when applying the technology described in Patent Document 1 mentioned above to extract feature labels added to property information, feature labels may not be extracted for properties with no posts or few posts. be.

The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can more appropriately extract characteristic labels added to property information. purpose.

The information processing device according to the present application includes an information acquisition section and a feature extraction section. The information acquisition unit acquires posted information, which is information posted by a user regarding the property, and advertisement information, which is information about an advertisement of the property by a vendor regarding the property. The feature extraction unit extracts information indicating the characteristics of the property as a feature label added to the property information based on the posted information and advertisement information acquired by the information acquisition unit.

According to one aspect of the embodiment, it is possible to more appropriately extract a characteristic label added to property information.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a diagram illustrating an example of the configuration of an information processing system including the information processing apparatus according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of an information processing device according to an embodiment. FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing apparatus according to the embodiment. FIG. 5 is a diagram illustrating an example of an advertisement information table stored in the property information storage unit of the information processing device according to the embodiment. FIG. 6 is a diagram illustrating an example of a posted information table stored in the property information storage unit of the information processing device according to the embodiment. FIG. 7 is a diagram illustrating an example of a feature label table stored in the feature label storage unit of the information processing device according to the embodiment. FIG. 8 is a diagram illustrating an example of property list information provided to the user by the information processing apparatus according to the embodiment and displayed on the user terminal. FIG. 9 is a flowchart illustrating an example of information processing by the processing unit of the information processing apparatus according to the embodiment. FIG. 10 is a flowchart illustrating an example of feature label extraction processing by the processing unit of the information processing device according to the embodiment. FIG. 11 is a flowchart illustrating an example of property information providing processing by the processing unit of the information processing device according to the embodiment. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, an information processing apparatus, an information processing method, and a form for implementing an information processing program (hereinafter referred to as an "embodiment") according to the present application will be described in detail with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. Moreover, each embodiment can be combined as appropriate within the range that does not conflict with the processing contents. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. An example of information processing]
FIG. 1 is a diagram showing an example of information processing according to an embodiment, and in this embodiment, an information processing method is executed by an information processing apparatus 1.

The information processing device 1 shown in FIG. 1 provides property information to the user _U1 . The property information provided to the user _U1 by the information processing device 1 is information obtained by adding a feature label to the property information. The property is, for example, movable property or real estate. The property is, for example, a property to be traded.

The businesses B ₁ to B _m are businesses related to properties, and when the property is real estate, the businesses B ₁ to B _m are, for example, real estate brokers. m is an integer of 2 or more. Although real estate will be described below as an example of a property, the property may be, for example, goods such as electrical appliances, clothes, shoes, furniture, ornaments, household goods, or books. Note that when the objects are goods, the businesses B ₁ to B _m are retailers, wholesalers, manufacturers, or the like.

Business operators B ₁ to B _m transmit advertisement information, which is information on advertisements for properties, from business terminals (not shown) to information processing device 1 via a network (not shown) (step S1). The information processing device 1 stores advertisement information transmitted from a business terminal (not shown) in a property information storage unit. The advertisement information is property information provided by business operators B ₁ to B _m in order to trade properties. Such advertisement information includes, for example, information on the outline of the property, information on details of the property, information on comments from businesses B ₁ to B _m , and the like.

Users U ₂ to U _n send information posted by users, such as word-of-mouth comments regarding properties that are transaction targets of businesses B ₁ to B _m , from user terminals (not shown) to information processing device 1 via a network (not shown). (Step S2). The information processing device 1 stores user-posted information transmitted from a user terminal (not shown) in a property information storage unit. User posts include, for example, comments and evaluation information of users U ₂ to U _n regarding properties.

The information processing device 1 adds information indicating the characteristics of the property to the property information based on the advertising information stored in the property information storage unit in addition to the posted information stored in the property information storage unit. It is extracted as a feature label (step S3). Thereby, the information processing apparatus 1 can more appropriately extract the characteristic label added to property information even for properties that have no user posts or few user posts.

For example, based on the posted information and advertisement information stored in the property information storage unit, the information processing device 1 generates a feature label among the property characteristics extracted from the posted information and the property characteristics extracted from the advertisement information. Determine the characteristics of the property to be extracted with priority.

For example, for a property where the number of posted information is greater than or equal to a preset number, the information processing device 1 sets the feature of the property to be preferentially extracted as a feature label to the feature of the property extracted from the posted information, and otherwise In this case, the characteristics of the property are extracted from the advertisement information. Thereby, the information processing device 1 can extract feature labels even for properties where the number of posted information is small and it is difficult to extract feature labels.

Furthermore, the information processing device 1 extracts positive features as feature labels from among the property features extracted from the advertisement information and the property features extracted from the posted information. Thereby, the information processing device 1 can extract characteristic labels that can actively promote the property to the users U ₁ to U _n who search for the property.

Furthermore, if the property characteristics extracted from the advertisement information and the property characteristics extracted from the posted information are contradictory to each other, the information processing device 1 gives priority to the property characteristics extracted from the advertisement information. Extract as a feature label. Thereby, the information processing device 1 can extract a more appropriate feature label even when there is no appropriate expression for extracting a feature label in a user post.

The information processing device 1 performs information processing to provide property information to the user _U1 (step S4). When providing property information to the user U ₁ , the information processing device 1 provides the user U ₁ with property information in which a characteristic label is added to the property information.

In the example shown in FIG. 1, property information in which characteristic labels such as "comfortable to live in" and "close to the station and convenient" are added to the property information is provided to the user _U1 . Thereby, the user U ₁ can easily know the characteristics of the property, and for example, it is possible to improve the convenience when the user U ₁ selects a property.

[2. Information processing system configuration]
FIG. 2 is a diagram illustrating an example of the configuration of an information processing system including the information processing apparatus according to the embodiment. As shown in FIG. 2, the information processing system 100 according to the embodiment includes an information processing device 1, user terminals 2 ₁ , 2 ₂ , ..., 2 _n , and business terminals 3 ₁ , ..., 3. _m . n is an integer of 3 or more, and m is an integer of 2 or more.

The information processing device 1, user terminals 2 ₁ , 2 ₂ , ..., 2 _n , and business terminals 3 ₁ , 3 ₂ , ..., 3 _m are connected to a communication network 4 . It is possible to send and receive information to each other via the .

The communication network 4 is, for example, a network including a WAN (Wide Area Network) such as the Internet. Note that the communication network 4 has a configuration including, for example, a mobile communication system such as 4G (4th Generation) or 5G (5th Generation), but is not limited to such an example.

The user terminals 2 ₁ , 2 ₂ , ..., 2 _n are terminal devices operated by users U ₁ , U ₂ , ..., _Un who use the services provided by the information processing device 1, For example, a personal computer, a tablet, or a smartphone. _In the following, when _each of _the user terminals 2 ₁ , 2 _{2 ,} . When each is shown without being distinguished individually, it may be written as user U.

The business terminals 3 ₁ , . . _. , 3 _m are terminal devices operated by the business operators B ₁ , . be. In the following _, when each of _the operator terminals 3 _{1 ,} . When shown without distinction, it may be written as Operator B.

Although the following description assumes that the property is real estate and business operator B is a real estate broker, the present invention is not limited to such an example. For example, if the object is a product, business B is, for example, a retailer, a wholesaler, or a manufacturer.

The business operator B operates the business terminal 3 to cause the business terminal 3 to execute a process of transmitting advertisement information, which is information about an advertisement for a property, to the information processing device 1 via the communication network 4. The advertisement information includes, for example, information on the outline of the property, information on the details of the property, information on comments from business operator B, and the like.

Hereinafter, the configuration of the information processing device 1 that performs such processing and the information processing system 100 including the information processing device 1 will be described in detail.

[3. Configuration of information processing device]
Next, the configuration of the information processing device 1 according to the embodiment will be described using FIG. 3. FIG. 3 is a diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication section 10, a storage section 11, and a processing section 12. Note that the information processing device 1 includes an input section (for example, a keyboard, a mouse, etc.) that accepts various operations from an administrator using the information processing device 1, and a display section (for example, a liquid crystal display, etc.) for displaying various information. ).

[3.1. Communication department 10]
The communication unit 10 is realized by, for example, a NIC (Network Interface Card). The communication unit 10 is connected to the communication network 4 by wire or wirelessly, and sends and receives information to and from the user terminal 2 and the operator terminal 3 via the communication network 4 .

[3.2. Storage unit 11]
The storage unit 11 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3, the storage unit 11 includes a user information storage unit 20, a property information storage unit 21, and a feature label storage unit 22.

[3.2.1. User information storage unit 20]
The user information storage unit 20 stores user information including information on users U ₁ , U ₂ , . . . , _Un . FIG. 4 is a diagram illustrating an example of a user information table stored in the user information storage unit of the information processing apparatus according to the embodiment.

As shown in FIG. 4, the user information table stored in the user information storage unit 20 includes "user ID (Identifier)", "user name", "attribute", "information provision history", "search history", etc. information for each user U. “User ID” is identification information unique to each user U. “User name” is information indicating the name of user U.

“Attribute” is information indicating the user U's attribute. The user U's attributes are user U's demographic attributes, psychographic attributes, and the like. The demographic attributes are demographic attributes of the user U. The psychographic attributes are attributes that indicate the values, lifestyle, personality, interests, etc. of the user U.

In the example shown in FIG. 4, the demographic attributes of user U include information such as "gender" and "age." “Gender” is information indicating the gender of the user U, and “age” is information indicating the age of the user U. Note that the demographic attributes of the user U further include, for example, the user U's position, work in charge, annual income, address, commuting route, training history, family composition, and the like. The user U's preferences include the user U's degree of interest in each object, such as clothes, travel, cars, motorcycles, computers, and lunch.

“Information provision history” is information regarding property information provided to user U in the past by the processing unit 12, and is information for each user U. Information regarding property information may be, for example, information on a property searched by user U, or property that user U has focused on, such as information on a property clicked by user U in a property list or advertisement provided to user U. be.

“Search history” is information about user U's search history in other services. Other services are services other than the property information providing service provided by the processing unit 12, and are, for example, services provided by a business operator that operates and manages the information processing device 1.

Other services are, for example, online services that provide services online to user U, such as search services provided by search sites, e-commerce services provided by e-commerce sites, and auctions provided by auction sites. Services, video distribution services provided by video distribution sites, news distribution services provided by news sites, etc.

[3.2.2. Property information storage unit 21]
The property information storage unit 21 stores advertisement information submitted by business operator B and posted information posted by user U. The property information storage unit 21 stores an advertisement information table including a plurality of advertisement information, a posted information table including a plurality of posted information, and the like.

FIG. 5 is a diagram illustrating an example of an advertisement information table stored in the property information storage unit of the information processing device according to the embodiment. As shown in FIG. 5, the advertisement information table stored in the property information storage unit 21 includes information such as "property ID", "property group ID", "property name", "property content", and "comment". Included for each property.

“Property ID” is information unique to each property. “Property group ID” is information unique to each property group. A property group is, for example, a group of a plurality of properties, and if the property is one unit of a housing complex such as a condominium, it is a housing complex. Note that when the property is a single-family house, the property group ID may include, for example, information indicating that there is no property group.

“Property name” is information indicating the name of the property. "Property content" is information indicating the content of the property, and includes "property overview" and "property details." “Property overview” is information indicating an overview of a property, and is information indicated by standard items. For example, if the property is a rental property, the property name, rent, time to the nearest station, security deposit, security deposit, key money, floor plan, exclusive area, age, building size, and the property in the building are included. It includes information such as the floor on which it is located and its location.

“Property details” is information indicating details of the property. “Property details” includes standard items and notes. Typical items include information such as details of facilities (baths, toilets, kitchens, storage, balconies, security, elevators, air conditioners, flooring, internet availability, etc.), floor plans, building structures, and parking lots. included. The notes include, for example, matters that the business operator B wants to inform the user U about other than standard items.

The "comment" is a comment by business operator B regarding the property, and is information for promoting the property. “Comment” is information displayed in the appeal column included in the information regarding the property provided to user U.

In the advertisement information table shown in FIG. 5, the property with the property ID "O1" has the property group ID "G1" and the property name "Property E1", and the property with the property ID "O2" has the property group ID "G1" and the property name "Property E1". is "G4", and the property name is "Property E2". Furthermore, the property with the property ID “O3” has the property group ID “G2” and the property name “Property E3”.

FIG. 6 is a diagram illustrating an example of a posted information table stored in the property information storage unit of the information processing device according to the embodiment. As shown in FIG. 6, the posted information table stored in the property information storage unit 21 includes information such as "posting ID", "user ID", "target ID", "posting date and time", and "posting content". Included for each user submission.

“Post ID” is identification information unique to each user post. The "user ID" is unique identification information for each posting user, who is the user U who posts a word of mouth, and is the same as the user ID shown in FIG. 4. The "target ID" is a property group ID if the posting target is a property group, and is a property ID if the posting target is a property. Note that if the property is one unit of a housing complex such as a condominium, the posting target is a group of properties, but is not limited to such an example.

“Posting date and time” is information indicating the date and time when the user posted. The "posted content" is information indicating the content of the user's submission, and is information indicating so-called user U's word of mouth.

In the posting information table shown in FIG. 6, the user posting with the posting ID "C1" is a posting made by the user U ₁ with the user ID "U1" to the property group with the target ID "G1", and the posting date and time is 2021. The post was made at 7:32 on December 28, 2017, and the content of the post was ``The lobby and hallways are wide.''

In addition, the user post with post ID "C2" is a post made by user _Un with user ID "Un" to the property group with target ID "G2", and the posting date and time is 9:00 on December 28, 2021. It was 46 minutes long and the content of the post was ``It's a comfortable place to live and it's close to the station, so it's convenient.''

In addition, the user post with post ID "C3" is a post made by user U ₂ with user ID "U2" to the property group with target ID "G1", and the posting date and time is 12:00 on December 28, 2021. It was 11 minutes long and the content of the post was ``The windows are large and easy to clean.''

[3.2.3. Feature label storage unit 22]
FIG. 7 is a diagram illustrating an example of a feature label table stored in the feature label storage unit of the information processing device according to the embodiment. As shown in FIG. 7, the feature label table stored in the feature label storage unit 22 includes information such as "property ID", "label information 1", "label information 2", etc. for each property. “Property ID” is the same as the user ID shown in FIG. 4.

"Label information 1" is information about the first feature label, and includes a feature label and a class ID. "Label information 2" is information on the second feature label, and includes a feature label and a class ID. The class ID is information unique to each class. The class is a class into which each user is classified by clustering based on user information.

In the characteristic label table shown in FIG. 7, the characteristic labels of the property with the property ID "O1" are "Large lobby" associated with the class ID "C1, C2, ..." and "Large lobby" associated with the class ID "C1, C2, ...". "..." is associated with "the hallway is wide."

In addition, the characteristic label of the property with property ID "O2" is "comfortable to live", which is associated with class ID "C1, C2, ...", and "comfortable to live", which is associated with class ID "C1, C3, ...". It is ``close to the station and convenient''.

In addition, the characteristic label of the property with property ID "O3" is "large windows", which is associated with class ID "C2, C3,...", and "large window", which is associated with class ID "C2, C4,...". ``Easy to clean.''

Although not shown, each label information includes information indicating whether the feature label is a feature extracted from posted information or advertising information. Information indicating the first feature label is added to the feature label extracted only from the posted information, and information indicating the second feature label is added to the feature label extracted only from the advertisement information.

[3.3. Processing unit 12]
The processing unit 12 is a controller, and for example, processes various programs (information processing programs) stored in a storage device inside the information processing device 1 by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). (corresponding to one example) is realized by being executed using RAM as a work area. Further, the processing unit 12 is, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the processing section 12 includes a reception section 30, an information acquisition section 31, a feature extraction section 32, a determination section 33, and an information provision section 34, and includes an information processing section described below. To realize or carry out a function or action. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration as long as it performs information processing to be described later. Further, the connection relationship between the respective processing units included in the processing unit 12 is not limited to the connection relationship shown in FIG. 3, and may be other connection relationships.

[3.3.1. Reception Department 30]
The reception unit 30 receives a property information transmission request transmitted from the user terminal 2 by the user U's operation on the user terminal 2 via the communication network 4 and the communication unit 10 .

The property information transmission request includes, for example, a property information transmission request that includes information for specifying a property, or a property information transmission request that includes information for searching for a property. The property information transmission request also includes user identification information for identifying the user U of the user terminal 2 that transmitted the property information transmission request.

[3.3.2. Information acquisition unit 31]
The information acquisition unit 31 acquires information transmitted from the user terminal 2, the operator terminal 3, other devices, etc. via the communication network 4 and the communication unit 10, and acquires information stored in the storage unit 11. or obtain it. The information acquisition unit 31 includes a user information acquisition unit 40 and a property information acquisition unit 41.

[3.3.2.1. User information acquisition unit 40]
When the property information transmission request is accepted by the reception unit 30, the user information acquisition unit 40 identifies the user U of the user terminal 2 that transmitted the property information transmission request based on the user identification information included in the property information transmission request. Information is acquired from the user information storage section 20. In this way, the user information acquisition unit 40 acquires information about the user U to whom property information is provided.

[3.3.2.2. Property information acquisition department 41]
The property information acquisition unit 41 acquires posted information transmitted from the user terminal 2 through the communication network 4 and the communication unit 10 when the user U operates the user terminal 2 . The posted information includes, for example, information for identifying a posting user, information for identifying a posting target, information indicating posted content, and the like.

When the property information acquisition unit 41 acquires the posted information via the communication network 4 and the communication unit 10, the property information acquisition unit 41 associates the acquired posted information with a new posting ID and adds it to the posted information table. The posting user is a user U who has used the property. If the property is a rental property, User U who has used the property is User U who rents and lives in the property or User U who has rented and lived in the property, but has not entered the property. may include a certain user U, etc. Note that the posting users may include the user U who has never used the property.

The property information acquisition unit 41 also acquires advertisement information transmitted from the business terminal 3 by the business operator B's operation on the business terminal 3 via the communication network 4 and the communication unit 10 . The advertisement information is information about the advertisement of business operator B regarding the property. Such advertising information includes, for example, the above-mentioned property name, property details, comments, and the like. When the property information acquisition unit 41 acquires advertisement information via the communication network 4 and communication unit 10, it associates the acquired advertisement information with a new posting ID and adds it to the advertisement information table.

[3.3.3. Feature extraction unit 32]
The feature extraction unit 32 extracts information indicating the characteristics of the property for each property as a feature label added to the property information, based on the advertisement information and posted information acquired by the information acquisition unit 31.

The feature extraction unit 32 extracts features of the property by natural language processing. For example, the feature extraction unit 32 extracts features of the property through natural language processing including morphological analysis, syntactic analysis, semantic analysis, context analysis, and the like. Note that the feature extraction unit 32 can also extract information indicating the characteristics of the property using tf-idf (term frequency inverse document frequency) or the like.

When the property is real estate, the feature label extracted by the feature extraction unit 32 is the living environment of the real estate property, and includes the surrounding environment of the real estate property. For example, characteristic labels include "Large lobby," "Comfortable place to live," "Convenient and close to the station," "Large windows," "Easy to clean," "Good manners of residents," or "Facilities." "fulfilling" etc.

The feature extraction unit 32 extracts features of the property based on the posted information. When extracting property features using only posted information, feature labels may not be extracted for properties with no posts or few posts. Therefore, the feature extraction unit 32 is configured to be able to extract property features based on advertisement information in addition to posted information.

The feature extraction unit 32 extracts features of the property based on the advertising information. For example, the feature extraction unit 32 can extract the characteristics of the property based on the advertising information from at least one of comments and notes regarding the property included in the advertising information.

Since comments and notes often contain characteristic information about a property, it is possible to efficiently extract the characteristics of a property by extracting the characteristics of the property from the comments and notes about the property included in the advertisement information. I can do it. Note that the feature extraction unit 32 can also extract property features from information included in the advertisement information other than comments and notes.

If the property features extracted from the posted information and the property features extracted from the advertisement information are contradictory features, the feature extraction unit 32 gives priority to the property features extracted from the advertisement information and generates a feature label. Extract as. Compared to property features extracted from posted information, property features extracted from advertising information are often more reliable, so property features extracted from advertising information are given priority as feature labels. By extracting the feature labels, the reliability of the feature labels can be further increased.

Further, the feature extraction unit 32 preferentially extracts as a feature label among the property features extracted from the posted information and the property features extracted from the advertising information, based on the number of posted information and the number of advertising information. Determine the characteristics of the property. If the ratio of the number of posted information to the number of advertising information is greater than or equal to a preset threshold, priority is given to the characteristics of the property extracted from the posted information; otherwise, the characteristics of the property extracted from the advertising information are prioritized. Prioritize features.

The feature extraction unit 32 adds the feature of the property extracted from the posted information to the feature label table as a first feature label, and adds the feature of the property extracted from the advertisement information to the feature label table as a second feature label.

[3.3.4. Determination section 33]
The determining unit 33 determines a characteristic label to be presented to the user U from among a plurality of characteristic labels indicating characteristics of the property.

When the property information transmission request received by the reception unit 30 includes information for identifying a property, the determining unit 33 assigns a feature label indicating the characteristics of the target property, which is the property specified in the property information transmission request, to the user. Determine the feature label to be presented to U.

Further, when the property information transmission request received by the reception unit 30 includes information for searching for a property, the determining unit 33 determines the characteristics indicating the characteristics of the target property that is the property to be searched by the property information transmission request. The label is determined as the feature label to be presented to the user U.

For example, when the number of feature labels indicating the characteristics of the target property is less than or equal to the specified number in the feature label table, the determining unit 33 determines all feature labels included in the feature label table as feature labels to be presented to the user U. . The prescribed number is the number of feature labels to be added to the information of the target property in response to the property information transmission request.

In addition, for example, when the number of feature labels indicating the characteristics of the target property exceeds a specified number in the feature label table, the determining unit 33 determines whether the user Determine the feature label to be presented to U.

The preset decision condition is, for example, a first decision condition, a second decision condition, a third decision condition, or a fourth decision condition. The determining unit 33 presents the determination condition to the target user, who is the user U of the user terminal 2 who transmitted the property information transmission request, based on the determination condition selected for each property or each type of property from among the plurality of decision conditions. Determine feature labels.

The type of property includes, for example, the total floor area of the property, the price of the property (rent in the case of a rental property), and the user group of the property (for example, single person, working couple, family including children, etc., or by annual household income, etc.) This type is classified based on the location of the property (urban or suburban, distance from the station, convenient transportation, etc.).

The first decision condition is a decision condition based on clustering. When the first determination condition is selected, the determining unit 33 selects a characteristic label to be presented to the target user from among the plurality of characteristic labels indicating characteristics of the property, based on the target user's information acquired by the information acquiring unit 31. decide.

For example, the determining unit 33 selects a feature label to be presented to the target user from among a plurality of feature labels indicating characteristics of the property based on one or more of the target user's attributes, property information provision history, and search history. decide.

For example, the determining unit 33 determines the class to which the target user belongs from among a plurality of classes through clustering processing based on one or more of the target user's attributes, property information provision history, and search history. The determining unit 33 extracts the feature label associated with the class to which the target user belongs from the feature label table, and determines the extracted feature label as the feature label to be presented to the target user.

The clustering process is performed by, for example, hierarchical clustering using the word method, group average method, shortest distance method, or longest distance method, or non-hierarchical clustering using the K-means method. Not limited.

Among the target user's attributes, property information provision history, and search history, information used for clustering processing is set for each property, but may be common to all properties. For example, in E1, the attributes of the target user among the target user's attributes, property information provision history, and search history are set as information used in the clustering process.

Furthermore, for the property E2, the property information provision history among the target user's attributes, property information provision history, and search history is set as information used in the clustering process. Furthermore, for the property E3, information other than the search history among the target user's attributes, property information provision history, and search history is set as information used in the clustering process.

The second decision condition is a decision condition using the type of feature label. When the second determination condition is selected, the determining unit 33 preferentially presents the first characteristic label and the second characteristic label to the target user based on the target user's information acquired by the information acquiring unit 31. Determine feature labels. The target user's information is one or more of the target user's attributes, property information provision history, and search history.

For example, when the target user is a user U having a specific attribute, the determining unit 33 determines one of the first feature label and the second feature label as the feature label to be presented preferentially to the target user. However, if this is not the case, the other feature label is determined as the feature label to be preferentially presented to the target user.

Further, when providing information on the same property to the target user, the determining unit 33 determines a feature label of a different type from the type of feature label presented to the target user last time as the feature label to be presented to the target user. For example, when the type of feature label presented to the target user last time is the first feature label, the determining unit 33 determines the second feature label as the feature label to be presented to the target user this time.

Further, when the target user has a search history of a specific service, the determining unit 33 determines one of the first feature label and the second feature label as the feature label to be presented preferentially to the target user. , otherwise, the other feature label is determined as the feature label to be presented preferentially to the target user.

The third determination condition is a determination condition using the number of first feature labels and the number of second feature labels. When the third determination condition is selected, the determining unit 33 determines whether the label number ratio, which is the ratio of the number of first feature labels to the number of second feature labels, is greater than or equal to a preset threshold. . If the label number ratio is greater than or equal to a preset threshold, the determining unit 33 determines the first feature label as the feature label to be preferentially presented to the target user, and if not, determines the second feature label to be presented to the target user. Determine the feature label to be presented preferentially.

The fourth determination condition is a determination condition using random determination. When the fourth determination condition is selected, the determining unit 33 determines a prescribed number of randomly selected feature labels from among the plurality of feature labels of the target property as the feature labels to be presented to the target user.

[3.3.5. Information provision department 34]
The information providing unit 34 provides the target user with property information in which the feature label extracted by the feature extraction unit 32 is added to the target property information. The information providing unit 34 provides property information to the target user by transmitting the property information to the user terminal 2 of the target user via the communication unit 10 and the communication network 4.

When the number of feature labels extracted by the feature extraction unit 32 is greater than or equal to the specified number, the information providing unit 34 uses the feature labels determined by the determination unit 33 from among the feature labels extracted by the feature extraction unit 32 as information on the target property. Provide the property information added to the target user.

Here, it is assumed that the information included in the property information transmission request received by the reception unit 30 is information for identifying the property. In this case, the information providing unit 34 sets the property specified by the information for specifying the property as the target property, and provides the property information added to the information on the target property to the target user as information on the individual section right.

Further, it is assumed that the information included in the property information transmission request accepted by the reception unit 30 is information for searching for a property. In this case, the information providing unit 34 sets each of the plurality of properties searched using the property search information as a target property, and provides the target user with information on a property list including the property information added to the information of each target property. do.

FIG. 8 is a diagram illustrating an example of property list information provided to the user by the information processing apparatus according to the embodiment and displayed on the user terminal. Property list information 50, which is property list information shown in FIG. 8, includes a plurality of property information 51, 52, and 53.

The property information 51 includes information 51a of the property E1 and characteristic labels 51b1 and 51b2 of the property E1. The feature label 51b1 is "the lobby is wide", and the feature label 51b2 is "the hallway is wide". Thereby, the target user can easily understand that the characteristics of the property E1 or a group of properties including the property E1 are "the lobby is large" and "the hallway is wide".

The property information 52 includes information 52a of the property E2 and characteristic labels 52b1 and 52b2 of the property E2. The feature label 52b1 is "comfortable to live in", and the feature label 52b2 is "close to the station and convenient". Thereby, the target user can easily understand that the characteristics of the property E2 or a group of properties including the property E2 are "comfortable to live in" and "convenient because it is close to the station."

The property information 53 includes information 53a of the property E3 and characteristic labels 53b1 and 53b2 of the property E3. The feature label 53b1 is "easy to clean", and the feature label 53b2 is "large window". Thereby, the target user can easily understand that the characteristics of the property E3 or a group of properties including the property E3 are "easy to clean" and "large windows."

The information providing unit 34 also provides property information in which a first feature label, which is a feature label extracted from the posted information, and a second feature label, which is a feature label extracted from advertising information, are added to the property information in different display modes. can also be provided to user U.

For example, the first feature label and the second feature label include at least one of the following: frame shape, frame color, frame thickness, frame color, text size, text font, and text modification. different. Thereby, the target user can distinguish between the first feature label and the second feature label.

Further, the information providing unit 34 can arrange each of the first feature label and the second feature label in the property information at a preset position among the specified number of feature labels. For example, the information providing unit 34 can set the feature labels 51b1, 52b1, and 53b1 as first feature labels, and set the feature labels 51b2, 52b2, and 53b2 as second feature labels.

[4. Processing procedure]
Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. FIG. 9 is a flowchart illustrating an example of information processing by the processing unit of the information processing apparatus according to the embodiment.

As shown in FIG. 9, the processing unit 12 of the information processing device 1 determines whether posted information has been acquired (step S10). When the processing unit 12 determines that the posted information has been acquired (step S10: Yes), the processing unit 12 causes the storage unit 11 to store the posted information determined to have been acquired (step S11).

When the process of step S11 is completed or when it is determined that posted information has not been acquired (step S10: No), the processing unit 12 determines whether advertisement information has been acquired (step S12). When the processing unit 12 determines that the advertisement information has been acquired (step S12: Yes), the processing unit 12 causes the storage unit 11 to store the advertisement information determined to have been acquired (step S13).

When the process of step S13 is completed, or when it is determined that the advertisement information has not been acquired (step S12: No), the processing unit 12 determines whether or not the characteristic label extraction timing has come (step S14). The characteristic label extraction timing is, for example, the timing when the number of at least one of newly stored advertisement information and posted information reaches a preset number, or the timing that arrives at a preset period.

If the processing unit 12 determines that it is the characteristic label extraction timing (step S14: Yes), it performs the characteristic label extraction process (step S15). The process in step S15 is the process in steps S20 to S25 shown in FIG. 10, and will be described in detail later.

When the process of step S15 is completed, or when it is determined that the feature label extraction timing has not come (step S14: No), the processing unit 12 determines whether or not a property information transmission request has been received (step S16). .

If the processing unit 12 determines that the property information transmission request has been received (step S16: Yes), it performs property information providing processing (step S17). The process in step S17 is the process in steps S30 to S32 shown in FIG. 11, and will be described in detail later.

When the process of step S17 is completed, or when it is determined that the property information transmission request has not been received (step S16: No), the processing unit 12 determines whether or not the operation end timing has come (step S18). The processing unit 12 determines that the operation end timing has come, for example, when the power of the information processing device 1 is turned off.

If the processing unit 12 determines that the operation end timing has not come (step S18: No), the process proceeds to step S10, and if it determines that the operation end timing has come (step S18: Yes), the process proceeds to FIG. The indicated process ends.

FIG. 10 is a flowchart illustrating an example of feature label extraction processing by the processing unit of the information processing device according to the embodiment. As shown in FIG. 10, the processing unit 12 acquires posted information from the storage unit 11 (step S20). The processing unit 12 extracts the first feature label from the posted information acquired in step S20 (step S21), and stores the extracted first feature label in the storage unit 11 (step S22).

Furthermore, the processing unit 12 acquires advertisement information from the storage unit 11 (step S23). The processing unit 12 extracts the second feature label from the advertisement information acquired in step S23 (step S24), and stores the extracted second feature label in the storage unit 11 (step S25). When the processing of step S25 is completed, the processing unit 12 ends the processing shown in FIG. 10.

FIG. 11 is a flowchart illustrating an example of property information providing processing by the processing unit of the information processing device according to the embodiment. As shown in FIG. 11, the processing unit 12 acquires information about the target user from the storage unit 11 (step S30).

Next, the processing unit 12 determines a feature label to be provided to the target user from among the plurality of feature labels of the target property, based on the target user's information extracted in step S30 (step S31). Then, the processing unit 12 provides the target user with information on the property to which the feature label extracted in step S31 has been added (step S32), and ends the process shown in FIG. 11.

[5. Modified example]
The feature extraction unit 32 can add property features that are commonly extracted from each of the posted information and the advertisement information to the feature label table as a third feature label. In this case, in the feature label table, information indicating the third feature label is added to the feature label commonly extracted from each of the posted information and the advertisement information.

The determining unit 33 can prioritize the third feature label, the second feature label, and the first feature label in this order and determine them as the feature labels to be provided to the target user. In this case, the information providing unit 34 may present the third feature label to the user U in a display mode different from the first feature label and the second feature label, in addition to the first feature label and the second feature label. I can do it.

Furthermore, even if the first feature label and the second feature label are contradictory, if the number of posted information from which the first feature label is extracted is greater than or equal to the threshold, or When one feature label is extracted from user U's posted information for which the extraction probability of feature labels is high relative to the number of posted information, priority can be given to the first feature label.

[6. Hardware configuration]
The information processing device 1 or user terminal 2 according to the embodiments described above is realized by, for example, a computer 80 having a configuration as shown in FIG. 12. The information processing device 1 will be described below as an example. FIG. 12 is a hardware configuration diagram showing an example of a computer 80 that implements the functions of the information processing device 1 according to the embodiment. The computer 80 includes a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, an HDD (Hard Disk Drive) 84, a communication interface (I/F) 85, an input/output interface (I/F) 86, and a media interface (I/F). )87.

The CPU 81 operates based on a program stored in the ROM 83 or HDD 84 and controls each part. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started, programs depending on the hardware of the computer 80, and the like.

The HDD 84 stores programs executed by the CPU 81 and data used by the programs. The communication interface 85 receives data from other devices via the communication network 4 (see FIG. 2) and sends it to the CPU 81, and sends data generated by the CPU 81 to the other devices via the communication network 4.

The CPU 81 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via an input/output interface 86. The CPU 81 obtains data from an input device via the input/output interface 86. Further, the CPU 81 outputs the generated data to an output device via the input/output interface 86.

Media interface 87 reads programs or data stored in recording medium 88 and provides them to CPU 81 via RAM 82. The CPU 81 loads this program from the recording medium 88 onto the RAM 82 via the media interface 87, and executes the loaded program. The recording medium 88 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 realizes the functions of the processing unit 12 by executing a program loaded onto the RAM 82. Furthermore, data in the storage unit 11 is stored in the HDD 84 . The CPU 81 of the computer 80 reads these programs from the recording medium 88 and executes them, but as another example, these programs may be acquired from another device via the communication network 4.

[7. others〕
Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or the processes described as being performed manually can be performed manually. All or part of the process can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured. For example, the reception unit 30 and information acquisition unit 31 shown in FIG. 3 may be integrated. Further, for example, the information stored in the storage unit 11 may be stored in a predetermined storage device provided externally via the communication network 4. Further, a part of the processing of the user terminal 2 may be executed by the information processing device 1.

Further, in the embodiment described above, the information processing device 1 performs an information acquisition process of acquiring posted information and advertisement information, and converts information indicating characteristics of the property into property information based on the posted information and advertisement information. An example is shown in which a feature extraction process is performed to extract a feature label to be added. However, the information processing device 1 described above may be separated into an information acquisition device that performs information acquisition processing and a feature extraction device that performs feature extraction processing. In this case, the information acquisition device includes at least an information acquisition section 31. The feature extraction device includes at least a feature extraction section 32. The processing by the information processing device 1 described above is realized by an information processing system 100 that includes an information acquisition device and a feature extraction processing device.

Further, in the embodiment described above, the information processing apparatus 1 performs, for example, an information acquisition process of acquiring information about the user U to whom property information is provided, a determination process of determining a characteristic label to be presented to the user U, and a characteristic label. An example is shown in which an information providing process is performed in which information on a property to which label information is added is provided to user U. However, the information processing device 1 described above may be separated into an information acquisition device that performs information acquisition processing, a determination device that performs determination processing, and an information provision device that performs information provision processing. In this case, the information acquisition device includes at least an information acquisition section 31. The determining device includes at least a determining section 33. The information providing device has at least an information providing section 34. The processing by the information processing device 1 described above is realized by an information processing system 100 that includes an information acquisition device, a determining device, and an information providing device.

Furthermore, the embodiments and modifications described above can be combined as appropriate within a range that does not conflict with the processing contents.

[8. effect〕
As described above, the information processing device 1 according to the embodiment includes the information acquisition section 31 and the feature extraction section 32. The information acquisition unit 31 acquires posted information, which is information posted by a user regarding a property, and advertisement information, which is information about an advertisement of a property by a vendor regarding the property. The feature extraction unit 32 extracts information indicating the characteristics of the property as a feature label added to the property information based on the posted information and advertisement information acquired by the information acquisition unit 31. Thereby, the information processing device 1 can more appropriately extract the characteristic label added to the property information.

Further, the feature extracting unit 32 extracts the feature of the property based on the advertising information as a feature label from at least one of comments and notes regarding the property included in the advertising information. Thereby, the information processing device 1 can increase the reliability of the feature label added to property information.

Furthermore, when the property features extracted from the posted information and the property features extracted from the advertisement information are contradictory features, the feature extraction unit 32 gives priority to the property features extracted from the advertisement information. Extract as a feature label. Thereby, the information processing device 1 can increase the reliability of the feature label added to property information.

Furthermore, the feature extracting unit 32 determines which feature label to prioritize among the first feature label and the second feature label, based on the number of posted information and the number of advertisement information. Thereby, the information processing device 1 can increase the reliability of the feature label added to property information.

Further, the property is a real estate property, and the feature extraction unit 32 extracts features related to the living environment of the real estate property as a feature label. Thereby, the information processing device 1 can extract a feature label useful for the user U who is searching for a real estate property as a feature label of the real estate property.

The information processing device 1 also includes an information providing unit 34 that provides the user U with property information in which the feature label extracted by the feature extraction unit 32 is added to the property information. Thereby, the information processing device 1 can more appropriately provide the target user with the characteristic label added to the property information.

Further, the information providing unit 34 provides the user U with property information in which the feature labels extracted from the posted information and the feature labels extracted from the advertisement information are added to the property information in different display modes. Thereby, the information processing device 1 can present the feature label extracted from the posted information and the feature label extracted from the advertisement information to the user U in a distinguishable manner.

Further, the information providing unit 34 provides the user U with information on a property list that includes property information on a property-by-property basis. Thereby, the information processing device 1 can appeal to the user U the characteristics of each property using the characteristic label of each property.

Although the embodiments of the present application have been described above in detail based on the drawings, this is merely an example, and various modifications and improvements can be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to implement the invention in other forms.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the information acquisition section can be replaced with information acquisition means or information acquisition circuit.

1 Information processing device 2, _{2 1} , 2 ₂ , ..., 2 _n user terminal 3, _{3 1} , ..., 3 _m operator terminal 4 communication network 10 communication section 11 storage section 12 processing section 20 user information storage Part 21 Property information storage part 22 Feature label storage part 30 Reception part 31 Information acquisition part 32 Feature extraction part 33 Determination part 34 Information provision part 40 User information acquisition part 41 Property information acquisition part 50 Property list information 51, 52, 53 Property information 51a, 52a, 53a information 51b1, 51b2, 52b1, 52b2, 53b1, 53b2 feature label

Claims (13)

an information acquisition unit that acquires posted information that is information posted by a user regarding a property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction unit that extracts information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired by the information acquisition unit;
The feature extraction unit is
If the characteristics of the property extracted from the posted information and the characteristics of the property extracted from the advertising information are contradictory to each other, the characteristics of the property extracted from the advertising information are given priority. An information processing device characterized by extraction as a label. an information acquisition unit that acquires posted information that is information posted by a user regarding a property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction unit that extracts information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired by the information acquisition unit;
The feature extraction unit is
Based on the number of posted information and the number of advertising information, among the features of the property extracted from the posted information and the features of the property extracted from the advertising information, the feature label is extracted with priority as the feature label. An information processing device characterized by determining characteristics of a property. an information acquisition unit that acquires posted information that is information posted by a user regarding a property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction unit that extracts information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired by the information acquisition unit;
an information providing unit that provides a user with property information in which the feature label extracted by the feature extraction unit is added to the property information;
The information provision department is
An information processing apparatus characterized in that property information is provided to a user in which the feature label extracted from the posted information and the feature label extracted from the advertisement information are added to the property information in different display modes. The feature extraction unit is
According to any one of claims 1 to 3 , the feature of the property based on the advertising information is extracted as the feature label from at least one of comments and notes regarding the property included in the advertising information. The information processing device described. The said property is
It is a real estate property,
The feature extraction unit is
The information processing device according to any one of claims 1 to 4 , wherein a feature related to the living environment of the real estate property is extracted as the feature label. The information processing apparatus according to claim 2 or 3, further comprising an information providing unit that provides a user with property information in which the feature label extracted by the feature extraction unit is added to the property information. The information provision department is
The information processing apparatus according to claim 3 or 6 , wherein the information processing apparatus provides the user with information on a list of properties that includes the property information on a property-by-property basis. An information processing method performed by a computer, the method comprising:
an information acquisition step of acquiring posted information that is information posted by a user regarding the property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction step of extracting information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired in the information acquisition step;
The feature extraction step includes:
If the characteristics of the property extracted from the posted information and the characteristics of the property extracted from the advertising information are contradictory to each other, the characteristics of the property extracted from the advertising information are given priority. An information processing method characterized by extraction as a label. An information processing method performed by a computer, the method comprising:
an information acquisition step of acquiring posted information that is information posted by a user regarding the property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction step of extracting information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired in the information acquisition step;
The feature extraction step includes:
Based on the number of posted information and the number of advertising information, among the features of the property extracted from the posted information and the features of the property extracted from the advertising information, the feature label is extracted with priority as the feature label. An information processing method characterized by determining characteristics of a property. An information processing method performed by a computer, the method comprising:
an information acquisition step of acquiring posted information that is information posted by a user regarding the property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction step of extracting information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired in the information acquisition step;
an information providing step of providing a user with property information in which the feature label extracted in the feature extraction step is added to the property information;
The information providing step includes:
An information processing method comprising: providing a user with property information in which the feature label extracted from the posted information and the feature label extracted from the advertising information are added to the property information in different display modes. an information acquisition procedure for acquiring posted information that is information posted by a user regarding a property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction procedure for extracting information indicating the characteristics of the property as a feature label added to the property information based on the posted information and the advertising information acquired by the information acquisition procedure; let me,
The feature extraction procedure is
If the characteristics of the property extracted from the posted information and the characteristics of the property extracted from the advertising information are contradictory to each other, the characteristics of the property extracted from the advertising information are given priority. An information processing program characterized by extraction as a label. an information acquisition procedure for acquiring posted information that is information posted by a user regarding a property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction procedure for extracting information indicating the characteristics of the property as a feature label added to the property information based on the posted information and the advertising information acquired by the information acquisition procedure; let me,
The feature extraction procedure is
Based on the number of posted information and the number of advertising information, among the features of the property extracted from the posted information and the features of the property extracted from the advertising information, the feature label is extracted with priority as the feature label. An information processing program characterized by determining the characteristics of a property. an information acquisition procedure for acquiring posted information that is information posted by a user regarding a property and advertising information that is information about an advertisement for the property by a vendor regarding the property;
a feature extraction step of extracting information indicating characteristics of the property as a feature label added to the property information based on the posted information and the advertisement information acquired by the information acquisition step;
causing a computer to execute an information providing step of providing a user with property information in which the feature label extracted by the feature extraction step is added to the property information;
The information provision procedure is as follows:
An information processing program that provides a user with property information in which the feature label extracted from the posted information and the feature label extracted from the advertisement information are added to the property information in different display modes.

Images