Information processing system, information processing method, and program

Abstract

We provide a system that enables the combination of consumer awareness data and behavioral data for analysis. [Solution] The information processing system includes a first acquisition means for acquiring responses to a survey on attitudes regarding at least one of daily life and outdoor activities from a plurality of residents, a first identification means for clustering the plurality of residents based on the attitude survey questions and the acquired responses and identifying the cluster to which each resident belongs, a reception means for accepting the designation of one of the identified clusters, a second identification means for identifying destinations visited by residents belonging to the specified cluster, and an output means for outputting information regarding the identified destinations.

Description

[Technical Field]

[0001] The present invention relates to an information processing system, an information processing method, and a program. [Background technology]

[0002] Japanese Patent Application Laid-Open Publication No. 2024-154682 (Patent Document 1) is a document disclosing background art in this technical field. Patent Document 1 states that "a travel-related information notification device capable of maintaining contact between a traveler and a travel destination or a travel business is provided" (see Abstract). More specifically, it states that "the travel-related information notification device of the present invention includes a traveler information acquisition unit, a behavioral information acquisition unit, a tag assignment unit, a proposed information extraction unit, and an output unit, wherein the traveler information acquisition unit acquires traveler information capable of identifying a traveler, the behavioral information acquisition unit acquires behavioral information of the traveler identified based on the traveler information, the tag assignment unit assigns tags to the traveler information based on the behavioral information, the proposed information extraction unit extracts proposed information suitable for the traveler based on the tags, and the output unit outputs the extracted proposed information to the traveler" (see Abstract). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2024-154682 Summary of the Invention [Problem to be solved by the invention]

[0004] The above-mentioned Patent Document 1 describes acquiring traveler behavior information, assigning tags based on the behavior information, extracting suggested information suitable for the traveler based on the tags, and outputting the extracted suggested information to the traveler. In other words, it describes outputting suggested information based on traveler behavior information. However, Patent Document 1 does not take into consideration the traveler's daily life or attitude toward travel.

[0005] The present invention has been made in consideration of the above circumstances, and provides a mechanism that enables combining and analyzing consumer awareness data and behavioral data. [Means for solving the problem]

[0006] In order to solve the above problems, for example, the configurations described in the claims are adopted. The present application includes multiple means for solving the above-mentioned problems, and one example is an information processing system comprising: a first acquisition means for acquiring responses to an attitude survey regarding at least one of daily life and outing behavior from a plurality of residents; a first identification means for clustering the plurality of residents based on the attitude survey questions and the acquired responses and identifying the cluster to which each residents belongs; a reception means for accepting designation of one of the identified clusters; a second identification means for identifying destinations visited by residents belonging to the specified cluster; and an output means for outputting information regarding the identified destinations. [Effects of the Invention]

[0007] According to the present invention, it is possible to combine and analyze consumer awareness data and behavioral data. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 shows an example of the configuration of an information processing system 100. As shown in FIG. [Figure 2] FIG. 2 shows an example of the question and answer DB 200 . [Figure 3] FIG. 3 shows an example of the question DB 300 . [Figure 4] FIG. 4 shows an example of the cluster DB 400. [Figure 5] FIG. 5 shows an example of the action log DB 500. [Figure 6] FIG. 6 shows an example of a POI list 600 . [Figure 7] FIG. 7 shows an example of the visited destination DB 700 . [Figure 8] FIG. 8 shows an example of the POI-related information DB 800. [Figure 9] FIG. 9 illustrates an example of a cluster determination process 900 . [Figure 10] FIG. 10 shows an example of a visit data generation process 1000 . [Figure 11] FIG. 11 shows an example of an output process 1100. [Figure 12] FIG. 12 shows an example of an output process 1200. [Figure 13] FIG. 13 shows an example of an output process 1300. [Figure 14] FIG. 14 shows an example of an output process 1400. [Figure 15] FIG. 15 shows an example of an output process 1500. [Figure 16] FIG. 16 shows an example of an information provision process 1600 . [Figure 17] FIG. 17 shows an example of the results of the factor analysis. [Figure 18] FIG. 18 shows another example of the results of factor analysis. [Figure 19] FIG. 19 shows an example of the clustering result. [Figure 20] FIG. 20 shows an example of an outline of the cluster determination process 900. [Figure 21] FIG. 21 shows an example of a graph showing the cluster ratio by nationality. [Figure 22] FIG. 22 shows an example of a graph showing the gender and age distribution by nationality. [Figure 23] FIG. 23 shows an example of a POI list by nationality. [Figure 24] FIG. 24 shows an example of a graph showing the visiting trends of an individual traveler. [Figure 25] FIG. 25 shows an example of a graph showing visitor trends by nationality. [Figure 26] FIG. 26 shows an example of a process 2600 for generating visit motivation data. [Figure 27]FIG. 27 shows an example of visit motivation data. [Figure 28] FIG. 28 shows an example of a latent topic calculation process 2800. [Figure 29] FIG. 29 shows an example of topic information. [Figure 30] FIG. 30 shows an example of a latent topic. [Figure 31] FIG. 31 shows an example of the latent topic calculation process 3100. [Figure 32] FIG. 32 shows an example of a latent topic calculation process 3200. [Figure 33] FIG. 33 shows an example of a latent topic calculation process 3300. [Figure 34] FIG. 34 shows an example of step 3202. [Figure 35] FIG. 35 shows an example of topic information. [Figure 36] FIG. 36 shows an example of a latent topic. [Figure 37] FIG. 37 shows an example of step 3303. DETAILED DESCRIPTION OF THE INVENTION

[0009] 1. Example Hereinafter, an embodiment of the present invention will be described with reference to the drawings. 1-1.Configuration Fig. 1 is a diagram showing an example of the configuration of an information processing system 100. The information processing system 100 shown in the figure is a system that enables combining and analyzing traveler awareness data and behavioral data. This information processing system 100 is configured, for example, by one or more servers deployed on a cloud.

[0010] This information processing system 100 includes a main storage device 101 such as RAM (Random Access Memory), an auxiliary storage device 102 such as an IC card, hard disk drive, SSD (Solid State Drive), or flash memory, a processor 103 that executes an operating system, applications, programs, etc., an input device 104 such as a touch panel, keyboard, mouse, voice input, or input based on motion detection captured by a camera unit, an output device 105 such as a monitor or display, and a communication control unit 106 such as a network card, wireless communication module, or mobile communication module. Note that the output device 105 may be a device or terminal that transmits information to be output to an external monitor, display, printer, device, etc.

[0011] Of these, the main memory device 101 stores various programs, applications, etc. (modules), and the processor 103 executes these programs and applications to realize the various functional elements of the information processing system 100. Note that each module may be implemented in hardware by integration, etc. Also, each module may be an independent program or application, or may be implemented as a subprogram or function within a single integrated program or application.

[0012] In this specification, each module is described as the entity (subject) that performs the processing, but in reality, the processing is carried out by a processor that processes various programs, applications, etc. (modules).

[0013] Various databases (DBs) are stored in the auxiliary storage device 102. A "database" is a functional element (storage unit) that stores a set of data so that it can accommodate any data manipulation (e.g., extraction, addition, deletion, overwriting, etc.) from a processor or an external computer. The method of implementing the database is not limited, and may be, for example, a database management system, spreadsheet software, or a text file such as XML or JSON.

[0014] Specifically, the main memory device 101 stores programs such as a factor analysis module 110, a score calculation module 111, a clustering module 112, a visit data generation module 113, an output module 114, and an information provision module 115. These programs are executed by the processor 103 to realize each functional element of the information processing system 100. Each module will be described below.

[0015] The factor analysis module 110 acquires responses from multiple travelers to a survey about daily life and travel. The factor analysis module 110 then performs factor analysis based on the survey questions and the acquired responses to extract multiple factors. In this case, the factor analysis module 110 extracts multiple factors using, for example, a principal factor method with varimax rotation. The extracted factors will be described later. Note that the factor analysis module 110 may also extract factors using other well-known factor analysis methods.

[0016] In this embodiment, the travelers are assumed to be foreign tourists visiting Japan (particularly travelers to Kyushu). However, foreign tourists visiting Japan are only an example of travelers, and other travelers (for example, Japanese travelers traveling overseas) may also be targeted by this system.

[0017] The score calculation module 111 calculates, for each of the multiple travelers, scores (factor scores) for the multiple factors extracted by the factor analysis module 110 based on the responses to the attitude survey. In this case, the score calculation module 111 calculates, as one example, the sum of the products of the travelers' responses and the factor loadings as the factor scores. Note that the score calculation module 111 may perform calculations using other well-known factor scoring methods.

[0018] The clustering module 112 clusters the plurality of travelers based on the attitude survey questions and the obtained answers, and identifies the cluster to which each traveler belongs. More specifically, the clustering module 112 clusters the plurality of travelers based on the factor scores calculated by the score calculation module 111, and identifies the cluster to which each traveler belongs. In this case, the clustering module 112 performs clustering using, for example, a Gaussian mixture model. The identified clusters will be described later. Note that the clustering module 112 may perform clustering using other well-known clustering methods.

[0019] In this specification, clustering refers to grouping in a broad sense, and is not limited to clustering based on factor analysis. Clustering methods that do not rely on factor analysis will be described later.

[0020] The visit data generation module 113 acquires the action log data for the above-mentioned multiple travelers, and then generates visit data based on the acquired action log data and a POI list 600, which will be described later.

[0021] The output module 114 receives from the user the specification of a cluster to be output. The output module 114 then identifies the destinations visited by travelers belonging to the specified cluster. The output module 114 then outputs information about the identified destinations to the output device 105.

[0022] The information providing module 115 identifies a cluster to which a first traveler belongs, for the first traveler who is included in the above-mentioned multiple travelers and is the target of information provision.The information providing module 115 then identifies destinations visited by each traveler belonging to the identified cluster.The information providing module 115 then provides information on the identified destinations to the first traveler.

[0023] When the information providing module 115 is to provide information to a second traveler who is not included in the plurality of travelers, the information providing module 115 acquires responses to the above-mentioned attitude survey for the second traveler. The information providing module 115 then calculates scores (factor scores) for the above-mentioned plurality of factors for the second traveler based on the acquired responses. In this case, the information providing module 115 calculates the factor score as the sum of the products of the second traveler's responses and the factor loadings, as an example. Note that the information providing module 115 may perform the calculation using other well-known factor score methods.

[0024] Then, the information providing module 115 identifies the cluster to which the second traveler belongs based on the calculated factor scores. Then, the information providing module 115 identifies the destinations visited by each traveler belonging to the identified cluster, and provides information on the identified destinations to the second traveler.

[0025] Next, the auxiliary storage device 102 of the information processing system 100 will be described. The auxiliary storage device 102 stores information such as a question and answer DB 200, a question DB 300, a cluster DB 400, an action log DB 500, a POI list 600, a visited destination DB 700, and a POI-related information DB 800. Each piece of data will be described below.

[0026] FIG. 2 shows an example of a question and answer DB 200. The question and answer DB 200 shown in the figure is information in a table format that stores travelers' answers to questions. This question and answer DB 200 has columns for user ID, basic questions, and awareness-related questions. Of these, the basic questions consist of questions about basic attributes (including gender, nationality, and age), city of residence, monthly household income, travel style, traveling companions, previous visits to Japan, travel-related information sources, intention to revisit, and planned timing. As a modification, the basic questions may be changed as appropriate depending on the travelers targeted by the system.

[0027] On the other hand, the attitude-related questions consist of questions about attitudes towards daily life and attitudes towards travel. Of these, the former questions consist of multiple question items, as shown in the example below.

[0028] 1 I like trying new things 2 I'm very interested in things that no one has ever done before. 3 I like to go to unfamiliar places by myself. 4. I want to make the right choice when choosing a product or experience. 5. When I see what everyone around me has or is experiencing, I often find myself wanting or wanting the same thing.

[0029] The latter question consists of multiple question items, as exemplified below. 1. I want to go to lesser-known places and experience the charm of my travel destination. 2. When traveling, I enjoy visiting places and shops that interest me, even if they are not famous. 3. I want to visit various tourist spots and shops, not just urban areas. *Urban areas: Commercial facilities and crowded areas such as Hakata, Tenjin, Kumamoto City, Oita City, Nagasaki City, Saga City, Miyazaki City, and Kagoshima City 4. I never get bored of my favorite travel destinations and want to visit them multiple times to get to know every corner of them. 5. I want to go to a famous tourist spot that many people know about.

[0030] The traveler answers the questions above. The answer may be either "yes" or "no," or may be a multi-level answer such as "I strongly agree."

[0031] As a modified example, the question items and answering methods of the awareness-related questions may be changed as appropriate depending on the travelers targeted by this system.

[0032] FIG. 3 shows an example of a question DB 300. The question DB 300 shown in the figure is information in a table format that stores factor loadings for each awareness-related question. This question DB 300 has columns for question ID, question content, and factor loadings. Of these, the factor loading column is composed of the following columns:

[0033] For example, factor 00 is a factor related to awareness of everyday life. ·Factor 00: Hobby / quality emphasis It relates to everyday concerns such as taste and quality. It relates to taste or quality consciousness. +: Value taste and quality -: Indifferent to taste and quality

[0034] Other factors may be included that relate to influence receptivity, challenge orientation, or price preference.

[0035] For example, factor 10 is a factor related to attitudes toward travel. ·Factor 10: Hidden gems · Attention to detail It relates to the degree to which you value your own preferences. +: Strong emphasis on hidden spots and personal preferences -: Easily influenced by others and has a less strict travel style

[0036] Other factors may include awareness of SNS, activity orientation, or the degree to which one values ​​the evaluations of others.

[0037] As a modified example, the number and types of factors used may be changed as appropriate depending on the results of the factor analysis.

[0038] FIG. 4 shows an example of a cluster DB 400. The cluster DB 400 shown in the figure is information in a table format that stores the score for each factor of each traveler and information on the cluster to which the traveler belongs. This cluster DB 400 has columns for user ID, nationality, factor score, and cluster. Of these, the factor score column is made up of at least one or more factor columns. The cluster column stores identification information for one of the clusters shown below as examples.

[0039] Cluster example: Hobby and quality-seeking travelers This cluster has higher scores for factors related to taste or awareness of quality and the degree to which people attach importance to their own preferences compared to the scores for other factors.

[0040] Other clusters may include clusters in which the variation in scores for each factor is smaller than in other clusters, clusters in which the scores for factors related to awareness of SNS and factors related to low price orientation are higher than the scores for other factors, clusters in which the scores for each factor are higher than the average of other clusters, and clusters in which the scores for each factor are lower than the average of other clusters.

[0041] As a modified example, the number and types of clusters used may be changed as appropriate depending on the results of clustering.

[0042] 5 shows an example of the action log DB 500. The action log DB 500 shown in the figure is information in a table format. This action log DB 500 has columns for user ID, timestamp, latitude, and longitude.

[0043] The behavioral logs of each traveler stored in this database are collected, for example, using a travel SIM card inserted into the traveler's smartphone.

[0044] 6 shows an example of a POI list 600. The POI list 600 shown in the figure is information in a table format that stores location information of POIs (points of interest). This POI list 600 has columns for destination ID, major category, intermediate category, name, latitude, longitude, POI information, and POI description.

[0045] 7 shows an example of a visited destination DB 700. The visited destination DB 700 shown in the figure is information in a table format that stores information on POIs visited by each traveler. This visited destination DB 700 has columns for user ID, visited destination ID, POI, and stay time.

[0046] FIG. 8 shows an example of a POI-related information DB 800. The POI-related information DB 800 shown in the figure is information in a table format that stores information related to each POI. This POI-related information DB 800 has columns for destination IDs and related information. Of these, the related information column stores information related to before, during, or after the trip.

[0047] Pre-trip information includes information to increase a traveler's interest in the destination, such as tour guides, sightseeing guides, tourist spot recommendations, dining information, and advance reservation information. The information about the trip includes information about the places the traveler visits during the trip, such as information about events at the visited places, information about products and stores that can be purchased at the visited places, information about transportation, and information about accommodations. Travel information includes information to maintain a traveler's interest in the destination, such as information about products available for purchase via e-commerce sites, news about the destination, and information about new tourist attractions.

[0048] 1-2.Operation Next, various processes executed by the information processing system 100 will be described. 1-2-1. Cluster determination process 900 9 is a flow diagram showing an example of a cluster determination process 900. The process shown in the figure is a process for determining the cluster to which each traveler belongs.

[0049] First, the factor analysis module 110 acquires attitude-related questions from the question DB 300 (step 901). Next, the factor analysis module 110 acquires responses to an attitude survey about daily life and travel for multiple travelers from the question and answer DB 200 (step 902). The factor analysis module 110 then performs factor analysis based on the acquired attitude-related questions and answers to extract multiple factors (step 903). In this case, the factor analysis module 110 extracts multiple factors using, for example, a principal factor method with varimax rotation. The factor analysis module 110 then stores the factor loading of each extracted factor in the question DB 300.

[0050] 17 is a diagram showing an example of the result of factor analysis, which shows the factor loadings of factors 00 to 03 for each question item regarding everyday consciousness. In the example shown in the figure, four factors, factors 00 to 03, have been extracted. The analyst refers to the factor loadings and interprets which question items each factor is associated with. Based on this interpretation, the analyst then assigns a classification name to each factor. In this example, factors 00 to 03 have been assigned the classification names "Hobbies / Quality Emphasis," "Social / Influence Acceptance," "Adventure / Challenge Orientation," and "Low Price Emphasis / Frugality Orientation." The result of the factor analysis shown in FIG.

[0051] 18 is a diagram showing another example of the results of factor analysis, which shows the factor loadings of factors 10 to 13 for each question item regarding travel attitudes. In the example shown in the figure, four factors, factors 10 to 13, have been extracted. The analyst refers to the factor loadings and interprets which question items each factor is associated with. Based on this interpretation, the analyst then assigns a classification name to each factor. In this example, factors 10 to 13 have been assigned the classification names "Hidden Spots - Emphasis on Particularity," "Emphasis on Social Media," "Emphasis on Activities," and "Major Spots - Emphasis on Word of Mouth." The result of the factor analysis shown in FIG.

[0052] Next, the score calculation module 111 calculates scores (factor scores) for the multiple factors extracted in step 903 for each of the multiple travelers based on the answers acquired in step 902 (step 904). In this case, the score calculation module 111 calculates, as an example, the sum of the products of the travelers' answers and the factor loadings as the factor scores. The score calculation module 111 then stores the calculated factor scores in the cluster DB 400.

[0053] Next, the clustering module 112 clusters the multiple travelers based on the factor scores calculated in step 904, and identifies the cluster to which each traveler belongs (step 905). At this time, the clustering module 112 performs clustering using, for example, a Gaussian mixture model. The clustering module 112 then stores information on the cluster identified for each traveler in the cluster DB 400.

[0054] 19 is a diagram showing an example of the clustering results, which shows the factor scores of five clusters for each of eight factors. In the example shown in the figure, the data is classified into five clusters, clusters 0 to 4. The analyst refers to the factor scores and interprets which factors each cluster is associated with. Then, based on that interpretation, the analyst may assign a classification name to each cluster. The clustering result shown in FIG. 19 may be output to the output device 105.

[0055] This concludes the explanation of the cluster determination process 900.

[0056] 20 is a diagram showing an example of the outline of the above-described cluster determination process 900. As shown in the figure, in the above-described cluster determination process 900, factor analysis is performed on question items regarding daily life attitudes, and factors 00 to 03 are extracted. Also, factor analysis is performed on question items regarding travel-related attitudes, and factors 10 to 13 are extracted. Then, multiple travelers are classified into one of clusters 0 to 4 based on the scores of the extracted factors.

[0057] In the above cluster determination process 900, questions about attitudes toward daily life and travel and their answers are used (see steps 901 and 902). Alternatively, only one of the questions and its answer may be used. Even in this case, analysis that combines traveler attitude data and behavioral data is possible.

[0058] 1-2-2. Visit data generation process 1000 10 is a flow diagram showing an example of the visit data generation process 1000. The process shown in the drawing is a process for generating visit data of a traveler.

[0059] First, the visit data generation module 113 acquires the behavior log data of the traveler to be processed from the behavior log DB 500 (step 1001). Next, the visit data generation module 113 references the acquired behavior log data and detects locations where the traveler stopped within a predetermined range for a predetermined time as stay points (step 1002). Next, the visit data generation module 113 clusters points that are close to each other (in other words, points whose distance is equal to or less than a predetermined value) among the detected stay points (step 1003). In this case, the module uses, for example, DBSCAN (Density-based spatial clustering of applications with noise).

[0060] Next, the visit data generation module 113 refers to the POI list 600 based on the location information (latitude and longitude) of the center point of the cluster, and estimates and assigns a POI (step 1004). At this time, the module stores the unnecessary POI in association with the stay time in the visited destination DB 700. The above is the explanation of the visit data generation process 1000.

[0061] Visit data is generated for each traveler by the above-described visit data generation process 1000. A cluster is identified for each traveler by the above-described cluster determination process 900. This makes it possible to perform analysis by combining the cluster and the visit data.

[0062] 1-2-3. Output processing 1100 11 is a flow diagram showing an example of the output process 1100. The process shown in the figure is a process for outputting the cluster ratio by nationality.

[0063] First, the output module 114 receives from the user the specification of a cluster to be output (step 1101). Next, the output module 114 refers to the cluster DB 400 and counts the number of travelers belonging to the specified cluster for each nationality (step 1102). The output module 114 also refers to the cluster DB 400 and counts the number of all travelers for each nationality (step 1103). Then, the output module 114 divides the number counted in step 1102 by the number counted in step 1103 for each nationality to calculate the cluster ratio (step 1104). Finally, the output module 114 outputs a graph showing the cluster ratios by nationality calculated in step 1104 to the output device 105 (step 1105).

[0064] 21 is a diagram showing an example of a graph showing cluster ratios by nationality. The graph shown in the figure shows the ratio of Cluster 2 for travelers from China, South Korea, and Taiwan.

[0065] 1-2-4. Output processing 1200 12 is a flow diagram showing an example of the output process 1200. The process shown in the figure is a process for outputting the gender and age composition by nationality.

[0066] First, the output module 114 receives from the user the specification of a cluster to be output (step 1201). Next, the output module 114 refers to the cluster DB 400 and extracts travelers belonging to the specified cluster by nationality (step 1202). Next, the output module 114 refers to the question and answer DB 200 and counts the travelers extracted by nationality by age and gender (step 1203). Finally, the output module 114 outputs to the output device 105 a graph showing the gender and age composition by nationality based on the number of travelers counted (step 1204).

[0067] 22 is a diagram showing an example of a graph showing the gender and age composition by nationality. The graph shown in the figure shows the gender and age composition of travelers belonging to Cluster 2 from Taiwan, South Korea, and China.

[0068] 1-2-5. Output processing 1300 13 is a flow diagram showing an example of the output process 1300. The process shown in the drawing is a process for outputting a POI list by nationality.

[0069] First, the output module 114 receives from the user the specification of a cluster to be output (step 1301). Next, the output module 114 references the cluster DB 400 and extracts travelers in the specified cluster by nationality (step 1302). Next, the output module 114 references the destination DB 700 and extracts POIs for each extracted traveler (step 1303). Next, the output module 114 generates a ranking of POIs by nationality based on the extracted POIs (step 1304). Then, the output module 114 extracts the top N (e.g., 5th place) of each ranking (step 1305) and outputs a list showing POIs by nationality to the output device 105 (step 1306).

[0070] 23 is a diagram showing an example of a POI list by nationality. The list shown in the figure shows popular POIs for travelers belonging to Cluster 2, which consists of China, South Korea, and Taiwan.

[0071] 1-2-6. Output processing 1400 14 is a flow diagram showing an example of the output process 1400. The process shown in the figure is a process for outputting the visiting tendency of an individual traveler.

[0072] First, the output module 114 receives from the user the designation of the traveler to be output (step 1401). Next, the output module 114 references the destination DB 700 and extracts the POIs of the designated traveler (step 1402). Next, the output module 114 applies a topic model to the extracted POIs to classify them (step 1403). In this process, as an example, the following classification names are assigned: "Area around Hakata Station," "Kitakyushu Area," "Kumamoto, Kagoshima, and Nagasaki Area," "Tenjin Area," and "Yufuin Area."

[0073] Finally, the output module 114 counts the POIs for each area (step 1404), and outputs a graph showing the visiting trends to the output device 105 (step 1405).

[0074] Fig. 24 shows an example of a graph showing the visit trends of individual travelers. Each graph in the figure shows the number of visits to each area for each traveler.

[0075] 1-2-7. Output processing 1500 15 is a flow diagram showing an example of the output process 1500. The process shown in the figure is a process for outputting visiting trends by nationality.

[0076] First, the output module 114 references the cluster DB 400 and extracts travelers by nationality (step 1501). Next, the output module 114 references the destination DB 700 and extracts POIs for the extracted travelers (step 1502). Next, the output module 114 applies a topic model to the extracted POIs to classify them (step 1503). In this process, as an example, the following classification names are assigned: "Hakata Station Area," "Kitakyushu Area," "Kumamoto, Kagoshima, and Nagasaki Area," "Tenjin Area," and "Yufuin Area."

[0077] Finally, the output module 114 counts the POIs in area units for each nationality (step 1504), and outputs a graph showing the visiting trends by nationality to the output device 105 based on the count values ​​(step 1505).

[0078] Figure 25 shows an example of a graph showing visit trends by nationality. The graph shows the visit rate by area for Chinese, Taiwanese, and Korean tourists.

[0079] 1-2-8. Information provision processing 1600 16 is a flow diagram showing an example of information provision processing 1600. The processing shown in the figure is processing for providing information about destinations to a traveler.

[0080] First, the information providing module 115 receives from the user the designation of a traveler to whom information is to be provided (step 1601). Next, the information providing module 115 refers to the cluster DB 400 to identify the cluster of the designated traveler (step 1602). At this time, if the cluster is registered in the cluster DB 400 (YES in step 1603), the information providing module 115 identifies POIs characteristic of that cluster. Specifically, the information providing module 115 refers to the cluster DB 400 to extract travelers belonging to that cluster (step 1604). Next, the information providing module 115 refers to the destination DB 700 to extract POIs for each extracted traveler (step 1605). Next, a ranking of the extracted POIs is generated (step 1606). Then, the top N (e.g., 5th place) of the generated rankings are extracted (step 1607).

[0081] Next, the information providing module 115 refers to the POI-related information DB 800 and extracts related information for each of the extracted POIs up to the Nth place (step 1608). Finally, the information providing module 115 provides the extracted information to the traveler to whom it is to be provided (step 1609).

[0082] In step 1603 above, if the cluster is not registered in the cluster DB 400 (NO in step 1603), the information providing module 115 acquires the answers to the attitude survey on daily life and travel for the traveler to whom information is to be provided from the question and answer DB 200 (step 1610). Then, the information providing module 115 calculates the factor scores by referring to the factor loadings stored in the question DB 300 (step 1611). In this case, as an example, the information providing module 115 calculates the sum of the products of the traveler's answers and the factor loadings as the factor scores. Then, the information providing module 115 stores the calculated factor scores in the cluster DB 400.

[0083] Next, the information providing module 115 identifies the cluster to which the traveler belongs based on the calculated factor score and the cluster DB 400 (step 1612). At this time, the module stores the identified cluster in the cluster DB 400. The information providing module 115 then proceeds to step 1604 described above. This concludes the explanation of the information provision processing 1600.

[0084] According to the information provision process 1600 explained above, it is possible to provide information by taking into account not only the behavioral data of the traveler to whom the information is to be provided, but also the behavioral data of other travelers who belong to the same cluster as the traveler. Specifically, it is possible to provide information on similar POIs based on the traveler's awareness and motivation for visiting, or to provide information on nearby POIs that may be of interest based on the traveler's location information.

[0085] 2. Variations The above embodiment may be modified as follows: The following modifications may be combined with each other. (1) Visit data In the above embodiment, visit data is generated based on the traveler's behavior log data (see FIG. 10). However, this method is merely an example. As an alternative, a survey may be conducted on the traveler to collect information on the destinations visited and the duration of their stay.

[0086] (2) Clustering As for clustering methods, in addition to those based on factor analysis, methods such as K-means, hierarchical clustering, mean shift, and spectral clustering can also be used.

[0087] (3) Other information In addition to attitude data and behavioral data, it is also possible to collect visit motivations and impressions from word-of-mouth on social media and other platforms, and then combine these with attitude data and behavioral data for analysis. Below, we will explain, as an example, how to generate visit motivation data from social media posting data.

[0088] The information processing system 100 includes a motivation data generation module 116 (not shown) for generating visit motivation data. The motivation data generation module 116 executes a visit motivation data generation process 2600.

[0089] FIG. 26 is a flow diagram showing an example of the visit motivation data generation process 2600. In the flow shown in the figure, first, the motivation data generation module 116 extracts posted data related to the motivation for visiting a POI from various SNSs (step 2601). Next, the motivation data generation module 116 inputs the extracted posting data and the POI list 600 into an LLM (in other words, a large-scale language model) and extracts one or more visiting motivations for each POI (step 2602).

[0090] Next, the motivation data generation module 116 clusters the extracted visit motivations and identifies the cluster to which each visit motivation belongs (step 2603). A known technique may be used as the clustering method. Finally, the motivation data generation module 116 generates, for each POI, visit motivation data indicating the cluster to which the visit motivation belongs, based on the identified clusters (step 2604).

[0091] FIG. 27 shows an example of generated visit motivation data. The visit motivation data 2700 shown in the figure is data in table format, and has columns for POI and motivation. Of these, the motivation column is made up of multiple clusters such as "I want to take pictures at photogenic spots," "Enjoy local ingredients," and "Enjoy popular gourmet food." The column for each cluster stores either "1," indicating that the POI belongs to that cluster, or "0," indicating that the POI does not belong to that cluster.

[0092] The generated visit motivation data is used for analysis by combining it with the attitude data and behavior data. As an example, the visit motivation data may be used when providing information to travelers. Specifically, the visit motivation of the target traveler may be identified through an attitude survey or the like, and information about the POI associated with that visit motivation in the visit motivation data may be provided to the traveler.

[0093] (4) System components The information processing system 100 may be, for example, a portable terminal (mobile terminal) such as a smartphone, tablet, mobile phone, or personal digital assistant (PDA), or may be a wearable terminal such as glasses, a wristwatch, or clothing. The device may also be a stationary or portable computer, or a server located on the cloud or a network. The device may also function as a VR (Virtual Reality) terminal, an AR (Augmented Reality) terminal, or an MR (Mixed Reality) terminal. Alternatively, the device may be a combination of multiple of these terminals. For example, a combination of one smartphone and one wearable terminal may logically function as a single terminal. Other information processing terminals may also be used.

[0094] (5) Behavior-based clustering In the above example, travelers are clustered based on their attitude data. In addition to this, travelers may be clustered based on their behavior data. This allows for analysis using behavior-based clusters in addition to attitude-based clusters.

[0095] As specific examples, the following three methods can be considered. Cluster travelers by applying a topic model to the POIs they visited. · Apply a topic model to the POIs visited by travelers and their POI information to cluster travelers. A topic model is applied to the descriptions of POIs to calculate latent topics for the POIs, and travelers are clustered based on the calculated latent topics and the POIs they visited. Each method will be explained below.

[0096] The topic model is a method for finding "topics" (groups of related words) from a sentence. This topic model identifies the topic, the words that make up the topic, and the topic to which the sentence belongs. This topic model can be applied to other fields by changing the concepts of words and sentences. In this case, by replacing words with POIs and sentences with a list of POIs visited by travelers, the topic of visited POIs (in other words, the purpose of visiting) can be discovered. Alternatively, by replacing words with words in POI descriptions and sentences with POI descriptions, the topic of POI descriptions (in other words, elements that may be motivations for visiting) can be discovered.

[0097] (a) Case of applying topic model to POI First, a case will be described in which a topic model is applied to POIs visited by travelers to cluster them. In this case, the information processing system 100 includes a topic calculation module 117 and a clustering module 118 (both not shown).

[0098] The topic calculation module 117 identifies potential topics for multiple travelers. Specifically, the topic calculation module 117 first acquires information about destinations visited by multiple travelers. Specifically, the acquired information about destinations is POI. Next, the topic calculation module 117 uses a topic model to identify, for each of the multiple travelers, a latent topic indicating the proportion of the information on the destinations visited by the traveler that belongs to each of the multiple topics. In this case, the module first applies the topic model to the information on the destinations acquired for the multiple travelers, and outputs topic information indicating the multiple topics and the information on the destinations related to each topic. Then, based on the output topic information, the module identifies, for each of the multiple travelers, a latent topic indicating the proportion of the information on the destinations visited by the traveler that belongs to each of the multiple topics.

[0099] The clustering module 118 clusters the plurality of travelers and identifies the cluster to which each traveler belongs based on the information on the destinations acquired by the topic calculation module 117. In this case, the clustering module 118 clusters the plurality of travelers based on the latent topics identified by the topic calculation module 117.

[0100] Here, a description will be given of the latent topic calculation process 2800 executed by the topic calculation module 117. Figure 28 is a flow diagram showing an example of the latent topic calculation process 2800. First, the topic calculation module 117 extracts POIs for each traveler by referring to the destination DB 700 (step 2801). Next, the module applies a topic model to the extracted POIs and outputs topic information indicating multiple topics and POIs related to each topic (step 2802).

[0101] An example of the topic information to be output is shown in Fig. 29. In the topic information 2900 shown in the figure, "topic 1 (shopping)," "topic 2 (history)," and "topic 3 (nature)" are each associated with a related POI (such as "aaa"). The output topic information is stored in the auxiliary storage device 102 .

[0102] Next, the topic calculation module 117 calculates, for each traveler, latent topics indicating the proportion of the traveler's visited POIs that belong to each of a plurality of topics based on the output topic information (step 2803).

[0103] Figure 30 shows an example of a calculated latent topic. The latent topic 3000 shown in the figure relates to traveler "A" and shows the percentage of the traveler's visited POIs to which "Topic 1 (Shopping)," "Topic 2 (History)," and "Topic 3 (Nature)" belong. For example, it shows that 20% of the traveler's visited POIs belong to "Topic 1 (Shopping)."

[0104] Finally, the topic calculation module 117 records the calculated latent topics in the auxiliary storage device 102 (step 2804). This concludes the description of the latent topic calculation process 2800.

[0105] (b) Applying topic models to POIs and POI information Next, a case will be described in which a topic model is applied to the POIs visited by travelers and the POI information to cluster travelers. In this case, the information processing system 100 includes a topic calculation module 119 and a clustering module 120 (both not shown).

[0106] The topic calculation module 119 identifies potential topics for multiple travelers. Specifically, the topic calculation module 119 first acquires information about destinations for multiple travelers. The acquired information about destinations is specifically POIs and POI information. Here, POI information is information related to a POI and indicates the characteristics of the POI. Next, the topic calculation module 119 uses a topic model to identify, for each of the multiple travelers, a latent topic indicating the proportion of the information on the destinations visited by the traveler that belongs to each of the multiple topics. In this case, the module first applies the topic model to the information on the destinations acquired for the multiple travelers and outputs topic information indicating the multiple topics and the information on the destinations related to each topic. Then, based on the output topic information, the module identifies, for each of the multiple travelers, a latent topic indicating the proportion of the information on the destinations visited by the traveler that belongs to each of the multiple topics.

[0107] The clustering module 120 clusters the above-mentioned multiple travelers and identifies the cluster to which each traveler belongs based on the information on the destinations acquired by the topic calculation module 119. In this case, the clustering module 120 clusters the above-mentioned multiple travelers based on the latent topics identified by the topic calculation module 119.

[0108] Next, a description will be given of the latent topic calculation process 3100 executed by the topic calculation module 119. Figure 31 is a flow diagram showing an example of the latent topic calculation process 3100. First, the topic calculation module 119 references the destination DB 700 to extract POIs for each traveler (step 3101). Next, the module extracts and assigns corresponding POI information for each extracted POI from the POI list 600 (step 3102). Next, the module applies a topic model to the POIs to which POI information has been assigned, and outputs topic information indicating multiple topics and POIs or POI information related to each topic (step 3103). The output topic information is stored in the auxiliary storage device 102.

[0109] Here, the topic calculation module 119 calculates, for each traveler, latent topics that indicate the POIs visited by the traveler and the proportion of the POI information that belongs to each of multiple topics based on the output topic information (step 3104). The calculated latent topics are, for example, as shown in FIG.

[0110] Finally, the topic calculation module 119 records the calculated latent topics in the auxiliary storage device 102 (step 3105). This concludes the description of the latent topic calculation process 3100.

[0111] (c) Applying topic models to POI descriptions Next, a case will be described in which a topic model is applied to the descriptions of POIs to calculate latent topics for the POIs, and travelers are clustered based on the calculated latent topics and the POIs visited by the travelers. In this case, the information processing system 100 includes a POI topic calculation module 121, a user topic calculation module 122, and a clustering module 123 (all not shown).

[0112] The POI topic calculation module 121 identifies a potential topic for each of a plurality of destinations. Specifically, the POI topic calculation module 121 first obtains descriptions of multiple destinations. Next, the POI topic calculation module 121 applies a topic model to the multiple words that make up the acquired description, and outputs topic information that indicates multiple topics and words related to each topic. Next, based on the output topic information, the POI topic calculation module 121 identifies, for each of the multiple destinations, a latent topic that indicates the proportion of words constituting the description of the destination that belong to each of the multiple topics.

[0113] The user topic calculation module 122 identifies potential topics for multiple travelers. Specifically, the user topic calculation module 122 first acquires information about destinations visited by multiple travelers. Specifically, the acquired information about destinations is POI. Next, the user topic calculation module 122 uses a topic model to identify, for each of the multiple travelers, a latent topic indicating the proportion of information on the destinations visited by the traveler that belongs to each of the multiple topics. At this time, the module aggregates, for each of the multiple travelers, latent topics corresponding to the destinations visited by the traveler, to identify a latent topic indicating the proportion of the destinations visited by the traveler that belong to each of the multiple topics.

[0114] The clustering module 123 clusters the above-mentioned multiple travelers and identifies the cluster to which each traveler belongs based on the information on the destinations acquired by the user topic calculation module 122. In this case, the clustering module 123 clusters the above-mentioned multiple travelers based on the latent topics identified by the user topic calculation module 122.

[0115] Here, a description will be given of the latent topic calculation process 3200 executed by the POI topic calculation module 121. FIG. First, the POI topic calculation module 121 acquires a description of each POI from the POI list 600 (step 3201). Then, the module performs morphological analysis on each acquired description to extract only nouns, verbs, and adjectives (step 3202). Figure 34 shows an example of step 3202.

[0116] Next, the module applies a topic model to the extracted nouns, etc., and outputs topic information indicating multiple topics and words related to each topic (step 3203).

[0117] An example of the topic information to be output is shown in Fig. 35. In the topic information 3500 shown in the figure, related words (such as "surroundings" and "spectacular views") are associated with each of the topics such as "nature and hiking (topic_00)," "tradition and silence (topic_01)," and "sightseeing and shopping (topic_02)." The output topic information is stored in the auxiliary storage device 102 .

[0118] Next, the POI topic calculation module 121 calculates, for each POI, latent topics indicating the proportion of words constituting the description of the POI that belong to each of a plurality of topics, based on the output topic information (step 3204).

[0119] Figure 36 shows an example of a calculated latent topic. The latent topic 3600 shown in the figure is related to the POI "M Department Store Main Branch," and shows the percentage of words in the description of the POI that belong to each of "nature and hiking (topic_00)," "tradition and tranquility (topic_01)," "sightseeing and shopping (topic_02)," etc. For example, it shows that 2% of the words in the description of the POI belong to "nature and hiking (topic_00)."

[0120] Finally, the POI topic calculation module 121 records the calculated latent topic in the auxiliary storage device 102 (step 3205). This concludes the description of the latent topic calculation process 3200.

[0121] Next, a description will be given of the latent topic calculation process 3300 executed by the user topic calculation module 122. Fig. 33 is a flow diagram showing an example of the latent topic calculation process 3300. The flow shown in the figure is performed for each traveler. First, the user topic calculation module 122 references the destination DB 700 to extract the POIs of the target traveler (step 3301). The module then references the latent topics calculated in step 3204 above to identify latent topics corresponding to each extracted POI (step 3302). The module then calculates latent topics by aggregating the values ​​constituting the identified latent topics for each topic and normalizing the aggregated values ​​(step 3303). An example of step 3303 is shown in FIG. 37. The module then records the calculated latent topics in the auxiliary storage device 102 (step 3304). This concludes the description of the latent topic calculation process 3300.

[0122] (d) How to use latent topics Based on the latent topics of the travelers calculated in the above cases (a) to (c), the travelers can be clustered. The clustering is performed by the clustering module 118, 120 or 123.

[0123] Clustering can be performed by setting each topic of the latent topics as a classification axis and determining the cluster to which the traveler belongs with the highest value, or by creating a new classification axis from the factor score values ​​with each topic as a factor and identifying the cluster to which the traveler belongs. Clustering can also be used in combination with awareness data. Examples of how it can be used include the following. Identify travelers who belong to the cluster and understand the relationship between their attitudes and behaviors from their attitude data. Latent topics may also be used in combination with consciousness data. For example, they may be used in the following ways: -Understand the relationship between awareness and behavior based on the number of people in each cluster with the highest potential topic. Calculate the average factor score for each of the highest latent topics to understand the relationship between awareness and behavior. -Look at the correlation between users' latent topics and factor scores to understand behavioral motivations that are highly correlated with their awareness.

[0124] In the above examples and cases, the cluster to which the traveler belongs is identified from the traveler's responses to the attitude survey or latent topics, but this may also be extended to users not subject to the attitude survey, and factor scores or clusters may be estimated and assigned to users not subject to the attitude survey.

[0125] For example, a spot that is frequently visited by a specific cluster may be identified in the survey subject data, and that cluster may be assigned to visiting users who are not subject to the survey. Specifically, if 90% of people in cluster aa among the survey subjects have visited Mount Aso, the cluster aa may be assigned to users who are not subject to the survey but have visited Mount Aso.

[0126] Furthermore, the factor scores or clusters of survey subjects who have latent topics similar to the latent topic of a user not subject to the survey may be assigned to the non-survey user, or if there are multiple survey subjects who have similar latent topics, the average factor scores or most frequent cluster of the group may be assigned to the non-survey user. This can be achieved, for example, by using the K nearest neighbors method.

[0127] Furthermore, it is possible to create a model that uses data from survey subjects to estimate factor scores or clusters using latent topics as features, and input latent topics from users not subject to the survey to estimate and assign factor scores or clusters to those users. This can be achieved using linear regression or machine learning.

[0128] In these cases, the information processing system 100 includes a destination identification module, a cluster estimation module, and a factor score estimation module (all not shown). Of these, the destination identification module identifies destinations for travelers who are different from the multiple travelers who are the subjects of the attitude survey (travelers who are not the subjects of the attitude survey). The cluster estimation module estimates clusters to which travelers not subject to the attitude survey belong, based on the identified destinations and the clusters identified for each of the plurality of travelers. The factor score estimation module estimates scores for multiple factors of travelers who are not the target of the attitude survey, based on the identified destinations and the scores calculated for each of the multiple travelers.

[0129] The information processing system 100 may include a calculation module (not shown) for calculating latent topics of travelers who are not the target of the attitude survey. This calculation module can calculate latent topics in the same way as in (a) to (c) above. That is, in the above case (a), first, the POIs of travelers who are not the target of the attitude survey are identified. Next, based on the topic information output in step 2802 above, the module calculates latent topics that indicate the proportion of visited POIs of travelers who are not the target of the attitude survey that belong to each of multiple topics.

[0130] In the above case (b), the calculation module first identifies POIs of travelers who are not the target of the attitude survey. Next, the module extracts and assigns corresponding POI information for each of the identified POIs from the POI list 600. Next, based on the topic information output in step 3103 above, the module calculates latent topics for travelers who are not the target of the attitude survey, indicating the visited POIs of the travelers and the proportion of their POI information that belongs to each of multiple topics.

[0131] In the above case (c), the calculation module first identifies POIs of travelers who are not the target of the attitude survey. Next, the module refers to the latent topics calculated in step 3204 above to identify latent topics corresponding to each extracted POI. The module then calculates the latent topics by aggregating the values ​​that make up the identified latent topics for each topic and normalizing the aggregated values.

[0132] In each of the above cases, the information processing system 100 may include an output module 124 and an information providing module 125 (both not shown). The output module 124 receives from the user the specification of a cluster to be output. The output module 124 then specifies the survey responses of travelers belonging to the specified cluster, or information specified based on the responses (e.g., factor scores, awareness-based clusters). The output module 124 then outputs the specified responses or information to the output device 105.

[0133] The information providing module 125 identifies a cluster to which a first traveler belongs, for the first traveler who is included in the above-mentioned multiple travelers and is the target of information provision.The information providing module 125 then identifies destinations visited by each traveler belonging to the identified cluster.The information providing module 125 then provides information about the identified destinations to the first traveler.

[0134] (6) Awareness and behavior-based clustering In the above embodiment or modification, travelers are clustered based on either the awareness data or the behavioral data. Alternatively, travelers may be clustered based on both the awareness data and the behavioral data. This enables analysis using clusters based on both awareness and behavior.

[0135] As a specific example, the following method can be considered. (i) Factor analysis is performed on the awareness data to calculate factor scores for each traveler. For example, steps 901 to 904 of the cluster determination process 900 described above are executed to calculate factor scores for each traveler. (ii) A topic model is applied to the behavioral data to calculate the topic belonging probability of each traveler. For example, one of the above-described latent topic calculation processes 3100 to 3300 is executed to calculate the latent topic of each traveler. (iii) Clustering is performed using the data from (i) and (ii). For example, each traveler is clustered based on the factor scores and latent topics of each traveler, and the cluster to which each traveler belongs is identified. In this case, a well-known clustering method may be used.

[0136] (7) Analysis subject In the above-described embodiment and modified examples, it is assumed that traveler attitude data and behavioral data are combined for analysis. However, the subject of analysis of the present invention is not limited to travelers (in other words, people who leave their living area and move to another location). The subject of analysis of the present invention may also include people who move within their living area. Here, people who move within their living area refer to, for example, people who perform daily errands (shopping, commuting to work, school, hospital visits, etc.) within their living area. Such people also share with travelers the fact that they also go out.

[0137] The concept of the present invention will be summarized below. First, in this invention, "outdoor behavior" refers to activities performed outside of one's everyday living space, and includes travel and movement within one's living area. Movement within one's living area includes movement for purposes such as commuting to work, going to the hospital, shopping, administrative procedures, volunteering, visiting someone, childcare, elderly care, eating out, leisure, exercise, and walking. Next, the term "residents" in the present invention includes residents who go out (in other words, visitors, visitors, etc.). Furthermore, the term "residents who go out" includes travelers (in other words, residents who leave their living area and travel to another place).

[0138] (8) Other The present invention is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

[0139] Furthermore, the above-described configurations, functions, processing units, processing means, etc. may be partially or entirely implemented in hardware, for example, by designing them as integrated circuits. The above-described configurations, functions, etc. may also be implemented in software, with a processor interpreting and executing a program that implements each function. Information such as the programs, tables, and files that implement each function can be stored in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD.

[0140] In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be assumed that almost all components are interconnected. The above-described embodiments disclose at least the configurations described in the claims. [Explanation of symbols]

[0141] 100...information processing system, 110...factor analysis module, 111...score calculation module, 112...clustering module, 113...visit data generation module, 114...output module, 115...information provision module, 200...question answer DB, 300...question DB, 400...cluster DB, 500...behavior log DB, 600...POI list, 700...visited destination DB, 800...POI related information DB

Claims

1. a first acquisition means for acquiring responses to an attitude survey regarding at least one of daily life and travel from a plurality of travelers; a first identification means for clustering the plurality of travelers based on the attitude survey questions and the acquired answers, and identifying the cluster to which each of the travelers belongs; a receiving means for receiving a designation of one of the identified clusters; a second identification means for identifying places where the traveler actually stayed as visiting destinations based on a behavior log including location information of the traveler belonging to the specified cluster; an output means for outputting information indicating the identified destination; An information processing system comprising:

2. extraction means for performing factor analysis based on the questions in the attitude survey and the obtained answers to extract a plurality of factors; a first calculation means for calculating a score for each of the plurality of travelers with respect to the plurality of extracted factors based on the acquired answers; Furthermore, The information processing system according to claim 1 , wherein the first specifying means clusters the plurality of travelers based on the calculated scores and specifies the cluster to which each of the travelers belongs.

3. The information processing system according to claim 2 , wherein the plurality of factors include factors related to taste or quality consciousness, receptivity to influence, willingness to take on a challenge, or willingness to pay low prices.

4. The information processing system according to claim 2 , wherein the plurality of factors include factors related to a degree of importance attached to one's own preferences, awareness of social media, activity orientation, or a degree of importance attached to the evaluations of others.

5. Each traveler belongs to a cluster, Clusters with less variance in scores for each factor compared to other clusters, A cluster in which the scores for factors related to awareness of SNS and factors related to low price orientation are higher than the scores for other factors. Clusters in which the scores for factors related to taste or quality consciousness and the degree to which people attach importance to their own preferences are higher than the scores for other factors. Clusters with higher scores for each factor compared to the average scores of other clusters, Clusters with low scores for each factor compared to the average scores of other clusters The information processing system according to claim 2 , further comprising at least one of:

6. a fifth identification means for identifying a cluster to which a first traveler included in the plurality of travelers belongs; a sixth identification means for identifying destinations visited by each traveler belonging to the identified cluster; a first providing means for providing information about the identified destination to the first traveler; The information processing system of claim 1 , further comprising:

7. A second acquisition means for acquiring a response to the attitude survey from a second traveler different from the plurality of travelers; a second calculation means for calculating a score for the second traveler with respect to the plurality of factors based on the acquired answers; an eighth identification means for identifying a cluster to which the second traveler belongs based on the calculated score; a ninth identification means for identifying destinations visited by each traveler belonging to the identified cluster; a second providing means for providing information about the identified destination to the second traveler; The information processing system according to claim 2 , further comprising:

8. a tenth identification means for identifying a destination for a second traveler different from the plurality of travelers; a first estimation means for estimating a cluster to which the second traveler belongs based on the identified destinations and the clusters identified for each of the plurality of travelers; The information processing system of claim 1 , further comprising:

9. a tenth identification means for identifying a destination for a second traveler different from the plurality of travelers; a second estimation means for estimating the scores of the second traveler for the plurality of factors based on the identified destinations and the scores calculated for each of the plurality of travellers; The information processing system according to claim 2 , further comprising:

10. 1. A computer-implemented information processing method, comprising: acquiring responses to a survey about at least one of daily life and travel from a plurality of travelers; clustering the plurality of travelers based on the survey questions and the obtained answers, and identifying the cluster to which each traveler belongs; a receiving step of receiving a designation of any one of the identified clusters; Identifying, as destinations, places where the traveler actually stayed based on a behavior log including location information of the traveler belonging to the specified cluster; outputting information indicating the identified destinations; An information processing method comprising:

11. performing a factor analysis based on the questions in the attitude survey and the obtained answers to extract a plurality of factors; calculating a score for each of the plurality of travelers for the plurality of extracted factors based on the obtained answers; and The information processing method according to claim 10 , wherein the step of identifying a cluster includes clustering the plurality of travelers based on the calculated scores, and identifying a cluster to which each of the travelers belongs.

12. The information processing method according to claim 11 , wherein the plurality of factors include factors related to taste or quality consciousness, receptivity to influence, willingness to take on a challenge, or willingness to pay low prices.

13. The information processing method according to claim 11 , wherein the plurality of factors include factors related to a degree of importance attached to one's own preferences, awareness of social media, activity orientation, or a degree of importance attached to the evaluations of others.

14. Each traveler belongs to a cluster, Clusters with less variance in scores for each factor compared to other clusters, A cluster in which the scores for factors related to awareness of SNS and factors related to low price orientation are higher than the scores for other factors. Clusters with higher scores on factors related to taste or quality consciousness and the degree to which they attach importance to their own preferences compared to other factors. Clusters with higher scores for each factor compared to the average scores of other clusters, Clusters with low scores for each factor compared to the average scores of other clusters The information processing method according to claim 11 , wherein at least one of the following is included.

15. Identifying a cluster to which a first traveler included in the plurality of travelers belongs; Identifying destinations of each traveler belonging to the identified cluster; providing information about the identified destinations to the first traveler; The information processing method of claim 10 further comprising:

16. acquiring a response to the attitude survey from a second traveler different from the plurality of travelers; calculating a score for the second traveler for the plurality of factors based on the obtained responses; Identifying a cluster to which the second traveler belongs based on the calculated score; Identifying destinations of each traveler belonging to the identified cluster; providing information about the identified destinations to the second traveler; The information processing method of claim 11 , further comprising:

17. Identifying a destination for a second traveler different from the plurality of travelers; estimating a cluster to which the second traveler belongs based on the identified destinations and the clusters identified for each of the plurality of travelers; The information processing method of claim 10 further comprising:

18. Identifying a destination for a second traveler different from the plurality of travelers; a step of estimating the scores of the second traveler for the plurality of factors based on the identified destinations and the scores calculated for each of the plurality of travellers; The information processing method of claim 11 , further comprising:

19. A program for causing a computer to function as each of the units according to any one of claims 1 to 5.

Images