JP2024011698A - Determination system, determination method, and determination program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a determination system, a determination method, and a determination program, configured so that a searcher who desires to rent a space can search for the space with higher accuracy, while deciding a type not based on a subjective view of a renter but based on a more objective view.

SOLUTION: A determination system which associates a types for use in searching for a space, from a type designated for the space based on a subjective view of a renter includes: receiving means which receives image data of a space that a renter desires to rent and a designation of a type for the space; learning means which trains a machine learning model using the image data of the space and the designated type as training data; calculation means which calculates likelihood of the space with respect to the type, on the basis of the received image data of the space, the type designated for the space, and the learned model; and determination means which decides a type to be associated with the space on the basis of the likelihood.

SELECTED DRAWING: Figure 2

COPYRIGHT: (C)2024,JPO&INPIT

Description

Application filed for application of Article 30, Paragraph 2 of the Patent Act February 2, 2020 Website <http://www. instabase. Published on jp／＞

The present invention relates to a determination system, a determination method, and a determination program.

Traditionally, it is known that a large percentage of people searching for rental spaces are looking for "rental conference rooms," so many of the spaces listed on search sites, etc. The ``Rental Conference Room'' flag is attached even though it is not a ``Rental Conference Room.'' Therefore, when a searcher searches for "rental conference room," a large number of spaces that are different from the "rental conference room" that the user is looking for appear in the search results, leading to the user giving up on the search. it is conceivable that.

In Patent Document 1, a robot device captures an image and stores it as a sensor data log, and uses the sensor data log as a training data set to identify the type of room through image recognition and more accurately detect collisions with objects. An invention for predicting the future is disclosed.

Patent No. 7025532

However, the invention described in Patent Document 1 discloses determining what kind of room it is from a room image, but it does not disclose determining the specific type of room such as "rental conference room". is not disclosed, nor is there any disclosure regarding improving the search function based on the room type determination results.

In view of the above circumstances, an object of the present invention is to provide a new technique related to a determination system.

In order to solve the above-mentioned problems, the present invention provides a determination system that associates a space with a type used for searching for a space from types specified based on the subjectivity of a poster, the system including a space that the poster desires to rent. a receiving means for receiving image data of the space and designation of a type for the space; a learning means for learning a machine learning model using the image data of the space and the designated type as training data; and the received image data of the space; a calculation means for calculating a likelihood of the space for the type based on a type specified for the space and a learned model; a determination means for determining a type to be associated with the space based on the likelihood; It is characterized by having the following. With this configuration, the present invention enables a type that is close to an objective viewpoint to be determined, rather than a type specified based on the subjectivity of the poster, and a searcher who wishes to rent a space can It can improve accuracy when searching for spaces.

In a preferred embodiment of the present invention, one or more types from among a plurality of types are specified for the space, and the determination means determines whether the space corresponds to each of the plurality of types. It is characterized by With such a configuration, the present invention can make it difficult for a searcher to omit a search when searching for a space that a searcher desires to rent when one space can be used for multiple purposes. .

In a preferred form of the present invention, the determination means is characterized in that, when the likelihood of the space with respect to the type is equal to or greater than a threshold value, the determination means associates the type with the space. With such a configuration, the present invention can present to the searcher only spaces whose likelihood in a predetermined type exceeds a threshold value.

In a preferred embodiment of the present invention, the learning means performs learning using the image data and the type received via the receiving means as teacher data. With such a configuration, the present invention can cause the machine learning model to perform relearning and generate a machine learning model that can make a type of determination that is closer to an objective viewpoint.

In a preferred embodiment of the present invention, the receiving means receives image data transmitted as a main image of a space and image data transmitted as a sub-image, and the learning means receives image data transmitted as a main image of a space. It is characterized by learning as training data. With such a configuration, the present invention can remove image data that may become noise during learning when a plurality of image data are received.

In a preferred embodiment of the present invention, the present invention includes search processing means for receiving a space search request and transmitting a search processing result, and the search processing means adjusts the display order of the spaces filtered based on the type based on the likelihood. It is characterized by making decisions based on quantity. With such a configuration, the present invention can present a space closer to the searcher's request.

In order to solve the above-mentioned problems, the present invention provides a determination method for associating a space with a type used for searching for a space from a type specified based on the subjectivity of the poster, the computer a receiving step for receiving image data of a desired space and designation of a type for the space; a learning step for training a machine learning model using the space image data and the designated type as training data; a calculation step of calculating a likelihood of the space with respect to the type based on image data, a type specified for the space, and a learned model; and a determination of determining a type to be associated with the space based on the likelihood. It is characterized by executing the steps.

In order to solve the above-mentioned problems, the present invention is a determination program that associates a space with a type used for searching for a space from types specified based on the subjectivity of a poster, the program for determining a space that the poster desires to rent. a receiving means for receiving image data of the space and designation of a type for the space; a learning means for learning a machine learning model using the image data of the space and the designated type as training data; and the received image data of the space; a calculation means for calculating a likelihood of the space for the type based on a type specified for the space and a learned model; a determination means for determining a type to be associated with the space based on the likelihood; It is characterized by having the following.

The present invention can provide a novel technique related to a determination system.

1 shows a configuration diagram of a determination system in an embodiment of the present invention. A hardware configuration diagram of a poster terminal 2A and a searcher terminal 2B in an embodiment of the present invention is shown. 1 shows a hardware configuration diagram of a management server 1 in an embodiment of the present invention. An example of a venue label in an embodiment of the present invention is shown. It is a flowchart which shows the flow of the determination procedure of the venue label for a search in embodiment of this invention.

In this specification, the configuration, effects, etc. of an embodiment of the present invention will be described below with reference to the drawings. The present invention is not limited to the following embodiments, and may adopt various configurations. Further, the embodiments of the present invention may adopt a part of the configuration of each embodiment to the extent that it does not impede the realization of the effects aimed at by the present invention.

Further, in this embodiment, the configuration, operation, etc. of the determination system will be described, but similar effects can be achieved by the method of execution, computer program, etc. The program in this embodiment may be provided as a computer-readable non-transitory recording medium, may be provided downloadable from an external server, or may be provided in order to realize its function in the determination system. Alternatively, the program may be started on an external computer (so-called cloud computing).

Further, in this embodiment, the term "means" may include, for example, a combination of hardware resources implemented by circuits in a broad sense and software information processing that can be concretely implemented by these hardware resources. In this embodiment, "information" refers to, for example, the physical value of a signal value representing voltage or current, the level of a signal value as a binary bit collection consisting of 0 or 1, or quantum superposition. (so-called quantum bits), and communication and calculations can be performed on circuits in a broad sense.

A circuit in a broad sense is a circuit realized by appropriately combining a circuit, a circuit, a processor, a memory, and the like. That is, CPU (Central Processing Unit), GPU (Graphics Processing Unit), LSI (Large Scale Integration), ASIC (Application Specific Integration) ated circuit), FPGA (Field-Programmable Gate Array), and the like.

In this embodiment, a case will be described in which a space search is performed on a space rental platform for renting out spaces for an hour. In the determination system, publishers register spaces they wish to rent, and searchers search for and reserve spaces they wish to use.
Note that the method of using the determination system is not limited to this. For example, it may be possible to use it for real estate brokerage platforms and public facility reservation systems.

<System configuration>
FIG. 1 is a schematic diagram of a determination system in the first embodiment. The determination system includes a management server 1, a publisher terminal 2A for registering information regarding a space that a publisher wishes to rent, and a searcher terminal for searching and making a reservation for a space that a searcher wishes to rent. 2B. The management server 1, the publisher terminal 2A, and the searcher terminal 2B are configured to be able to communicate via the communication network NW.

The communication network NW is composed of an IP (Internet Protocol) network such as the Internet. Note that in the following description, the intervention of the communication network NW will be omitted unless it becomes unclear.

In FIG. 1, one management server 1, one publisher terminal 2A, and one searcher terminal 2B are shown, but a plurality of each may exist.

<Management server 1>
As the management server 1, it is possible to use a general-purpose server computer, a personal computer, or the like. Furthermore, in this embodiment, it is also possible to configure the management server 1 using a plurality of computers.

<Publisher terminal 2A and searcher terminal 2B>
Each publisher terminal 2A and searcher terminal 2B may be a personal computer, a smartphone, a tablet terminal, or the like. The publisher terminal 2A and the searcher terminal 2B have an application (typically a web browser) for making a request to the management server 1 and receiving a response.

<Hardware configuration of management server 1>
FIG. 2 is a diagram showing an example of the hardware configuration of the management server 1. The management server 1 includes, as a hardware configuration, an arithmetic unit (CPU (Central Processing Unit)) 11 and a main storage device (RAM (Random Access Memory)) 12 as a working memory.

The management server 1 includes an auxiliary storage device 13 such as an HDD, SSD, or flash memory that rewritably stores an OS (Operating System), application programs, and various information (including data), a communication control unit 16, and an NIC (NIC). The device further includes a communication interface (IF) unit 17 such as a network interface card.

<Hardware configuration of publisher terminal 2A and searcher terminal 2B>
FIG. 3 is a diagram showing an example of the hardware configuration of the poster terminal 2A and the searcher terminal 2B. The poster terminal 2A and the searcher terminal 2B each include, as a hardware configuration, an arithmetic unit (CPU (Central Processing Unit)) 21 and a main storage device (RAM (Random Access Memory)) 22 as a working memory. .

The poster terminal 2A and the searcher terminal 2B are connected to an auxiliary storage device 23 such as an HDD, SSD, or flash memory that rewritably stores an OS (Operating System), application programs, and various information (including data), and a communication control system. 26 and a communication interface (IF) section 27 such as a NIC (Network Interface Card).

In addition, the poster terminal 2A and the searcher terminal 2B have an input unit 24, which is an interface that allows operation input, such as a mouse, keyboard, or touch panel, and a monitor or display, for example, for the poster and the searcher. It further includes an output unit 25, which is an interface for displaying a screen to be described later.

<Functional components>
As illustrated in FIG. 2, the management server 1 includes a reception means 101, a learning means 102, a calculation means 103, a determination means 104, a search processing means 105, an output processing means 106, and a database DB.

In order to logically realize the functional components described above in the management server 1, a determination program is installed in the auxiliary storage device 13 as an application program. In the management server 1, when the power is turned on, the arithmetic unit 11 expands the determination program stored in the auxiliary storage device 13 into the main storage device (RAM) 12 and executes it, thereby performing the above-mentioned functions. The configuration is realized.

<Type definition>
In this embodiment, the type is an indicator that is subjectively specified for a space. Examples of subjectively designated indicators include space usage, space quality, taste, concept, and atmosphere. Type may be an indicator that is difficult to set qualitatively. In this embodiment, the types representing the purpose of the rental space (hereinafter referred to as "venue type") include "rental conference room", "rental space", "seminar", "rental studio", "music studio", "rental salon", and "photography". Studio, Party Room, Coworking Space, Private Cafe/Restaurant, Exhibition Hall/Gallery, Pop-up Store, Live House/Theater, Sports Facility, Event Space, Old House, House Studio Settings include "rooftop/outdoor", "workspace", "amusement facility", and "hotel". Further, when setting the style of the room as a type, for example, "Brooklyn style", "Hotel-like interior", "Mid-century", "Japanese modern", and "Shabby chic" are set.

<Enter publication information>
The accepting means 101 accepts image data of a space that the publisher wishes to rent and designation of the type of space. In this embodiment, the poster operates a space information registration screen (not shown), which will be described later, displayed on the poster terminal 2A, and enters the name, nearest station, address, and hourly information of the space to be registered for rental. The management server 1 is sent the rental fee, the available rental date and time, the day of the week, the size, the number of people accommodated, explanatory text, image data of the space, and the venue type indicating the use of the space specified by the publisher. The receiving means 101 associates these pieces of information with the space ID, gives a label (hereinafter referred to as a "designated venue label") based on the designated venue type, and stores it in the database DB as space information.

In this embodiment, the receiving means 101 may accept one or more pieces of image data, and when accepting a plurality of pieces of image data, it may accept image data transmitted as a main image and image data transmitted as a sub-image. . Additionally, the publisher can specify multiple venue labels within a predetermined number. In the present embodiment, the venue label includes a designated venue label in which the poster specified a venue label to which the space appearing in the image data corresponds, and a search venue label that is associated with space information by the determining means 104, which will be described later. may include.

<Example of designated venue label>
FIG. 4A is a diagram showing an example of a designated venue label for each space information received via the reception means 101. In the illustrated example, the venue type designated by the publisher is stored as "1", and the designated venue label is defined thereby. On the other hand, unspecified venue types are stored as "0".

<Generation of machine learning model>
The learning means 102 generates a machine learning model using the image data of the space and the venue type associated with the image data as training data. The teacher data is, for example, image data that the database DB has in advance and a venue type associated with the image data. Here, the image data that the database DB has in advance may be image data prepared in advance by the owner of the management server 1, etc., and the venue type associated with the image data. It may be the image data received from the publisher via the reception means 101 and the venue type associated with the image data.

Further, when space information including a plurality of image data is received via the receiving means 101, the learning means 102 uses the image data transmitted as the main image when receiving the space information as an input value, A machine learning model is generated using training data whose output values include venue types.

<Calculation of likelihood>
The calculation unit 103 calculates the likelihood of a space for the venue type based on the image data received via the reception unit 101, the venue type associated with the image data, and the learned model. The calculation means 103 calculates the likelihood, which is a numerical value indicating the "likeness" of each venue type of the space, by image recognition based on the learned model.

The determining means 104 may calculate the likelihood for all venue types of one space, or may calculate the likelihood only for a predetermined venue type. For example, if there are many spaces that are labeled as "Conference Rooms for Rent" even though they are not "Conference Rooms for Rent," when a searcher performs a search, spaces that are not "Conference Rooms for Rent" will be displayed. Only the likelihood for the venue type of "rental conference room" is calculated so that it is not displayed as a search result.

<Example of likelihood for venue type>
FIG. 4(b) shows the likelihood of a certain space for each venue type, calculated by the calculating means 103. Here, in this embodiment, the likelihood calculated by the calculating means 103 is a numerical value between 0 and 1, but the width of the likelihood may be arbitrary.

<Determining venue type>
The determining means 104 determines the venue type to be associated with the space based on the likelihood calculated by the calculating means 103. In this embodiment, if the likelihood of a certain space for a certain venue type is greater than a threshold value, it is determined that the space corresponds to the venue type.

As an example, if the threshold value is 0.7, the space with "Space ID: 0002" in Figure 4(b) corresponds to three types: "Rental conference room", "Rental kitchen", and "Seminar venue". However, it is determined that it does not fall under the two types of "rental space" and "rental studio." Note that the same threshold value may be used for some or all venue types, or may be different for each venue type.

<Assignment of venue label for search>
Further, the determining means 104 assigns a label (hereinafter referred to as a "search venue label") based on the determined venue type, and stores it in the database DB in association with the space information.

Note that the number of search venue labels given to space information is less than or equal to a predetermined number. If the number of venue types with a likelihood greater than the threshold value is greater than a predetermined number, search venue labels within the same number as the above number may be associated with the space information in descending order of likelihood. Further, if all the likelihoods in a certain space calculated by the calculating means 103 are smaller than the threshold value, the determining means 104 assigns a search venue label based on the venue type with the largest calculated likelihood, and It may be stored in the database DB in association with the information.

Further, when the calculation means 103 calculates only the likelihood for a predetermined venue type, the determination means 104 determines whether the space corresponds to the venue type, and the search venue label other than the venue type is posted. The designated venue label may be the same as the designated venue label based on the designation of the designated venue.

<Search for space information>
The search processing means 105 receives a search request via the input unit 24 and transmits the search processing result to the searcher terminal 2B. In this embodiment, the search processing means 105 receives search conditions and a search request input via the input unit 24 on a space search screen (not shown) to be described later, and retrieves the search conditions from the database DB based on the search conditions. Get the space information applicable to . Note that the search conditions are conditions related to the space that the searcher desires to rent, and information related to other conditions such as the search venue label, the nearest station, and the rental fee per hour specified by the searcher.

<Display processing of space information registration screen and space search screen>
The output processing means 106 displays a space information registration screen (not shown) and a space search screen (not shown), and transmits the processing results to the poster terminal 2A and the searcher terminal 2B.

On the space information registration screen, the poster can upload image data, select the venue type to which the image data corresponds based on the poster's subjective opinion, and input other information related to the image data. At this time, on the space information registration screen, frames for uploading a main image and a sub-image may be respectively provided, and the configuration may be such that image data to be used as the main image can be determined from among the images to be uploaded. Further, the first image uploaded among the plurality of images may be the main image.

On the space search screen, it is possible for the searcher to input search conditions that are conditions related to a space that the searcher desires to rent, and to search for the space. The space search screen has a label specification section that accepts the specification of a designated venue label, a condition specification section that allows the specification (input) of information related to other conditions, and a condition confirmation section that confirms the search conditions and sends a search request. . Further, the space search screen can display space information acquired by the search processing means 105 according to the above search conditions. Here, the search processing means 105 determines the display order of space information to which the same venue label is attached, which is displayed on the space search screen, based on the likelihood of the venue type in the venue label. Furthermore, when a plurality of designated venue labels are specified in the search conditions, space information to be displayed in descending order of the sum of likelihoods for the designated venue labels or venue types with high priority is determined.

<Flowchart of procedure for determining venue label for search>
An example of the overall procedure for determining a search venue label using the determination system will be described with reference to FIG. In this example, when a searcher searches for a space that he or she wishes to rent, the designated venue label is not specified based on the subjectivity of the advertiser, but is based on a judgment based on a more objective viewpoint based on a machine learning model. It is used for the purpose of enabling a search using the determined search venue label. Note that the order of each step shown in FIG. 5 is an example, and unless otherwise specified, the order may be changed as appropriate.

The reception means 101 inputs, via the input unit 24, image data of the space that the poster wishes to rent, designation of a venue label indicating the venue type to which the poster believes the space applies, and other information related to the space. Input of space information including information is accepted (step S101).

The calculation means 103 calculates the likelihood for each venue type of the space based on the trained model and the space image data and designated venue label received in step S101 (step S102).

The determining means 104 determines the search venue label to which the space corresponds based on the likelihood calculated in step S102 (step S103). The determining means 104 stores the search venue label determined in step S103 in association with the space information in the database DB (step S104).

In this embodiment, the search venue label determined in step S103 is stored in the database DB in association with space information in step S104, but when a space search is performed via the space search screen, The search processing means 105 may obtain information on spaces whose likelihood in the search venue label specified as the search condition is higher than a threshold value, and the determination means 104 may assign a search venue label to the space information. .

The determination system includes a reservation means (not shown), and after searching for space information through the space search screen, the searcher can reserve the searched space through the reservation means.

Furthermore, after a predetermined period of time has passed since the previous learning time, or when a predetermined number of space information has been received, the learning means 102 receives the image data and the corresponding information received via the reception means 101. The trained model may be trained again using the venue type associated with the image data as training data. Further, when the learned model is retrained, the calculating means 103 further calculates each venue type of the space using the learned model after the relearning, for the space for which the likelihood for the venue type was calculated before the relearning. You may recalculate the likelihood for .

According to the present invention, a novel technique related to a determination system can be provided.

1: Management server 2A: Poster terminal 2B: Searcher terminal 11, 21: Arithmetic device 12, 22: Main storage device 13, 23: Auxiliary storage device 24: Input section 25: Output section 16, 26: Communication control section 17 , 27: Communication IF unit 101: Reception means 102: Learning means 103: Calculation means 104: Determination means 105: Search processing means 106: Output processing means

The calculation means 103 may calculate the likelihood for all venue types of one space, or may calculate the likelihood only for a predetermined venue type. For example, if there are many spaces that are labeled as "Conference Rooms for Rent" but are not labeled as "Conference Rooms for Rent," searchers will not be able to display spaces that are not "Conference Rooms for Rent" in their search results. Then, only the likelihood for the venue type of “rental conference room” is calculated.

Claims (8)

A determination system that associates types used for space searches from types specified for spaces based on the subjectivity of the poster,
a reception means for accepting image data of a space that a poster wishes to rent and designation of a type for the space;
a learning means for learning a machine learning model using space image data and a specified type as training data;
Calculation means for calculating the likelihood of the space for the type based on the received image data of the space, the type specified for the space, and a learned model;
determination means for determining a type to be associated with the space based on the likelihood;
A judgment system with One or more types are specified from among a plurality of types for the space,
The determination system according to claim 1, wherein the determination means determines whether the space corresponds to each of the plurality of types. The determination system according to claim 1, wherein the determination means associates the type with the space when the likelihood of the space with respect to the type is equal to or greater than a threshold value. 2. The determination system according to claim 1, wherein the learning means performs learning using the image data and the type received via the receiving means as teacher data. The receiving means receives image data transmitted as a main image of the space and image data transmitted as a sub-image,
The determination system according to claim 1, wherein the learning means performs learning using image data transmitted as the main image as teacher data. Equipped with a search processing means for accepting space search requests and transmitting search processing results,
2. The determination system according to claim 1, wherein the search processing means determines the display order of the spaces filtered based on the type based on the likelihood. A determination method that associates a type used for searching a space from types specified for the space based on the subjectivity of the poster, the method comprising:
The computer is
a reception step for receiving image data of a space that the poster wishes to rent and designation of a type for the space;
a learning step of learning a machine learning model using space image data and a specified type as training data;
a calculation step of calculating the likelihood of the space for the type based on the received image data of the space, the type specified for the space, and a learned model;
a determination step of determining a type to be associated with the space based on the likelihood;
Judgment method to perform. A determination program that associates a type used for space search from types specified for a space based on the subjectivity of a poster,
a reception means for accepting image data of a space that a poster wishes to rent and designation of a type for the space;
a learning means for learning a machine learning model using space image data and a specified type as training data;
Calculation means for calculating the likelihood of the space for the type based on the received image data of the space, the type specified for the space, and a learned model;
determination means for determining a type to be associated with the space based on the likelihood;
A determination program having the following.