Suggestion system, suggestion method, and program

Abstract

To display word-of-mouth information to be a reference for examining a visit spot for each user.SOLUTION: A suggestion system includes: a storage section that stores spot information indicating a spot, word-of-mouth information about the spot, and scene / situation information indicating a scene or a situation of a poster of the word-of-mouth information; an acquisition section that acquires scene / situation information indicating a scene or a situation of a user in response to reception of a search request designating the spot from the user; an extraction section that compares the scene / situation information of the user acquired by the acquisition section with the scene / situation information of the poster who has posted the word-of-mouth information about the spot designated by the search request stored in the storage section and extracts word-of-mouth information to be suggested to the user from the word-of-mouth information stored in the storage section on the basis of a comparison result; and a suggestion section that suggests the word-of-mouth information extracted by the extraction section.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a suggestion system, a suggestion method, and a program.

Background Art

[0002] Conventionally, a technique for providing content including word-of-mouth in response to a user's search request is known. This type of technique is described in, for example, Patent Document 1. The information processing apparatus described in Patent Document 1 includes a control unit that estimates potential requests according to the current user situation, searches for word-of-mouth information corresponding to the requests, and controls to present the searched word-of-mouth information to the user. The control unit searches from word-of-mouth information transmitted by other users around the user.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technique of displaying word-of-mouth information, even if the word-of-mouth is displayed in the order of new arrivals or high evaluations, there is a problem that the word-of-mouth that is useful for everyone is displayed at the top, but the word-of-mouth that is more useful for each individual user is not displayed at the top.

[0005] The present invention has been made in view of the above problems, and an object thereof is to provide a suggestion system, a suggestion method, and a program capable of displaying word-of-mouth information that is useful for considering visit spots for each individual user.

Means for Solving the Problems

[0006] (1) One aspect of the present invention is a suggestion system comprising: a storage unit that stores spot information indicating a spot, word-of-mouth information regarding the spot, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information; an acquisition unit that acquires scene / situation information indicating the scene or situation of a user in response to receiving a search request designating a spot from the user; an extraction unit that compares the scene / situation information of the user acquired by the acquisition unit with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot designated by the search request stored in the storage unit, and extracts word-of-mouth information to be suggested to the user from the word-of-mouth information stored in the storage unit based on the comparison result; and a suggestion unit that suggests the word-of-mouth information extracted by the extraction unit.

[0007] (2) One aspect of the present invention is that the suggestion unit may transmit the scene / situation information of the poster as a reason for suggesting the word-of-mouth information based on the comparison result.

[0008] (3) One aspect of the present invention may include a scene / situation estimation unit that estimates the scene or situation of the poster based on the content of the word-of-mouth information of the poster.

[0009] (4) One aspect of the present invention includes a sufficiency estimation unit that estimates the sufficiency of information indicating that a plurality of types of elements emphasized by the user are included in the word-of-mouth information of the poster, and the suggestion unit may suggest word-of-mouth information based on the sufficiency estimated by the sufficiency estimation unit.

[0010] (5) One aspect of the present invention is that the extraction unit extracts word-of-mouth information narrowed down based on the positivity of the word-of-mouth, and the suggestion unit includes the word-of-mouth information narrowed down based on the positivity of the word-of-mouth in list content including a list of spots, the word-of-mouth information ranked based on the scene / situation and the information sufficiency, and may include the word-of-mouth information ranked based on the suggestion score in detail content including the details of the spot.

[0011] (6) One aspect of the present invention is that an information processing apparatus stores spot information indicating a spot, word-of-mouth information regarding the spot, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information; the information processing apparatus acquires scene / situation information indicating the scene or situation of a user in response to receiving a search request for specifying a spot from the user; the information processing apparatus compares the acquired scene / situation information of the user with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot specified by the stored search request, and extracts word-of-mouth information to be suggested to the user from the stored word-of-mouth information based on the comparison result; and the information processing apparatus suggests the extracted word-of-mouth information. This is a suggestion method.

[0012] (7) One aspect of the present invention is a program for a computer of an information processing apparatus to store spot information indicating a spot, word-of-mouth information regarding the spot, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information; acquire scene / situation information indicating the scene or situation of a user in response to receiving a search request for specifying a spot from the user; compare the acquired scene / situation information of the user with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot specified by the stored search request, and extract word-of-mouth information to be suggested to the user from the stored word-of-mouth information based on the comparison result; and suggest the extracted word-of-mouth information.

Advantages of the Invention

[0013] According to one aspect of the present invention, it is possible to display word-of-mouth information that is useful for considering visited spots for each individual user.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Embodiments for Carrying Out the Invention

[0015] Hereinafter, a suggestion system, a suggestion method, and a program to which the present invention is applied will be described with reference to the drawings. The suggestion system, the suggestion method, and the program to which the present invention is applied receive a search request specifying a spot from a user (reference person), and compare the scene / situation information of the user with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot specified by the search request. Based on the comparison result, word-of-mouth information to be suggested to the user is extracted from the word-of-mouth information, and the extracted word-of-mouth information is suggested. Suggestion is a process of providing data including a list of contents or word-of-mouth or details of contents or word-of-mouth to the user. Thereby, the suggestion system realizes an information providing service that is highly convenient for the user. In the following embodiments, the application field of the suggestion system is tourism and walking around the town, but it is not limited thereto and can be applied to any field such as shopping. Also, in the following embodiments, a person who refers to word-of-mouth information or contents is described as a reference person or a user, and a person who posts word-of-mouth information is described as a poster.

[0016] <Configuration of Suggestion System> First, the overall configuration and processing content of the suggestion system 1 in the embodiment will be described. FIG. 1 is a block diagram showing a configuration example of the suggestion system 1 in the embodiment. The suggestion system 1 includes, for example, a poster terminal device 100, a reference person terminal device 110, a suggestion device 200, a content providing device 300, and an environment information providing device 400. The poster terminal device 100, the reference person terminal device 110, the suggestion device 200, the content providing device 300, and the environment information providing device 400 are connected to a communication network NW, for example. Each device connected to the communication network NW is provided with a communication interface such as a NIC (Network Interface Card) or a wireless communication module (not shown in FIG. 1). The communication network includes, for example, the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), a cellular network, and the like.

[0017] The contributor terminal device 100 and the reference terminal device 110 are portable terminal devices such as smartphones and tablet terminals. The contributor terminal device 100 and the reference terminal device 110 activate a UA (User Agent) such as a browser or an application program. The UA is an application for receiving an information providing service provided by, for example, the suggestion device 200. The contributor terminal device 100 and the reference terminal device 110 generate operation information based on a user's operation, position information of the reference terminal device 110 using GPS (Global Positioning System, Global Positioning Satellite), and various requests, and transmit them to the suggestion device 200 or the content providing device 300.

[0018] The contributor terminal device 100 transmits various information such as a posting request designating a spot, word-of-mouth information, and image information, and causes the suggestion device 200 to store the transmitted various information. The reference terminal device 110 transmits a search request designating a spot, and performs display processing, operation reception processing, etc. using the content provided by the suggestion device 200 and the content received from the content providing device 300.

[0019] The suggestion device 200 is, for example, an information processing device that performs processing for an information providing service. The suggestion device 200 includes, for example, a reception unit 210, a scene / situation acquisition unit 220, a word-of-mouth information extraction unit 230, a scene / situation estimation unit 240, a fulfillment degree estimation unit 250, a suggestion unit 260, and a database unit 270. Functional units such as the reception unit 210, the scene / situation acquisition unit 220, the word-of-mouth information extraction unit 230, the scene / situation estimation unit 240, the fulfillment degree estimation unit 250, and the suggestion unit 260 are realized, for example, by a processor such as a CPU (Central Processing Unit) executing a program stored in a program memory. Also, some or all of these functional units may be realized by hardware such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field-Programmable Gate Array), or may be realized by the cooperation of software and hardware.

[0020] The reception unit 210 receives requests such as a posting request transmitted by the poster terminal device 100 and a search request transmitted by the reference user terminal device 110.

[0021] The scene / situation acquisition unit 220 acquires scene / situation information indicating the scene or situation of the user in response to receiving a search request in which the user designates a spot. The scene or situation is information such as co-travelers, time zone, weather, location, etc. The scene / situation acquisition unit 220 may acquire environmental information such as the weather of the spot from the environmental information providing device 400 based on the search request. The scene / situation of the user (reference user) acquired by the scene / situation acquisition unit 220 is stored in the database unit 270 as word-of-mouth reference user attribute data 274.

[0022] The word-of-mouth information extraction unit 230 compares the scene / situation information of the referrer acquired by the scene / situation acquisition unit 220 with the scene / situation information of the poster who posted word-of-mouth information regarding the spot designated by the search request stored in the database unit 270, and extracts word-of-mouth information to be suggested to the user from the word-of-mouth information stored in the database unit 270 based on the comparison result.

[0023] The scene / situation estimation unit 240 estimates the scene or situation of the poster based on the content of the word-of-mouth information of the poster. The scene or situation of the poster estimated by the scene / situation estimation unit 240 is stored in the database unit 270 as word-of-mouth poster attribute data 272.

[0024] The richness estimation unit 250 estimates the information richness indicating that a plurality of types of elements that the user values are included in the word-of-mouth information of the poster. The information richness estimated by the richness estimation unit 250 is stored in the database unit 270 as word-of-mouth poster attribute data 272.

[0025] The suggestion unit 260 suggests the word-of-mouth information extracted by the word-of-mouth information extraction unit 230. Specifically, the suggestion unit 260 transmits display data for displaying a spot list screen or a spot detail screen including the word-of-mouth of the poster who visited the spot, together with the content regarding the spot requested by the user, to the referrer terminal device 110. The suggestion unit 260 may transmit the scene / situation information of the poster to the referrer terminal device 110 as the reason for suggesting the word-of-mouth information based on the comparison result of the word-of-mouth information extraction unit 230. The suggestion unit 260 may suggest the word-of-mouth information based on the richness estimated by the richness estimation unit 250.

[0026] The word-of-mouth information extraction unit 230 may extract word-of-mouth information based on the scene / situation information of the reference person acquired by the scene / situation acquisition unit 220. The suggestion unit 260 may include the word-of-mouth information ranked based on the suggestion score calculated from the scene / situation and information sufficiency and statistical information, for the word-of-mouth information narrowed down based on the freshness, recommendability, sentence length, and positivity of the word-of-mouth, in the list content including the list of spots, and may include the word-of-mouth information ranked based on the suggestion score for all the word-of-mouth information without performing narrowing down, in the detailed content including the details of the spots.

[0027] The database unit 270 is realized, for example, by an HDD (Hard Disc Drive), a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), or a RAM (Random Access Memory), or a hybrid type storage device using a plurality of these. The database unit 270 may be realized by an external storage device accessible via various networks. As an example of the external storage device, a NAS (Network Attached Storage) device can be mentioned. The database unit 270 manages the information necessary for the processing of each unit in the suggestion device 200. The database unit 270 is a storage unit that stores spot information indicating spots, word-of-mouth information regarding the spots, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information.

[0028] The content providing device 300 is, for example, a server device that provides various contents in response to a search request from the viewer terminal device 110. The content providing device 300 provides contents related to various spots such as restaurants, stores, public facilities (such as parks), transportation facilities, and for-profit facilities at travel destinations. The content providing device 300 stores various content data in the content storage unit 300A, for example. Content attribute information indicating attributes such as content categories (meal category, accommodation category, shopping category, sightseeing category) is added to the content data. The attributes of the content are information indicating the nature of the content, and are, for example, information corresponding to the scene or situation of the content.

[0029] The environmental information providing device 400 is a server device that distributes environmental information that changes moment by moment, such as weather information, traffic information, and disaster information. The environmental information providing device 400 transmits environmental information in response to a request from, for example, the suggestion device 200. Note that the environmental information may include current location information and spot information indicating the current location spot (for example, store name, tourist destination name).

[0030] <Overview of the operation of the suggestion system 1> FIG. 2 is a diagram for explaining an example of the concept of suggesting content and word-of-mouth based on the scene / situation in the embodiment. First, the viewer terminal device 110 transmits a request specifying travel records, spots, etc. to the suggestion device 200 before the user's trip (before the trip). The suggestion device 200 suggests content including word-of-mouth information and photos shared as travel records, and content including photos and word-of-mouth shared in relation to the spot. Thereby, the suggestion system 1 allows the user to view the travel records, shared photos, and word-of-mouth posted by the poster, and encourages the user to want to have the same experience as the poster.

[0031] During the user's trip, the reference terminal device 110 sends a request to the suggestion device 200 to view the travel record specifying the spots. The suggestion device 200 suggests contents such as photos and reviews related to the spots. Thereby, the suggestion system 1 can make the user discover that they want to have the same experience as the poster by allowing the user to view the photos and reviews posted by the poster.

[0032] After the trip, the poster terminal device 100 posts the travel record, photos, and reviews related to the spots. Thereby, the suggestion device 200 can accumulate the reviews related to the spots.

[0033] FIG. 3 is a diagram showing the relationship between the poster, the review, the scene / situation, and the reference person in the embodiment. FIG. 4 is a diagram showing an example of the content to be viewed by the reference person in the embodiment. When the poster terminal device 100 posts review information, the suggestion device 200 accumulates the review information (review text data 276) in the database unit 270 in association with the spots and the scene / situation (review poster attribute data 272). In response to a request from the reference terminal device 110, the suggestion device 200 sends to the reference terminal device 110 the spots corresponding to the request and the review information of the scene / situation corresponding to the scene / situation of the reference person. For example, when the scene / situation of the reference person is "sunset" and "with children", the suggestion device 200 causes the reference terminal device 110 to display a list of contents including, for example, the content in which review information related to the sunset among the contents related to the spot is posted, and the review information, and the content in which review information related to "with children" among the contents related to the spot is posted, and the review information. Thereby, the suggestion system 1 can attach the real experience of the poster and the reviews including the scene / situation to the content list in order to encourage an enjoyable way according to the scene / situation.

[0034] FIG. 5 is a diagram showing an example of the spot list screen and the spot detail screen in the embodiment. The spot list screen includes the content image on which the spot is posted, the word-of-mouth image of the content, and the other content images on which the spot is posted. The word-of-mouth information on the spot list screen is positive word-of-mouth information that conveys the charm of the spot. The word-of-mouth image includes a poster icon, a word-of-mouth title image, a word-of-mouth text image, a recommended degree icon, and a scene / situation icon. The scene / situation icon indicates the scene / situation information of the poster as the reason for suggesting the word-of-mouth information. In the example of FIG. 5, it shows that the "family" and "rain" of the scene / situation corresponding to the content displayed at the top of the spot list screen match the scene / situation of the viewer.

[0035] The spot detail screen is a screen that shows the details of the content selected by the viewer among the content included in the spot list screen. The spot detail screen displays the word-of-mouth with similar scene / situations at the top for the spots that the viewer felt charming among the spots displayed on the spot list screen. The suggestion system 1 provides information that contributes to the user's decision-making by displaying the spot detail screen on the viewer terminal device 110.

[0036] The word-of-mouth information extraction unit 230 extracts word-of-mouth information based on the scene / situation information of the viewer obtained by the scene / situation acquisition unit 220. The suggestion unit 260 includes the word-of-mouth information ranked based on the suggestion score calculated from the scene / situation, information sufficiency, and statistical information for the word-of-mouth information narrowed down based on the freshness, recommended degree, sentence length, and positivity of the word-of-mouth in the content (spot list screen) including the list of spots, and includes the word-of-mouth information ranked based on the suggestion score for all the word-of-mouth information without narrowing down in the content (spot detail screen) including the details of the spot.

[0037] [Overall Processing of Suggestion System 1] FIG. 6 is a diagram showing an example of processing in the reference terminal device 110, the suggestion device 200, and the database unit 270 in the suggestion system 1 according to the embodiment. The database unit 270 stores, in advance, word-of-mouth poster attribute data 272 including scene / situation information indicating the scene or situation of the word-of-mouth information poster, word-of-mouth referrer attribute data 274 including scene / situation information indicating the scene or situation of the word-of-mouth information referrer, word-of-mouth text data 276 as word-of-mouth information regarding a spot, and word-of-mouth statistical data 278. In addition, the content providing device 300 stores spot information indicating spots to be suggested to the referrer.

[0038] First, the reference terminal device 110 transmits a spot list request or a spot detail request to the suggestion device 200 (step S200). The suggestion device 200 performs a calculation process of scene / situation similarity in processes 1-1 and 1-2 (steps S100, S102), performs a calculation process of information sufficiency in process 2 (step S104), performs a calculation process of a suggestion score in process 3 (step S106), and creates a suggestion screen in process 4 (step S108). The suggestion device 200 transmits display data for displaying the suggestion screen to the reference terminal device 110, and the reference terminal device 110 displays a spot list screen or a spot detail screen as the suggestion screen based on the display data (step S202). Hereinafter, each process will be described in detail.

[0039] [Process 1-1] The suggestion device 200 performs process 1-1 in response to receiving a spot list request or a spot detail request by the reception unit 210 (step S100). Process 1-1 is a calculation process of scene / situation similarity. The calculation process of scene / situation similarity is a process of calculating the similarity between the scene or situation of the referrer and the scene or situation of the poster based on the word-of-mouth poster attribute data 272, the word-of-mouth referrer attribute data 274, and the word-of-mouth text data 276. Process 1-1 calculates the similarity regarding companions and weather among the scene / situation, but is not limited thereto.

[0040] FIG. 7 is a diagram for explaining the content of Process 1-1 in the embodiment. (a) is an example of word-of-mouth data, (b) is a diagram showing an example of data of a reference person, and (c) is a diagram showing an example of the similarity of the scene / situation for each contributor with respect to the reference person. The word-of-mouth data in FIG. 7(a) includes, for example, a word-of-mouth serial number, a spot ID, a word-of-mouth contributor, a word-of-mouth title, word-of-mouth text data 276, and the accompanying person at the time of visit and the weather at the time of visit included in the word-of-mouth contributor attribute data 272. The word-of-mouth reference person data in FIG. 7(b) is data corresponding to the word-of-mouth reference person attribute data 274 and includes, for example, the user name of the word-of-mouth reference person, the accompanying person of the reference person, and the weather of the reference person.

[0041] The suggestion device 200 calculates, for each reference person, a matching score between the scene or situation (accompanying person / weather) of the reference person and the scene or situation (accompanying person / weather) of the contributor based on the word-of-mouth reference person attribute data 274, the word-of-mouth contributor attribute data 272, and the word-of-mouth text data 276. Thereby, as shown in FIG. 7(c), the suggestion device 200 calculates, for example, an accompanying person similarity score and a weather matching score for user X. For example, in word-of-mouth 001, if the accompanying person at the time of visit of the word-of-mouth contributor is "family" and the weather at the time of visit is "sunny", and the accompanying person at the time of visit of user X is "family" and the weather at the time of visit is "rainy", the accompanying person matching score is "1" and the weather matching score is "0". For example, in word-of-mouth 002, if "son" is described in the word-of-mouth text data 276 and the accompanying person at the time of visit of user X is "family", the accompanying person matching score is "1.5". For example, in word-of-mouth 003, if "rain" is described in the word-of-mouth text data 276 and the weather at the time of visit of user X is "rainy", the weather matching score is "1.5".

[0042] FIG. 8 is a diagram for explaining a process of calculating the similarity of a scene / situation. (a) is a diagram showing an example of a determination word. (b) is a diagram showing a process of determining the similarity from the review text. (c) is a diagram showing a process of determining the similarity from the attributes of the scene or situation of the poster and the attributes of the scene or situation of the viewer. The suggestion device 200 performs the following processes to calculate the matching score (similarity) of the scene / situation based on the review text data 276. First, as a preliminary work, the definition of determination words is performed. In the present embodiment, as shown in FIG. 8(a), a group of words for determining specific attributes in each of the companion and the weather is defined. First, the actual review text data 276 is collected, and topic modeling (a natural language processing method) using LDA is calculated to extract words from the review text data 276.

[0043] The suggestion device 200 performs the following determination process (1) and determination process (2) for each of the companion and the weather. In determination process (1), it is searched whether the words defined in the preliminary work corresponding to the attributes of the scene / situation of the review viewer (for example, family, rain) are included in the review text data 276. As shown in FIG. 8(b), when the words defined in the preliminary work (for example, son) are included in the review text data 276, "1.5" is given as the companion matching score, and the determination process is terminated. When the words defined in the preliminary work are not included in the review text data 276, in determination process (2), the attributes of the scene / situation of the review viewer (for example, family, rain) and the attributes of the scene or situation of the review poster are compared. When they match like "family" or "partner" and "family" as shown in FIG. 8(c), "1.0" is given as the companion matching score, and when they do not match, "0" is given as the companion matching score.

[0044] If the review text contains words related to the attributes of the scene or situation of the reviewer, it is highly likely that the review information contains useful information for the reviewer. However, it is difficult to extract the scene / situation from the review text, and there is a high possibility of omission or mis-extraction of the scene / situation. On the other hand, the attributes of the scene / situation input by the poster himself / herself can be easily obtained, and the reliability of the scene / situation is high. However, the review text of the poster does not necessarily match the scene or situation. Therefore, the suggestion device 200 defines determination words by narrowing down to highly reproducible words so as to reduce misdetection. In determination process (1), since it is highly likely that a review containing a word corresponding to the determination word is beneficial, a high match score can be assigned. Further, even if the determination word is not described in the review text, the suggestion device 200 extracts the review based on the attributes of the scene / situation in determination process (2). In the case of determination process (2), since it is highly likely that the experience corresponding to the scene / situation is not described in the review text, a lower match score is assigned than in determination process (1).

[0045] [Process 1-2] After or in parallel with process 1-1, the suggestion device 200 performs process 1-2 (step S102). Process 1-2 is a similarity calculation process for the scene / situation. The similarity calculation process of the scene / situation in process 1-2 is a process of calculating a match score (similarity) between the scene or situation of the reviewer and the scene or situation of the poster based on the reviewer attribute data 272 and the reviewee attribute data 274 of the review. Process 1-2 calculates the match score for the date and time zone among the scene / situation, but is not limited thereto.

[0046] FIG. 9 is a diagram showing another example of the calculation process of the match score of the scene / situation in the embodiment. When the items of the scene / situation are companions and weather, the suggestion device 200 calculates the match score by the above-described process 1-1. When the items of the scene / situation are date and time, the suggestion device 200 calculates the match score in process 1-2.

[0047] When calculating the matching score of the date as the scene / situation, the suggestion device 200 uses the visitor date of the poster as the date. When the difference between the visitor date of the poster and the date specified by the referrer is N days or less (e.g., N = 20), the suggestion device 200 assigns "1.0" to the matching score of the review of the said poster. When the difference between the visitor date of the poster and the date specified by the referrer is greater than N days and 2N days or less, the suggestion device 200 assigns "0.5" to the matching score of the review of the said poster. Note that the suggestion device 200 does not need to consider the year of the visitor date of the poster in order to suggest reviews with the same season (date). For example, if the date specified by the referrer is July 23, 2024, and the visitor date of the poster is July 23, 2023, "1.0" is assigned to the review.

[0048] When calculating the matching score of the time zone as the scene / situation, the suggestion device 200 compares the visitor time zone of the poster with the time zone specified by the referrer and calculates the matching score for the time zone. The suggestion device 200 assigns "1.0" when the time zones match, and assigns "0" when the time zones do not match. The suggestion device 200 may assign "1.0" when "day" or "night" as the time zone matches. The suggestion device 200 may change the time zone according to the category of the content. For example, the suggestion device 200 may consider before 17:00 as day and after 17:00 as night for sightseeing and shopping, and consider before 11:00 as morning, from 11:00 to before 17:00 as day, and after 17:00 as night for meals.

[0049] [Process 2] The suggestion device 200 performs Process 2 for calculating the richness of the information included in the review (step S104). Process 2 estimates the information richness based on the review text data 276. The information richness increases as the number of elements that the referrer values increases. For example, for each category of content, the information richness is set with a plurality of elements that the referrer values, and the information richness increases as the number of elements mentioned in the review is larger.

[0050] FIG. 10 is a diagram for explaining the calculation process of the information richness in the embodiment. The categories of the content are, for example, meals, accommodation, shopping, and sightseeing. In the meal category, for example, five elements are set: (1) meal content, (2) customer service, (3) price, (4) atmosphere / view, and (5) crowding / reservation. The suggestion device 200 counts the number of elements mentioned in the word-of-mouth among the elements (1) to (5), multiplies the count value by 0.2, and calculates the information richness. When the number of elements mentioned in the word-of-mouth is 0, the information richness is 0.0; when the number of elements mentioned in the word-of-mouth is 1, the information richness is 0.2; and when the number of elements mentioned in the word-of-mouth is 5, the information richness is 1.0.

[0051] The selection of the elements is, for example, based on a survey report in the tourism industry, extracting the elements that are emphasized when considering the spots visited by the word-of-mouth referrers, and based on the extraction results, selecting and aggregating the information elements to select five elements. There may be categories in which a plurality of elements can be selected by the selection of the elements, and categories in which a plurality of elements cannot be selected. For example, in the meal category and the accommodation category, five elements can be selected, so the information richness can be calculated for the word-of-mouth of the meal category and the accommodation category. On the other hand, in the shopping category and the sightseeing category, since the emphasized elements are not clearly determined, it is not necessary to calculate the information richness.

[0052] FIG. 11 is a diagram showing the relationship between the content categories, information elements, and words representing the information elements in the embodiment. The words representing the information elements are the result of calculating topic modeling (a natural language processing method) using LDA on the word-of-mouth text data 276, extracting representative words representing each information element, and adding, deleting, and modifying the extracted words to provide content and word-of-mouth related to the spot.

[0053] The content adequacy estimation unit 250 determines whether words corresponding to the category of the content and elements of the information are included in the review text data 276. The content adequacy estimation unit 250 extracts review information in which one or more words corresponding to the category of the content and elements of the information are included. The content adequacy estimation unit 250 may divide the review text into words and perform morphological analysis, and convert adjectives, verbs, etc. into their original forms. For example, the content adequacy estimation unit 250 converts "oishikatt" to "oishii".

[0054] FIG. 12 is a diagram for explaining an example of the calculation process of the information adequacy for review information in the embodiment. (a) is a diagram showing the review content and the information adequacy of the content in the food category, and (b) is a diagram showing the review content and the information adequacy of the content in the accommodation category. In the review text shown in the upper part of FIG. 12(a), words representing food in the food category, words representing customer service in the food category, words representing price, and words representing atmosphere / scenery are included. Therefore, the content adequacy estimation unit 250 calculates an information adequacy of 0.8. In the review text shown in the lower part of FIG. 12(a), three words representing food in the food category are included, but no words representing other elements are included. Therefore, the content adequacy estimation unit 250 calculates an information adequacy of 0.2. In the review text shown in the upper part of FIG. 12(b), words representing food in the accommodation category, words representing customer service in the accommodation category, words representing rooms, and words representing cleanliness are included. Therefore, the content adequacy estimation unit 250 calculates an information adequacy of 0.8. In the review text shown in the lower part of FIG. 12(a), three words representing food in the accommodation category are included, but no words representing other elements are included. Therefore, the content adequacy estimation unit 250 calculates an information adequacy of 0.2.

[0055] [Process 3] The suggestion device 200 performs process 3 of calculating a suggestion score based on the similar scene / situation calculated in processes 1-1 and 1-2, the information richness calculated in process 2, and the statistical information including the word-of-mouth statistical data 278 (step S106). The suggestion unit 260 calculates a comprehensive suggestion score by adding points to the score based on the statistical information in addition to the matching score of the scene / situation calculated in process 1 and the score of the information richness calculated in process 2.

[0056] FIG. 13 is a diagram for explaining the process of calculating the suggestion score in the embodiment, and is a diagram showing the correspondence between the statistical information and the suggestion screens ((a) is a list screen, (b) is a detailed screen). The suggestion unit 260 calculates (1) a photo score, (2) a title score, (3) a freshness score, (4) a useful score, (5) a recommendation score, (6) a sentence length score, and (7) a positivity score.

[0057] (1) The photo score is likely to be a useful word-of-mouth as the number of photos attached to the word-of-mouth is larger, so it becomes a high value. The suggestion unit 260 calculates, for example, a value obtained by multiplying the number of attached photos by 0.25, and calculates so that it becomes 1.0 when there are 5 or more photos. (2) The title score is 1.0 when there is a title because the word-of-mouth with the title described can confirm information simply, and 0 when there is no title. (3) The freshness score is a value according to the number of days elapsed from the visit date because the word-of-mouth with a short number of days elapsed from the visit date is referenceable. The suggestion unit 260 sets the freshness score to 1.0 when it is within half a year from the visit date, 0.5 when it is from half a year to 1 year, 0.25 when it is from 1 year to 2 years, and 0 when it is 2 years or more, for example. (4) The useful score is higher when the number of useful comments from the referrers is larger because the quality of the comments is high. The suggestion unit 260 adds points, for example, using the value obtained by taking the logarithm (with base 10) of the number of useful comments as the useful score. The number of useful comments has no defined numerical range, and this is to prevent comments with an extremely large number of useful comments from being frequently suggested. For this purpose, logarithmic conversion may be performed as a mechanism to make the score less likely to increase when the number of useful comments reaches a certain level. (5) The recommendation score is added according to the degree of recommendation for the spot in the comment (a mechanism of rating with stars on a 5 - level scale) because comments with a high degree of recommendation from the poster describe the attractiveness of the spot. The suggestion unit 260 calculates the recommendation score by multiplying the degree of recommendation by 0.2, for example. (6) The sentence length score is added according to the sentence length of the comment text because the longer the sentence length of the comment, the more information it contains. The suggestion unit 260 calculates the sentence length score by multiplying the number of characters by 0.0025, for example. However, when the number of characters is 401 or more, the sentence length score becomes 1. This is to prevent comments with extremely long sentence lengths from being frequently suggested when the numerical range of the sentence length is not defined. (7) The positivity score is added according to the positivity of the comment text because comments with a high positivity describe the attractiveness of the spot and are useful for referrers. The positivity is higher when the comment text contains more pre - registered positive words and is calculated, for example, by known natural language processing.

[0058] Figure 14 is a diagram showing an example of the calculation formula for the suggestion score in the embodiment. The suggestion unit 260 calculates the suggestion score of the content by multiplying each of the companion agreement score, time - zone agreement score, season (date) agreement score, weather agreement score, information sufficiency score, photo score, title score, freshness score, useful score, recommendation score, sentence length score, and positivity score based on the similarity of the scene / situation by a weight, and adding the multiplied values.

[0059] FIG. 15 is a diagram showing an example of items for calculating a suggestion score, values for calculating a score, a score, and weights in the embodiment. The suggestion unit 260, for example, sets the weights of process 1-1, process 1-2, and information sufficiency to "2.0", making the weights higher than those of other items. Thereby, the suggestion unit 260 can calculate a suggestion score that emphasizes the scene / situation and information sufficiency. Also, by setting the upper limit values of the companion matching score and time zone matching score in process 1-1 to be higher than those of other similarity scores, such as 1.5, a suggestion score that emphasizes the similarity score calculated in process 1-1 can be calculated.

[0060] [Process 4] The suggestion device 200 performs process 4 after process 3 (step S108). Process 4 is a process of creating a spot list screen or a spot detail screen based on the suggestion score calculated in process 3. The suggestion device 200 transmits information for displaying the created spot list screen or spot detail screen to the reference terminal device 110. The reference terminal device 110 displays a spot list screen or a spot detail screen based on the received information (step S202).

[0061] FIG. 16 is a diagram for explaining a process of creating a ranking of contents on a spot list screen in the embodiment. The suggestion unit 260 creates a ranking of contents to determine the contents and reviews to be displayed on the spot list screen based on the calculated suggestion score. The spot list screen picks up one positive review that conveys the charm of the tourist destination and publishes the picked-up review together with the spot. Therefore, the suggestion unit 260 performs a two-step process of first narrowing down the reviews and then ranking the reviews.

[0062] The suggestion section 260 narrows down the reviews to those that meet all four conditions for freshness, recommendability, sentence length, and positivity. Among the reviews shown in Fig. 16, the reviews shown in the upper and middle sections will be narrowed down. (1) Freshness condition: The visit date of the review contributor is within the past three years. (2) Recommendability condition: The recommendability of the review contributor is 3 stars or more. (3) Sentence length condition: The sentence length of the review text is 100 characters or more. (4) Positivity condition: The positivity of the review text is 0.8 or more.

[0063] The suggestion section 260 creates a ranking based on the suggestion score calculated in process 3 for the narrowed-down reviews. The suggestion section 260 creates display data for displaying a spot list screen that displays the review ranked first at the top. Among the reviews shown in Fig. 16, the review shown in the upper section becomes the first in the ranking and is the review displayed at the top on the spot list screen.

[0064] Fig. 17 is a diagram for explaining the process of creating a ranking of contents on the spot detail screen in the embodiment. The spot detail screen displays the raw opinions of users with similar scenes and situations at the top for the spots that are felt to be attractive on the spot list screen, and provides information useful for the user's decision-making. The suggestion section 260 causes the review displayed on the spot list screen to be displayed at the top (first) of the spot detail screen. The suggestion section 260 creates a ranking for the second place and below on the spot detail screen based on the suggestion score calculated in process 3. The suggestion section 260 does not perform narrowing as in the case of the reviews displayed on the spot list screen. As a result, reviews with old freshness, low recommendability, short sentence length, and low positivity can also be used as a reference for the viewer's decision-making. Therefore, unlike the spot list, a ranking can be created without narrowing.

[0065] FIG. 18 is a diagram showing an example of a spot list screen and a spot detail screen in the embodiment. The suggestion unit 260 first displays the top-ranked review on the spot list screen by performing a review narrowing-down and ranking based on the suggestion score (FIG. 18(a)). When the review displayed on the spot list screen is selected, the suggestion unit 260 sets the ranking of the review displayed on the spot list screen as the first place, creates a ranking for other reviews, and displays the spot detail screen (FIG. 18(b)).

[0066] (Effect of the Embodiment) As described above, according to the suggestion system 1 of the embodiment, a database unit 270 that stores spot information indicating spots, review information regarding the spots, and scene / situation information indicating the scene or situation of the poster of the review information; a scene / situation acquisition unit 220 that acquires scene / situation information indicating the scene or situation of the user in response to receiving a search request for specifying a spot from a reference person (user); a comparison is made between the scene / situation information of the user acquired by the scene / situation acquisition unit 220 and the scene / situation information of the poster of the review information regarding the spot specified by the search request stored in the database unit 270, and based on the comparison result, a review information extraction unit 230 that extracts review information to be suggested to the user from the review information stored in the database unit 270, and a suggestion unit 260 that suggests the review information extracted by the review information extraction unit 230, and a suggestion device 200 can be realized. According to this suggestion system 1, it is possible to display review information that is useful for considering the visited spots for each individual user.

[0067] According to the suggestion system 1, the suggestion unit 260 can transmit the scene / situation information of the poster as the reason for suggesting word-of-mouth information based on the comparison result. When searching for word-of-mouth that meets the requirements according to the current user situation, or when searching from the word-of-mouth information transmitted by other users around the user, there may be cases where the reason for displaying the word-of-mouth is not conveyed to the user, and the acceptability of the displayed word-of-mouth may be low. In contrast, according to the suggestion system 1, since the scene / situation information of the poster is transmitted as the reason for the suggestion, the acceptability of the word-of-mouth can be increased.

[0068] Furthermore, word-of-mouth with high evaluations and short texts or word-of-mouth that repeats the same content are often displayed at the top, which may reduce the user's opportunity to access meaningful information. Furthermore, since word-of-mouth with high rankings in both the spot list content and the spot detail content provided in response to the user's request is displayed at the top, it is not possible to display word-of-mouth suitable for each of the spot list content and the spot detail content, and it is not possible to display word-of-mouth that attracts users in each content.

[0069] According to the suggestion system 1, the scene / situation estimation unit 240 can estimate the scene or situation of the poster based on the content of the poster's word-of-mouth information. Word-of-mouth created by the poster often does not appropriately describe the scene or situation related to the word-of-mouth due to errors or omissions in the word-of-mouth, and the accuracy of the suggestion may decrease even if the suggestion is made using the word-of-mouth. In contrast, according to the suggestion system 1, since the scene or situation is estimated based on the actual content of the word-of-mouth, the accuracy of suggesting word-of-mouth suitable for the scene / situation of the viewer can be increased.

[0070] According to the suggestion system 1, it is possible to estimate the information richness indicating that a plurality of types of elements that the user values are included in the word-of-mouth information of the poster, and the suggestion unit 260 can suggest the word-of-mouth information based on the information richness. According to the suggestion system 1, it is possible to suppress the high-ranking display of highly evaluated short word-of-mouth or word-of-mouth that repeatedly writes the same content, and increase the opportunity for the user to access meaningful information.

[0071] According to the suggestion system 1, the word-of-mouth information extraction unit 230 extracts the word-of-mouth information narrowed down based on the positivity of the word-of-mouth, and ranks the narrowed-down word-of-mouth information based on the scene / situation and information richness. The word-of-mouth information can be included in the list content (spot list screen) including the list of spots, and the word-of-mouth information ranked based on the suggestion score can be included in the detailed content (spot detail screen) including the details of the spot. According to the suggestion system 1, on the spot list screen, the word-of-mouth with a high positivity and a high ranking can be displayed, and on the spot detail screen, the word-of-mouth with a high ranking can be displayed at the top. Thus, according to the suggestion system 1, the user can be attracted by the positive word-of-mouth displayed on the spot list screen, and information that contributes to the user's decision-making can be provided by the word-of-mouth including the raw opinions of the poster displayed on the spot detail screen.

[0072] Although each embodiment and each modification have been described, these are merely examples and are not limited thereto. For example, any one of each embodiment or each modification, or a part of each embodiment or a part of each modification may be combined with one or more other embodiments or one or more other modifications to realize an aspect of the present invention.

[0073] Note that a program for executing each process of the poster terminal device 100, the viewer terminal device 110, the suggestion device 200, the content providing device 300, and the environmental information providing device 400 in the present embodiment may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed to perform the various processes described above related to the poster terminal device 100, the viewer terminal device 110, the suggestion device 200, the content providing device 300, and the environmental information providing device 400.

[0074] Note that the "computer system" referred to here may include hardware such as an OS and peripheral devices. Also, the "computer system" shall include a homepage providing environment (or display environment) if the WWW system is being used. Further, the "computer-readable recording medium" refers to a writable non-volatile memory such as a flexible disk, a magneto-optical disk, a ROM, a flash memory, a portable medium such as a CD-ROM, or a storage device such as a hard disk incorporated in a computer system.

[0075] Furthermore, the "computer-readable recording medium" also includes a volatile memory (for example, DRAM (Dynamic Random Access Memory)) inside a computer system that becomes a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line, and that holds the program for a certain period of time. Also, the above program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium.

[0076] Here, the "transmission medium" for transmitting a program refers to a medium having a function of transmitting information, such as a network (communication network) like the Internet or a communication line (communication wire) like a telephone line. Also, the above program may be for realizing a part of the functions described above. Further, it may be a so-called difference file (difference program) that can be realized in combination with a program already recorded in a computer system for the functions described above.

[0077] As described above, the embodiments of the present invention have been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and designs within the scope not departing from the gist of the present invention are also included.

Explanation of Reference Numerals

[0078] 1 Suggestion System 100 Submitter Terminal Device 110 Viewer Terminal Device 200 Suggestion Device 210 Reception Unit 220 Scene / Situation Acquisition Unit 230 Word-of-Mouth Information Extraction Unit 240 Scene / Situation Estimation Unit 250 Completeness Estimation Unit 260 Suggestion Unit 270 Database Unit 272 Word-of-Mouth Submitter Attribute Data 274 Word-of-Mouth Viewer Attribute Data 276 Word-of-Mouth Text Data 278 Word-of-Mouth Statistical Data 300 Content Providing Device 300A Content Storage Unit 400 Environmental Information Providing Device

Claims

1. A storage unit that stores spot information indicating a spot, word-of-mouth information regarding the spot, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information; An acquisition unit that acquires scene / situation information indicating the scene or situation of the user in response to receiving a search request designating a spot from the user; A comparison unit that compares the scene / situation information of the user acquired by the acquisition unit with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot designated by the search request stored in the storage unit, and extracts word-of-mouth information to be suggested to the user from the word-of-mouth information stored in the storage unit based on the comparison result; A suggestion unit that suggests the word-of-mouth information extracted by the extraction unit; A suggestion system comprising:

2. The suggestion system according to claim 1, wherein the suggestion unit transmits the scene / situation information of the poster as a reason for suggesting the word-of-mouth information based on the comparison result.

3. The suggestion system according to claim 1 or 2, further comprising a scene / situation estimation unit that estimates the scene or situation of the poster based on the content of the word-of-mouth information of the poster.

4. comprising a sufficiency estimation unit that estimates the sufficiency of information indicating that a plurality of types of elements emphasized by the user are included in the word-of-mouth information of the poster, wherein the suggestion unit suggests word-of-mouth information based on the sufficiency estimated by the sufficiency estimation unit; The suggestion system according to claim 1.

5. The extraction unit extracts word-of-mouth information narrowed down based on the positivity of the word-of-mouth; The suggestion unit includes the word-of-mouth information ranked based on the scene / situation and the information sufficiency of the word-of-mouth information filtered based on the positivity of the word-of-mouth in the list content including the list of spots, and includes the word-of-mouth information ranked based on the suggestion score in the detailed content including the details of the spot. The suggestion system according to claim 4.

6. A step in which an information processing device stores spot information indicating a spot, word-of-mouth information regarding the spot, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information; A step in which the information processing device acquires scene / situation information indicating the scene or situation of the user in response to receiving a search request specifying a spot from the user; A step in which the information processing device compares the acquired scene / situation information of the user with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot specified by the stored search request, and extracts, based on the comparison result, the word-of-mouth information to be suggested to the user from the stored word-of-mouth information; A step in which the information processing device suggests the extracted word-of-mouth information; A suggestion method including:

7. In the computer of the information processing device, A step in which the computer stores spot information indicating a spot, word-of-mouth information regarding the spot, and scene / situation information indicating the scene or situation of the poster of the word-of-mouth information; A step in which the computer acquires scene / situation information indicating the scene or situation of the user in response to receiving a search request specifying a spot from the user; A step in which the computer compares the acquired scene / situation information of the user with the scene / situation information of the poster who posted the word-of-mouth information regarding the spot specified by the stored search request, and extracts, based on the comparison result, the word-of-mouth information to be suggested to the user from the stored word-of-mouth information; A step in which the computer suggests the extracted word-of-mouth information; A program including

Images