JP7520097B2 - Determination device, determination method, and determination program - Google Patents

Description

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

In recent years, there has been technology in services that introduce restaurants that select restaurants to recommend based on the preferences of users. In such technology, restaurants to recommend are selected based on features extracted from restaurant introduction information in response to a search query entered by a user (see, for example, Patent Document 1).

JP 2016-53870 A

However, conventional technology leaves room for improvement in providing users with appropriate search services.

The present invention has been made in consideration of the above, and aims to provide a determination device, a determination method, and a determination program that can provide users with an appropriate search service.

To solve the above-mentioned problems and achieve the object, the determination device according to the present invention includes an extraction unit that extracts tag candidates from a search target, and a determination unit that determines whether or not to adopt the tag candidates as tags to be used during a search based on the tag candidates extracted by the extraction unit and the behavioral history of a user corresponding to the tag candidates.

The determination device according to the present invention can provide users with an appropriate search service.

FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. FIG. 2 is a block diagram illustrating an example of a configuration of an information providing device according to the embodiment. FIG. 3 is a diagram illustrating an example of information stored in a user information database according to the embodiment. FIG. 4 is a diagram illustrating an example of information stored in a store information database according to the embodiment. FIG. 5 is a diagram illustrating an example of information stored in the tag information database according to the embodiment. FIG. 6 is a schematic diagram of a periodicity estimation process according to the embodiment. FIG. 7 is a diagram illustrating an example of the scores of tag candidates according to the embodiment. FIG. 8 is a flowchart illustrating an example of an estimation process according to the embodiment. FIG. 9 is a flowchart illustrating an example of a determination process according to the embodiment. FIG. 10 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information providing device according to the embodiment.

Below, the form for implementing the determination device, determination method, and determination program according to the present application (hereinafter, referred to as "embodiment") will be described in detail with reference to the drawings. Note that the determination device, determination method, and determination program according to the present application are not limited to the embodiment.

[Embodiment]
[1. Information Processing]
First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment.

The information providing device 1 according to the embodiment shown in FIG. 1 is an information providing device that provides various web services. The information providing device 1 is an example of a determination device according to the embodiment, and operates, for example, a gourmet website. Note that the information providing device 1 may provide services such as Internet connection, search services, SNS (Social Networking Service), electronic commerce, electronic payment, online games, online banking, online trading, accommodation and ticket reservations, and video and music distribution as web services.

The information providing device 1 is an information providing device that cooperates with the user terminal 10 of each user U and provides API (Application Programming Interface) services for various applications (hereinafter, apps) and various data to the user terminal 10 of each user U, and is realized by a server device, a cloud system, or the like. In addition, the information providing device 1 may actually cooperate with various servers that provide the above-mentioned web services and act as an intermediary for the web services.

The user terminal 10 is a terminal operated by the user U. For example, the user terminal 10 provides the user U with various web services provided by the information providing device 1 via a specified network.

For example, the user terminal 10 provides the user U with various information related to gourmet sites provided by the information providing device 1. The user terminal 10 also provides the information providing device 1 with information related to word-of-mouth (posted information) by the user U.

The information providing device 1 has a store database that stores store information about stores (restaurants) posted on the gourmet site, and a tag information database that serves as a search tag for each store. The information providing device 1 acquires word-of-mouth information acquired from the user terminal 10 (step S1) and stores it in the store information database.

For example, the information providing device 1 provides each user U with word-of-mouth information acquired from the user U along with information about the store. The word-of-mouth information includes the user U's evaluation of the store he or she used (e.g., a 5-point rating), impressions about the store's services, photos taken at the store, etc.

The information providing device 1 uses a predetermined natural language processing to extract tag candidates for each store from the word-of-mouth information (step S2) and store them in the tag information database. In the example shown in FIG. 1, the information providing device 1 extracts tag candidates such as "nice atmosphere" and "delicious eel" from word-of-mouth information about "XX Eel Store" that says "the atmosphere (of the store) is good and the eel is delicious."

Next, the information providing device 1 measures the number of page views (PV) of each store searched for using each tag information (step S3). When the store page of a corresponding store is accessed from the search query "good atmosphere", the information providing device 1 adds the number of page views to the tag candidate "good atmosphere".

The information providing device 1 uses the results of the PV count measurement to estimate the presence or absence of periodicity for each tag candidate. The information providing device 1 uses various statistical processes to estimate the presence or absence of periodicity from the trend in the PV count (step S4).

The periodicity may be, for example, on a seasonal, monthly or weekly basis, but may also be on a day-of-the-week or date-by-date basis. In other words, the information providing device 1 tallies the number of pageviews for each tag candidate on a seasonal or monthly basis, and estimates the presence or absence of periodicity through various statistical processes of the number of pageviews for each tag candidate on a seasonal or monthly basis.

For example, the information providing device 1 calculates a periodicity score for each tag candidate by statistical processing, and estimates that a tag candidate whose calculated periodicity score exceeds a threshold has periodicity. The information providing device 1 may also estimate the presence or absence of periodicity for each store category or type of food offered. The information providing device 1 may also estimate periodicity for each predetermined category classified according to the store's customer unit price, etc.

In the example shown in Figure 1, the tag candidate "good atmosphere" is assumed to have no periodicity, while the tag candidate "delicious eel" is assumed to have periodicity, with the peaks of the tag candidate "delicious eel" being in "January and July." Note that in the following, tag candidates with no periodicity may be referred to as "year-round tags," and tag candidates with periodicity may be referred to as "periodic tags."

Then, the information providing device 1 receives a search request from the user terminal 10 (step S5). The information providing device 1 determines the tags to be adopted for the search request (step S6).

The information providing device 1 varies the score linked to the PV performance for each tag candidate in accordance with the time of search, and, for example, determines a tag candidate whose score exceeds a threshold as a tag to be adopted. For example, the information providing device 1 increases the score of the corresponding periodicity tag in January and July, when the periodicity tag peaks, and decreases the score of the periodicity tag in periods other than the peak.

As a result, during peak periods when the score of a periodicity tag is high, the corresponding store will be ranked higher in search results using the periodicity tag, and during periods other than peak periods, the search ranking of the corresponding store will drop. In other words, the information providing device 1 adjusts the weight of the corresponding tag candidate depending on whether or not the period is one in which the tag candidate is trending.

Then, the information providing device 1 provides the search results to the user terminal 10 that has made the search request (step S7). In this way, the information providing device 1 varies the scores of the tag candidates in accordance with the periodicity of the tag candidates.

This enables the information providing device 1 to provide appropriate search results in accordance with the periodicity, and therefore an appropriate search service can be provided to the user U. Furthermore, the information providing device 1 can provide a search service in accordance with trends related to the offerings by determining whether or not to adopt candidate tags related to offerings (e.g., eel) provided at a restaurant as tags.

2. Example of the configuration of the information providing device
Next, a configuration example of the information providing device 1 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information providing device 1 according to the embodiment. As shown in Fig. 2, the information providing device 1 has a communication unit 2, a storage unit 3, and a control unit 4.

(Communication unit 2)
The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 is connected to a network in a wired or wireless manner.

(Memory unit 3)
The storage unit 3 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , the storage unit 3 has a user information database 31, a store information database 32, and a tag information database 33.

(User information database 31)
The user information database 31 is a database that stores various types of user information related to the user U. Fig. 3 is a diagram showing an example of information stored in the user information database 31 according to the embodiment.

The user information database 31 stores information such as "user ID," "account information," "search history," "usage history," and "account information" in association with each other. "User ID" is an identifier for identifying each user.

"Account information" is information registered by each user U for various web services provided by the information providing device 1. Account information includes information such as name, age, occupation, address, family composition, etc.

"Search history" is the search history of user U identified by the corresponding user ID. "Usage history" is the usage history of user U identified by the corresponding user ID. The usage history is a history of stores used by user U via a gourmet site provided by the information providing device 1. The usage history may identify stores used by user U from a history of location information of the user terminal 10 or a usage history of an electronic payment service using the user terminal 10. The usage history may also identify stores used by user U from word-of-mouth information by user U or posts on SNS.

"Account information" is account information of user U identified by the corresponding user ID. The account information is information about an account for an electronic payment service using the user terminal 10, but may also be linked to a bank account, securities account, or credit card.

(Store information database 32)
The store information database 32 is a database that stores various store information related to stores posted on the gourmet site. Fig. 4 is a diagram showing an example of information stored in the store information database 32 according to the embodiment.

As shown in FIG. 4, the store information database 32 stores information on items such as "store ID," "store information," "posted information," "PV history," and "purpose of use," in association with each other.

"Store ID" is an identifier for identifying each store. "Store information" is basic information about each store, including the store name, business hours, address, phone number, store introduction, menu and courses, and available coupons.

"Posted information" is information about reviews posted by each user, including each user's ratings, impressions, and photos of the store.

"PV history" is the access history to the store page of the corresponding store, and includes information such as when, by whom, and what search query was used to access the store page. Usage history is the usage history of the store by each user, and includes information such as when and what type of user used the store, as well as information regarding the amount paid.

"Usage" is the usage of the corresponding store. Note that the usage may be estimated from the posted information, for example, or may be extracted from the store information. In addition, since the usage varies depending on the user, multiple usages may be included depending on the user's attributes, etc.

(Tag information database 33)
The tag information database 33 is a database that stores various types of tag information related to tags and tag candidates. Fig. 5 is a diagram showing an example of information stored in the tag information database 33 according to the embodiment.

As shown in FIG. 5, the tag information database 33 stores information for each store in the fields of "search query," "type," "PV performance," "periodicity," "peak," and "abnormal flag," in association with each other.

"Query" is a query tagged to the corresponding store. "Type" indicates the type of the corresponding query, being "0" if it is a tag and "1" if it is a candidate tag. "PV performance" is the history of the store's PV based on the corresponding query.

"Periodicity" refers to whether or not the corresponding query is periodic. "Peak" refers to the period when the periodic query peaks. "Abnormality flag" refers to whether or not the corresponding query is abnormal. For example, if the PV is behaving normally, it is set to "0," and if the PV is behaving abnormally, it is set to "1." Examples of abnormal behavior include when the corresponding query is used frequently in a short period of time (when it goes viral).

(Control unit 4)
The control unit 4 is a controller, and is realized by, for example, a central processing unit (CPU), a micro processing unit (MPU), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information providing device 1 using a storage area such as a RAM as a working area. In the example shown in FIG. 2, the control unit 4 has an acquisition unit 41, an extraction unit 42, an estimation unit 43, a determination unit 44, a proposal unit 45, and a provision unit 46.

(Acquisition unit 41)
The acquisition unit 41 acquires various requests including search queries and word-of-mouth information from the user terminal 10 via the communication unit 2. The acquisition unit 41 also acquires reservation information for each store on the website from the user terminal 10.

(Extraction Unit 42)
The extraction unit 42 extracts tag candidates from the search target. The extraction unit 42 extracts tag candidates from store information of each store that is the search target and word-of-mouth information of each store. The extraction unit 42 is able to autonomously generate tag candidates by extracting tag candidates from word-of-mouth information.

The extraction unit 42 analyzes the word-of-mouth information and extracts frequently occurring words and positive words as tag candidates. Positive words are keywords such as evaluations of each store that is the subject of the search, and may be words that indicate favorable evaluations.

In other words, a positive word is a keyword that is determined to be favorable by any of a variety of determination means, and is a concept that includes keywords for the store itself or objects (food, etc.) related to the corresponding store.

(Estimation unit 43)
The estimation unit 43 estimates the presence or absence of periodicity regarding searches for tag candidates based on the behavior history of the user. The estimation unit 43 estimates the presence or absence of periodicity for each tag candidate by using a pair of a search query and a store page used by the user as the behavior history of the user. The behavior history may be a predetermined conversion by the user. The predetermined conversion may be the use of a store, a reservation, or favorite registration, or may be the posting of word-of-mouth information.

The estimation unit 43 estimates the presence or absence of periodicity for each tag candidate by performing various statistical processes on the PV performance of each tag candidate registered in the tag information database 33. The estimation unit 43 calculates a periodicity score for each tag candidate by performing various statistical processes on the PV performance of each tag candidate in each period. The PV performance corresponds to an example of a browsing history.

The estimation unit 43 estimates that a tag candidate whose calculated periodicity score exceeds a threshold has periodicity, and estimates that a tag candidate whose periodicity score is equal to or less than the threshold has no periodicity. The estimation unit 43 may also estimate the presence or absence of periodicity from the periodicity of other similar tag candidates.

Figure 6 is a schematic diagram of the periodicity estimation process according to the embodiment. As shown in Figure 6, the first hierarchical level is "hot pot dishes," and the presence or absence of periodicity for "lemon hot pot" in the second hierarchical level below is estimated.

For example, when a new peak for "lemon hot pot" is observed in the PV performance, the estimation unit 43 estimates whether or not there is periodicity for lemon hot pot based on the periodicity of hot pot dishes in a higher hierarchy. More specifically, the estimation unit 43 estimates that the current peak for lemon hot pot is based on periodicity when the peak period for "hot pot dishes," which already have periodicity, overlaps with the peak period for lemon hot pot or the shapes of the peaks are similar.

As a result, even if a new tag candidate peak is observed, the presence or absence of periodicity can be appropriately estimated from the peaks of other similar tag candidates. Note that the estimation unit 43 can estimate other tag candidates similar to the tag candidate by using a dictionary or knowledge base.

In addition, when a peak of a new tag candidate is observed, for example, when no periodicity can be found even by using the periodicity of similar tag candidates, the estimation unit 43 may set an abnormality flag. For example, if the peak of "lemon hotpot" is a single peak, an abnormality flag will be set.

(Determination unit 44)
The determination unit 44 determines whether or not to adopt the tag candidate as a tag to be used during a search, based on the tag candidate extracted by the extraction unit 42 and the behavior history of the user corresponding to the tag candidate.

The determination unit 44 determines, for example, whether or not to adopt a periodic tag, which is a tag candidate determined by the estimation unit 43 to have periodicity, as a tag. Note that year-round tags are excluded from the determination of whether or not to adopt them as tags in order to keep their scores constant.

The determination unit 44 varies the score according to the period of each periodic tag, and determines that periodic tags whose scores exceed a threshold value are to be adopted as tags. FIG. 7 is a diagram showing an example of the scores of tag candidates according to the embodiment. Note that FIG. 7 shows the ranking of each tag candidate based on the scores in period A and period B, and the score of the year-round tag "good atmosphere" is assumed to be constant.

As shown in Figure 7, during period A, when the tag candidate "delicious eel" which is a periodic tag reaches its peak, the score of the tag candidate "delicious eel" increases, and is therefore higher than the score of the tag candidate "good atmosphere" which is a year-round tag.

On the other hand, for example, in a period B other than period A, the score of the tag candidate "eel is delicious" decreases, and the scores of both tag candidates are reversed. The determination unit 44 determines the tag candidate "eel is delicious" as a tag in period A, and does not determine it as a tag candidate in period B, for example. As a result, the tag candidate corresponding to the period when "eel is delicious" is adopted as a tag.

The determination unit 44 may also determine whether or not to adopt a tag candidate as a tag depending on the attributes of the user. The attributes of the user may be classified, for example, according to various demographic attributes, and may be classified according to at least one of the tendencies of the stores used, the tendencies of the search queries, and the tendencies of the store pages viewed. For example, the tendencies of the stores used may be further subdivided according to the store category, price range, time of day or day of the week, whether the user is accompanied, etc.

For example, the determination unit 44 performs clustering of users based on the behavioral history of each user and classifies the users into each attribute. Then, the determination unit 44 determines whether or not to adopt a tag candidate as a tag according to the behavioral tendency of each attribute.

The determination unit 44 may also analyze the user's behavioral history, estimate the purpose of use this time, and determine whether or not to adopt each tag candidate as a tag. For example, when the determination unit 44 estimates the user's purpose of use as "girls' get-together," it determines that the tag candidate "girls' get-together" should be adopted as a tag.

As a result, the determination unit 44 determines whether or not to adopt the tag candidate as a tag, depending on the attributes of the user and the purpose of the user. For example, the determination unit 44 determines not to adopt a tag candidate such as "luxury," which is the polar opposite, as a tag for a group of users who click on a store with the tag "reasonable." In addition, if the estimated purpose of the user is a girls' get-together, the determination unit 44 increases the score of the tag candidate "girls' get-together" and adopts it as a tag.

(Proposal Unit 45)
The suggestion unit 45 suggests, at the time of a search by the user, the tag candidates determined to be adopted as tags by the determination unit 44. When a search screen or the like is displayed on the user terminal 10, the suggestion unit 45 suggests, to the user, the tag candidates to be adopted as tags.

In the example described in FIG. 7, the suggestion unit 45 will suggest the tag candidate "eel is delicious" to the user during period A. The suggestion unit 45 may also suggest the tag candidate to the user as a search category or one of the special features.

For example, in this case, a new search category or feature "delicious eel" will be generated for period A, allowing users to easily search for stores according to periodicity.

(Providing unit 46)
When a search is performed using a tag candidate determined by the determination unit 44 to be adopted as a tag, the providing unit 46 provides a search result including a search target corresponding to the tag candidate. For example, the providing unit 46 extracts stores corresponding to the search criteria input by the user from the store information database 32, and provides information on the extracted stores to the user. The providing unit 46 extracts stores by matching the search criteria and the tags of each store.

When providing information about the store page of each store, the providing unit 46 may generate a screen in which tags from reviews of each store are highlighted. For example, the character string "delicious eel" is highlighted in the reviews, so that users can easily understand the season of the food provided at the store from the reviews.

3. Processing flow
Next, a process flow executed by the information providing device 1 according to the embodiment will be described with reference to Fig. 8 and Fig. 9. Fig. 8 is a flowchart showing an example of an estimation process according to the embodiment. Fig. 9 is a flowchart showing an example of a determination process according to the embodiment.

As shown in FIG. 8, the information providing device 1 acquires posted information posted by each user on the gourmet site (step S101). Next, the information providing device 1 extracts tag candidates from the posted information (step S102).

Then, the information providing device 1 performs a PV measurement process for each tag candidate (step S103), and estimates the presence or absence of periodicity for each tag candidate by performing various statistical processes based on the results of the PV measurement process (step S104). Then, the information providing device 1 ends the process.

Next, the process flow of the determination process according to the embodiment will be described with reference to FIG. 9. As shown in FIG. 9, the information providing device 1 varies the score for the periodicity tag according to the periodicity (step S111).

The information providing device 1 then determines whether the score of the periodic tag exceeds the threshold (step S112), and if it determines that the score of the periodic tag exceeds the threshold (step S112; Yes), it adopts the corresponding periodic tag as a tag (step S113).

In addition, if the information providing device 1 determines that the score of the periodicity tag is equal to or less than the threshold (step S112; No), it ends the process without going through the process of step S113.

4. Modifications
In the above embodiment, the search target is a store (restaurant), but the present invention is not limited to this. The search target may be a store or a product that is open on an EC site, as long as the search target displays user posted information. The present invention may also be applied to various reservation services, such as a hotel reservation service or a hair salon reservation service.

5. Effects
As described above, the information providing device 1 according to the present application includes an extraction unit 42 that extracts tag candidates from a search target, and a determination unit 44 that determines whether or not to adopt the tag candidates as tags to be used during a search, based on the tag candidates extracted by the extraction unit 42 and the behavioral history of the user corresponding to the tag candidates.

The information providing device 1 also includes an estimation unit 43 that estimates whether or not there is periodicity in the search for the tag candidates based on the behavioral history, and a determination unit 44 determines whether or not to adopt the tag candidate that is determined by the estimation unit 43 to have periodicity as a tag.

The determination unit 44 determines that the tag candidate that peaks during the period to be determined should be adopted as a tag. The estimation unit 43 estimates whether the tag candidate has periodicity based on the periodicity of other similar tag candidates.

The information providing device 1 also includes a suggestion unit 45 that suggests the tag candidates determined to be adopted as tags when a user performs a search. When a search is performed using the tag candidates determined to be adopted as tags, the information providing device 1 provides search results that include search targets that correspond to the tag candidates.

The estimation unit 43 also estimates the presence or absence of periodicity based on the browsing history of the search target. The estimation unit 43 also estimates the presence or absence of periodicity based on the browsing history of the search target from the tag candidates.

The extraction unit 42 also extracts tag candidates from posted information related to the search target. The extraction unit 42 also extracts tag candidates from posted information related to restaurants as the search target. The determination unit 44 also determines whether or not to adopt tag candidates related to offerings provided at restaurants as tags.

The determination unit 44 also determines whether or not to adopt the tag candidate as a tag to be used during a search, depending on the attributes of the user. The determination unit 44 also determines whether or not to adopt the tag candidate as a tag to be used during a search, depending on the purpose of use of the search target.

By performing any one or a combination of the above-mentioned processes, the determination device according to the present application can provide users with an appropriate search service.

6. Hardware Configuration
The information providing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 10, for example. Fig. 10 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which a calculation device 1030, a primary storage device 1040, a secondary storage device 1050, an output I/F (Interface) 1060, an input I/F 1070, and a network I/F 1080 are connected by a bus 1090.

The arithmetic device 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, programs read from the input device 1020, and the like, and executes various processes. The arithmetic device 1030 is realized, for example, by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

The primary storage device 1040 is a memory device such as a RAM (Random Access Memory) that primarily stores data used by the arithmetic device 1030 for various calculations. The secondary storage device 1050 is a storage device in which data used by the arithmetic device 1030 for various calculations and various databases are registered, and is realized by a ROM (Read Only Memory), a HDD (Hard Disk Drive), a SSD (Solid State Drive), a flash memory, or the like. The secondary storage device 1050 may be an internal storage device or an external storage device. The secondary storage device 1050 may be a removable storage medium such as a USB memory or a SD (Secure Digital) memory card. The secondary storage device 1050 may be a cloud storage device (online storage device), a NAS (Network Attached Storage), a file server, or the like.

The output I/F 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various types of information, such as a display, projector, printer, etc., and is realized by a connector conforming to a standard such as USB (Universal Serial Bus), DVI (Digital Visual Interface), or HDMI (registered trademark) (High Definition Multimedia Interface). The input I/F 1070 is an interface for receiving information from various input devices 1020, such as a mouse, keyboard, keypad, button, scanner, etc., and is realized by a USB, etc.

In addition, the output I/F 1060 and the input I/F 1070 may be wirelessly connected to the output device 1010 and the input device 1020, respectively. That is, the output device 1010 and the input device 1020 may be wireless devices.

The output device 1010 and the input device 1020 may be integrated together, such as a touch panel. In this case, the output I/F 1060 and the input I/F 1070 may also be integrated together as an input/output I/F.

The input device 1020 may be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), 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.

The network I/F 1080 receives data from other devices via the network N and sends it to the computing device 1030, and also transmits data generated by the computing device 1030 to other devices via the network N.

The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output I/F 1060 and the input I/F 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

For example, when the computer 1000 functions as the information providing device 1, the arithmetic unit 1030 of the computer 1000 realizes the functions of the control unit 4 by executing a program loaded onto the primary storage device 1040. The arithmetic unit 1030 of the computer 1000 may also load a program acquired from another device via the network I/F 1080 onto the primary storage device 1040 and execute the loaded program. The arithmetic unit 1030 of the computer 1000 may also cooperate with other devices via the network I/F 1080 and use the functions and data of a program by calling them from other programs of the other devices.

[7. Other]
Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that a person skilled in the art can easily imagine, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

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 all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

For example, the information providing device 1 described above may be realized by multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

The above-described embodiments and variations can be combined as appropriate to the extent that they do not cause inconsistencies in the processing content.

In addition, the above-mentioned "section, module, unit" can be read as "means" or "circuit." For example, an acquisition unit can be read as an acquisition means or an acquisition circuit.

Reference Signs List 1 Information providing device 2 Communication unit 3 Storage unit 4 Control unit 10 User terminal 31 User information database 32 Store information database 33 Tag information database 41 Acquisition unit 42 Extraction unit 43 Estimation unit 44 Determination unit 45 Proposal unit 46 Providing unit U User

Claims (13)

an extraction unit that extracts tag candidates from a search target;
an estimation unit that estimates whether or not there is periodicity regarding searches for the tag candidates based on a behavior history of a user corresponding to the tag candidates extracted by the extraction unit;
a determination unit that determines , for the tag candidate determined by the estimation unit to have periodicity, whether or not to adopt the tag candidate as a tag to be used during a search. The determination unit is
The determination device according to claim 1 , wherein the tag candidate that reaches a peak during a period to be determined is determined to be adopted as the tag. The estimation unit is
The determination device according to claim 1 , wherein the presence or absence of periodicity of the tag candidate is estimated based on periodicity of other similar tag candidates. The determination device according to claim 1 , further comprising a suggestion unit that suggests the tag candidate determined to be adopted as the tag at the time of a search by a user. The determination device according to claim 1 , further comprising: a providing unit that, when a search is performed using the tag candidate determined to be adopted as the tag, provides search results including the search target corresponding to the tag candidate. The estimation unit is
The determination device according to claim 1 , wherein the presence or absence of periodicity is estimated based on a browsing history in which the search target was viewed from the tag candidates. The extraction unit is
The determination device according to claim 1 , wherein the tag candidates are extracted from posted information related to the search target. The extraction unit is
The determination device according to claim 7 , wherein the tag candidates are extracted from posted information related to restaurants as the search target. The determination unit is
The determination device according to claim 8 , further comprising: a determination unit configured to determine whether or not to adopt the tag candidate related to the food provided at the restaurant as the tag. The determination unit is
The determination device according to claim 1 , further comprising: a determination unit that determines whether or not to adopt the tag candidate as the tag to be used in a search, depending on an attribute of the user. The determination unit is
The determination device according to claim 1 , further comprising: a determination unit that determines whether or not to adopt the tag candidate as the tag to be used during a search, depending on a purpose of use of the search target estimated from a service usage history of the user. A computer-implemented method for determining whether a
An extraction step of extracting tag candidates from the search target;
an estimation step of estimating whether or not there is periodicity regarding searches for the tag candidates based on a behavior history of a user corresponding to the tag candidates extracted by the extraction step;
a determination step of determining whether or not to adopt the tag candidate determined to have periodicity by the estimation step as a tag to be used during a search. an extraction step for extracting tag candidates from a search target;
an estimation step of estimating whether or not there is periodicity in searches for the tag candidates based on a behavior history of a user corresponding to the tag candidates extracted by the extraction step;
a determination step of determining whether or not to adopt the tag candidate determined to have periodicity by the estimation step as a tag to be used during a search.

Images