Information Processing Systems

Abstract

An information processing system, an information processing method, and a program are provided that quickly and effectively analyze posted information. [Solution] In the information processing system, the management server includes an acquisition unit that acquires posted information about a specified store, and an analysis unit that is a setting unit that sets evaluation items for the store and is a classification unit that acquires classification results in which sentences included in the posted information are classified into evaluation items according to the content of the sentences.

Description

[Technical Field]

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

[0002] In recent years, a number of posting sites have been established on the Internet, which are websites that publish posted information indicating user evaluations and usage status of stores and products. On such posting sites, for example, when users post information such as photos of the interior of a store such as a restaurant or food, or written descriptions of the store's atmosphere or impressions of the store, the posted information is organized by store or product and made available for general users to view. This allows general users to refer to the posted information when selecting a store or product.

[0003] Furthermore, stores can use the collected information posted by users as a reference for managing their stores. For example, Patent Document 1 discloses a system that acquires information posted by users about stores it operates from multiple posting sites and displays it as a list. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6984938 Summary of the Invention [Problem to be solved by the invention]

[0005] In the above situation, the store can further utilize the collected posted information for reference in store management by analyzing the details of the information. However, the amount of posted information is enormous and the content is diverse, which creates the problem that the analysis takes time and makes it difficult to perform an effective analysis.

[0006] Therefore, an object of the present disclosure is to solve the above-mentioned problem that analyzing posted information takes time and is difficult to perform effectively. [Means for solving the problem]

[0007] An information processing system according to an embodiment of the present disclosure includes: An acquisition means for acquiring posted information posted about a predetermined store; A setting means for setting evaluation items for a store; a classification means for acquiring a classification result in which a sentence included in the posted information is classified into the evaluation items according to the content of the sentence; Equipped with The structure is as follows. Furthermore, an information processing method according to an embodiment of the present disclosure includes: The information processing device Acquires posted information about a specific store, Set evaluation criteria for the store, Obtaining a classification result in which the sentences included in the posted information are classified into the evaluation items according to the contents of the sentences. The structure is as follows. Furthermore, a program according to an embodiment of the present disclosure includes: Acquires posted information about a specific store, Set evaluation criteria for the store, Obtaining a classification result in which the sentences included in the posted information are classified into the evaluation items according to the contents of the sentences. Have the computer perform the process, The structure is as follows. [Effects of the Invention]

[0008] With the above-described configuration, the present disclosure makes it possible to quickly and effectively analyze posted information. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating an overall configuration of an information processing system according to the present disclosure. [Figure 2] FIG. 2 is a block diagram showing the configuration of the management server disclosed in FIG. 1. [Figure 3] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 4] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 5] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 6] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 7] 2 is a flowchart showing the operation of the management server disclosed in FIG. 1; [Figure 8] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 9] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 10] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 11] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 12] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. [Figure 13] FIG. 2 is a diagram showing a process performed by the management server disclosed in FIG. 1. DETAILED DESCRIPTION OF THE INVENTION

[0010] <Embodiment 1> A first embodiment of the present disclosure will be described with reference to Fig. 1 to Fig. 7. Fig. 1 and Fig. 2 are diagrams for explaining the configuration of an information processing system, and Fig. 3 to Fig. 7 are diagrams for explaining the processing operation of the information processing system.

[0011] [composition] The information processing system of the present invention is primarily intended to manage information posted on a posting site, known as a word-of-mouth site. As shown in Fig. 1, the information processing system is configured by a management server 10, a plurality of posting site servers 20, a poster terminal 30, a viewer terminal 40, an administrator terminal 50, and a text processing device 60, all of which are connected via a network N. Each component will be described in detail below.

[0012] The posting site server 20 is an information processing device managed by a business that provides a service for publishing posted information, and operates a website such as a posting site on the Internet. In this embodiment, the posting site provided by the posting site server 20 publishes a page that publishes information about a store P, such as a restaurant, as well as a page that publishes posted information from contributors 31 who are users who have visited the store P. The posted information posted and published by contributors 31 includes, for example, photographs (photographed images) of the interior and food of store P (target), written information (character information) such as impressions about the service and food received at store P, and even numerical evaluation information expressing an evaluation of store P.

[0013] In this case, the evaluation information is a numerical evaluation value that indicates the degree of evaluation of the store by the user. For example, the evaluation value is set to a value of "0 to 5," with the larger the value, the higher the evaluation. However, the evaluation value may be expressed as any range of values ​​and may be expressed by any information, not limited to numerical values. The evaluation information also includes time information. For example, the time information is information that indicates time, such as the date when the user visited the store or the date when the evaluation information was posted by the user. The time information is included in the evaluation information, for example, by being input together with the evaluation information when the user posts it, or by being added when the evaluation information is posted by the posting site server 20.

[0014] An example of a posting site provided by the posting site server 20 is Google (registered trademark). However, the posting site provided by the posting site server 20 may be any posting site, such as a search site, a reservation site, a review site, a survey site, a weblog, or a social networking service (SNS) site. An example of an SNS site is Instagram (registered trademark).

[0015] In this embodiment, there are multiple posting site servers 20, each of which operates a different posting site. Therefore, the posted information for the same store P is posted and made public on each of the posting sites operated by each posting site server 20.

[0016] Furthermore, the posting site server 20 is not necessarily limited to publishing posted information on a website, etc. For example, the posting site server 20 may simply set up a survey site or a payment site and acquire and store the posted information described above from users.

[0017] The posted information handled on the posting site provided by the posting site server 20 is not limited to information about a store P such as a restaurant, but may be information about any type of store, or may be posted information about a product or service (target). Furthermore, the posted information is not limited to information about a store or product, but may be information about any target. Furthermore, the posting site server 20 is not necessarily limited to discriminating posted information by target, such as by store or product, but may disclose posted information without discriminating by target, for example, by poster 31.

[0018] Contributor terminal 30 (user terminal) is an information processing terminal such as a smartphone or laptop computer operated by contributor 31, who is a user who has visited a target such as store P. Contributor terminal 30 has a function of accessing a posting site on the Internet and posting posted information to the posting site when operated by contributor 31. For example, contributor terminal 30 posts, as posted information, photos taken by contributor 31 inside store P or photos of food served at store P, or posts, as posted information, evaluation information that evaluates store P using a number on a multiple-level scale entered by contributor 31, or text information expressing impressions in text.

[0019] The poster terminal 30 may access the posting site directly, or may be guided to access the posting site from an access destination based on address information such as a QR code installed in store P. Furthermore, if the access destination of address information such as a QR code installed in store P is the survey site of store P, the poster terminal 30 also has a function to transmit responses to surveys presented on the survey site.

[0020] Viewer terminal 40 is an information processing terminal such as a smartphone or laptop computer operated by viewer 41. Viewer terminal 40 has a function of accessing a posting site on the Internet and viewing posted information published on the posting site when operated by viewer 41. For example, viewer terminal 40 can view photos of the interior of store P and photos of the food served at store P posted by poster 31, evaluation information that rates store P on a multiple-level numerical scale, and text information that expresses impressions in text.

[0021] The administrator terminal 50 is an information processing terminal operated by an administrator 51 who manages posted information about a store at a business operator that operates the store. The administrator terminal 50 accesses the management server 10 and manages posted information about the store, such as by displaying and monitoring the posted information about the store acquired by the management server 10 as described below, and analyzing the posted information. In particular, the administrator terminal 50 acquires a classification result in which text information (divided text information) of the posted information is classified into evaluation items and emotion items according to the content of the text information, and displays information based on the classification result to analyze the posted information, as described below. The administrator terminal 50 also generates a reply message to the posted information via the management server 10 and posts it to the posting site server 20. The administrator terminal 50 also manages information such as a questionnaire about the store acquired by the management server 10. The administrator terminal 50 can also post information about the store on each posting site via the management server 10. The number of stores for which the administrator 51 manages posted information is not limited to one, and may be multiple.

[0022] In this embodiment, it is assumed that the business operator who operates store P operates multiple stores P. For example, the business operator operates 50 stores, and monitors and analyzes information posted to these stores, and also posts replies to the posted information. However, the business operator who operates store P may operate only one store, or may monitor and analyze information posted to multiple stores, including its own store and stores of other businesses.

[0023] The text processing device 60 (text processing device) is an information processing device that is connected to the management server 10 via the network N, performs requested processing on input text information, and outputs the processing results to the management server 10 and is managed by a business that provides such services. As an example, the text processing device 60 is realized by an artificial intelligence chatbot such as ChatGPT provided by OpenAI, Inc. of the United States or VertexAI provided by Google LLC of the United States.

[0024] In this embodiment, the text processing device 60 is equipped with a text segmentation processing model generated by machine learning. The text segmentation processing model is generated by machine learning training data consisting of a combination of pre-prepared text information and segmented text information obtained by segmenting the text information according to its content. As a result, the text segmentation processing model is configured to segment the text information into segmented text information consisting of shorter character strings in response to a request for segmentation processing of the text information. However, the text processing device 60 may also segment the text information into multiple segmented text information using any method without using the text segmentation processing model. For example, the text processing device 60 may perform morphological analysis on character strings in the text information to generate segmented text information according to the content of the sentence based on the order and connection status of morphemes, or may generate segmented text information by segmenting the text information based on punctuation or paragraphs.

[0025] In addition, in this embodiment, the text processing device 60 is equipped with a text classification processing model generated by machine learning. The text classification processing model is generated by machine learning training data that is prepared in advance and is composed of a combination of text information (segmented text information) and items corresponding to the content of the text information (segmented text information). As a result, the text classification processing model is configured to classify the text information into items corresponding to the content of the text information from among multiple items (e.g., evaluation items and emotion items described below) in response to a request for classification processing of the text information. Note that in this embodiment, the text classification processing model is configured to classify each piece of segmented text information segmented from the text information by the text segmentation processing model as described above into items corresponding to the content of the segmented text information. However, the text classification processing model may be configured to classify any unsegmented text.

[0026] Here, the text classification processing model is set with four items as first classification items that can be used to evaluate a store: "quality," "customer service," "cleanliness," and "atmosphere." The "quality" item refers to the quality (Q) of the store, and represents, for example, the quality of the products (e.g., food) offered at the store, the menu, and prices, etc. The "customer service" item refers to the service (S) of the store, and represents, for example, the service-related details, such as the store's customer service and attention to detail. The "cleanliness" item refers to the hygienic conditions (C) of the store, and represents, for example, details related to hygiene aspects, such as the store's cleanliness, cleaning status, and product handling. The "atmosphere" item refers to the atmosphere (A) of the store, and represents, for example, details related to the environment, such as the exterior and interior design that matches the store's concept, and employee uniforms. The text classification processing model then analyzes the content of the segmented text information described above and classifies it into the first items corresponding to such content: "quality," "customer service," "cleanliness," and "atmosphere."

[0027] In addition to the four items described above, the sentence classification processing model of this embodiment further includes two second items, "positive" and "negative," which are emotion items (expression items) that correspond to emotions expressed in sentences, different from the evaluation items. In other words, the sentence classification processing model classifies segmented sentence information into "positive" and "negative" items according to the content of the sentence. Therefore, the sentence classification processing model classifies each piece of segmented sentence information into one of the four store evaluation items set as first items, namely, "quality," "customer service," "cleanliness," and "atmosphere," and also into one of two sentence expression items set as second items, namely, "positive" and "negative." Here, "positive" indicates a positive statement about the store, and "negative" indicates a negative statement about the store. The sentence classification processing model then analyzes the content of the segmented sentence information and classifies it into the items corresponding to the content, namely, "positive" and "negative."

[0028] However, the text processing device 60 may classify the segmented text information into the above-mentioned items in any manner without using a text classification processing model. For example, the text processing device 60 may be configured such that the content, phrases, keywords, etc. of the text corresponding to each item are set in advance, and the segmented text information may be classified into the corresponding item according to the content, phrases, keywords in the text, etc.

[0029] In this embodiment, the text processing device 60 implements a program generation model generated by machine learning. The program generation model is generated by machine learning learning data consisting of a combination of pre-prepared text information (segmented text information), items, and program data associating these items. As a result, the program generation model is configured to generate program data associating text information with items into which the text information is classified, as described above, in response to a request for program generation processing of the text information. In this embodiment, the program generation model generates program data associating segmented text information segmented from the text information by the text segmentation processing model with items into which the segmented text information is classified, as described above. As an example, as shown in FIG. 3 (described later), the program generation model generates program data in a programming language in JSON (JavaScript Object Notation) format that associates segmented text information with classified items (one of "quality," "customer service," "cleanliness," and "atmosphere," and one of "positive" and "negative"). However, the format of the program generated by the program generation model may be any format or language.

[0030] However, the text processing device 60 may generate program data in any manner without using a program generation model. For example, the text processing device 60 may have set rules for converting associated divided text data and items into program data or set program data templates, and may use such rules or templates to convert the associated divided text data and items into program data.

[0031] The management server 10 is configured with one or more information processing devices each including a calculation device and a storage device. As shown in FIG. 2, the management server 10 includes an acquisition unit 11, an analysis unit 12, and an output unit 13. The functions of the acquisition unit 11, the analysis unit 12, and the output unit 13 can be realized by the calculation device executing a program for realizing each function stored in the storage device. The management server 10 also includes a store information storage unit 16 and a posted information storage unit 17. The store information storage unit 16 and the posted information storage unit 17 are configured with a storage device. Each component will be described in detail below.

[0032] First, the store information storage unit 16 stores information about the store P input from the administrator terminal 50 of the business operator that operates the store P. At this time, if the business operator operates multiple stores P, information about each of the multiple stores P is registered.

[0033] Store information to be registered includes the store name, store address, store attributes, and information about the posting site server 20 to which posted information about the store is posted. The store name functions as identification information for identifying the store. The store address indicates the location of the store and can specify the location by prefecture or region, for example, and also functions as an attribute of the store. Store attributes include information about the store's location (roadside, downtown, tourist spot, suburban area, commercial facility, etc.), whether or not there is parking, the store's store representative on the business side, the store's franchisee, the store's brand, etc. The information about the posting site server 20 to which posted information about the store is posted is information for identifying the posting site or information for obtaining posted information posted to the posting site server 20 from the posting site server 20. For example, it is information for identifying the posting site server 20 and the store, such as address information of the posting site where posted information about the store is published.

[0034] Furthermore, in the store information storage unit 16, for example, a plurality of stores operated by the same business or businesses forming a group are associated with each other to form a store group and are registered.

[0035] The acquisition unit 11 (acquisition means) accesses each posting site server 20 based on the registered store information as described above, acquires posted information published on each posting site, and stores the information in the posted information storage unit 17. At this time, the acquisition unit 11 acquires posted information about each store from each posting site server 20, distinguishing between each store and each store group, associates the store information with the posting site information, and stores the associated information in the posted information storage unit 17. In other words, the acquired posted information associates the information about the corresponding store with the information about the posting site where the information was posted. The acquisition unit 11 may acquire posted information from any posting site, such as the search sites, reservation sites, review sites, survey sites, weblogs, and SNS sites described above.

[0036] The analysis unit 12 (classification means) requests the text processing device 60 to analyze the text information included in the acquired posted information as described above. Specifically, the analysis unit 12 transmits the text information included in the posted information to the text processing device 60, and requests segmentation processing, classification processing, and program generation processing of the text information. In response to this, the text processing device 60 first segments the text information into segmented text information using the text segmentation processing model, as described above, and then classifies each segmented text information into items according to the content of the segmented text information using the text classification processing model. Furthermore, the text processing device 60 uses the program generation model to generate program data that associates the segmented text information with the items into which the segmented text information has been classified. Then, the analysis unit 12 acquires the program data generated by the text processing device 60. In other words, the analysis unit 12 acquires a classification result in which each segmented text information obtained by segmenting the text information included in the posted information is classified into predetermined items, and also acquires program data that associates the segmented text information with the items that are the classification result.

[0037] The analysis unit 12 may sequentially obtain the above-mentioned processing results from the text processing device 60, or may sequentially issue the above-mentioned processing requests to the text processing device 60. That is, the analysis unit 12 may first issue a request for segmentation processing of text information to obtain segmented text information, then issue a request for classification processing of the segmented text information to obtain the classification results, and further issue a request for program generation to obtain program data.

[0038] Here, with reference to FIG. 3, we will explain an example of text information included in the posted information for which the analysis unit 12 requests the text processing device 60 to perform analysis, and an example of analysis processing by the text processing device 60. First, assume that the text information included in the posted information, as shown in reference character D1 in FIG. 3, is "You can eat delicious yakiniku for 1,000 yen! The staff are a little unfriendly and scary, but the floor is slippery, so be careful not to fall. The atmosphere is calm and comfortable." The text processing device 60 divides the text information shown in reference character D1 in FIG. 3 into segments of text information shown in each line of reference character D2 in FIG. 3, and further classifies the segments into items shown at the left end of each line according to the content of the segments. For example, the segmented text information "You can eat delicious yakiniku for 1,000 yen!" shown in the first line of reference character D2 in FIG. 3 is classified into a first item "quality (Q)" and a second item "positive (positive)" according to its content. Furthermore, the segmented sentence information shown in the second line, "The staff are a bit unfriendly and scary, though," is classified into the first category, "Service (S)," and the second category, "Negative," depending on its content. Furthermore, the segmented sentence information shown in the third line, "Also, the floor is slippery, so be careful not to fall," is classified into the first category, "Cleanliness (C)," and the second category, "Positive," depending on its content. Furthermore, the segmented sentence information shown in the fourth line, "The atmosphere is calm and comfortable," is classified into the first category, "Atmosphere (A)," and the second category, "Positive," depending on its content.

[0039] The text processing device 60 then generates program data associating the segmented text information shown in symbol D2 of Fig. 3 with the classified items, as shown in symbol D3 of Fig. 3. For example, the segmented text information shown in the first line of symbol D2 of Fig. 3, "You can eat delicious yakiniku for 1,000 yen!", with the first item "quality (Q)" and the second item "positive," to generate program data like the first paragraph of symbol D3 of Fig. 3. In the program data, the segmented text information is indicated by "text information" following "sentence," the first item is indicated by "category" followed by "quality," "service," "cleanliness," or "Atmosphere," and yet another second item is indicated by "posigive" or "negative" following "sentiment."

[0040] The analysis unit 12 acquires the program data shown as symbol D3 in Figure 3 from the text processing device 60, but it may also acquire each divided text information obtained by dividing the text information, as shown as symbol D2, or information that associates the divided text information with items that are classification results.

[0041] Furthermore, the analysis unit 12 requests the text processing device 60 to analyze the text information and obtains the processing results from the text processing device 60. However, the analysis unit 12 itself may perform the above-described analysis of the text information. For example, the analysis unit 12 may be equipped with each model provided in the text processing device 60 and perform the above-described segmentation, classification, and program generation processes using such models. Alternatively, the analysis unit 12 may segment the text information, classify the segmented text information, and generate program data according to the content of the text information. For example, the analysis unit 12 may generate segmented text information according to the results of morphological analysis of the text information, or may classify the segmented text information into categories according to keywords contained in the segmented text information, and may generate a program using a template that associates the segmented text information with the classified categories.

[0042] The output unit 13 outputs the posted information for a specific store acquired from the posting site server 20 as described above to be displayed on the administrator terminal 50. At this time, if there is a plurality of pieces of posted information corresponding to a specific store acquired from a plurality of posting site servers 20, the output unit 13 outputs the plurality of pieces of posted information so as to be collectively displayed as a list. Furthermore, if a plurality of specific stores are associated with each other to form a store group and registered as described above, the output unit 13 outputs the posted information corresponding to each of the plurality of specific stores so as to be collectively displayed as a list. Note that the output unit 13 associates the posted information with information such as a store name that identifies the store where the posted information was posted, information such as a posting site name that identifies the posting site, and information about the poster, and displays the information in association with the posted information.

[0043] For example, as shown in FIG. 4, the output unit 13 outputs a list of rating information and text information from the posted information to be displayed on the administrator terminal 50. The example in FIG. 4 shows a case where "AAA Store" and "BBB Store" are associated as group stores, and the output unit 13 displays a list of rating information and text information as posted information posted to multiple posting sites, such as "Posting Site A" and "Posting Site B," for each of these multiple stores. Note that in FIG. 4, "stars" represent rating information, and the number of stars represents a numerical rating value, with a higher number indicating a higher rating for the store. Also, in FIG. 4, the output unit 13 displays text information such as impressions about the store included in the rating information, but if the posted information includes photographed images such as photos, the output unit 13 may display a list of the photographed images.

[0044] Then, when displaying the posted information, the output unit 13 outputs information corresponding to the processing result acquired from the text processing device 60. Specifically, the output unit 13 outputs the divided text information so as to associate and display the items into which the divided text information is categorized. As an example, as shown in FIG. 4, the output unit 13 associates and displays the divided text information "You can eat delicious yakiniku for 1,000 yen!" with the first item "Quality (Q)" and the second item "Positive," and also associates and displays the divided text information "The waiter is a bit unfriendly and scary, though" with the first item "Service (S)" and the second item "Negative." At this time, the output unit 13 can easily associate and display the divided text information with the items into which the divided text information is categorized by using the program data acquired from the text processing device 60.

[0045] The output unit 13 may also output information about the categories into which the acquired segmented text information is categorized, so that it is displayed on the administrator terminal 50 for each store or for each attribute set for the store. In this case, the output unit 13 tallies the number of segmented text information for each store or for each attribute set for the store, and outputs the tallied results for display. For example, as shown in FIG. 5, the output unit 13 may tallie the number of segmented text information categorized into each first category and the number of segmented text information categorized into each second category for each store, calculate the ratio of the number of segmented text information categorized into the second category to the total number of segmented text information categorized into the first category, and display this ratio as the tallied information. As an example, in FIG. 5, the tallied results for "AAA Store" are displayed in the second row, and a radar chart is first displayed with the four first categories, "quality," "customer service," "cleanliness," and "atmosphere," as vertices. Then, on the radar chart, the percentage of the number of divided sentence information classified into each first item that is classified into either the second item "positive" or "negative" is displayed, along with the numerical value of this percentage. In particular, in this example, the percentage of the number of divided sentence information classified into each first item "quality," "customer service," "cleanliness," and "atmosphere" that is classified into the second item "positive" is displayed.

[0046] The first row of FIG. 5 displays the aggregated results for "all stores," which allows comparison with the average value. Specifically, the first row of FIG. 5 displays, on a radar chart with each of the four first items as a vertex, the percentage of the number of segmented text information classified into the second item "positive" among the segmented text information classified into each first item for all stores, along with the numerical value of that percentage. In the above example, the percentage of the number of segmented text information classified into the second item "positive" among the number of segmented text information classified into each of the first items "quality," "customer service," "cleanliness," and "atmosphere" is calculated and displayed. However, it is also possible to calculate and display the percentage of the number of segmented text information classified into the second item "negative" among the number of segmented text information classified into each of the first items "quality," "customer service," "cleanliness," and "atmosphere."

[0047] Furthermore, as shown in FIG. 6, the output unit 13 may output, for each store attribute, aggregated information that aggregates the number of segmented text information items classified into each category for all stores belonging to the corresponding attribute, so as to be displayed on the administrator terminal 50. Specifically, for each store attribute, the output unit 13 displays the ratio of the number of segmented text information items classified into the second category "positive" to the number of segmented text information items classified into each first category, along with the numerical value of this ratio. As an example, FIG. 6 shows an example of aggregation by store attribute "brand," and the second row displays the aggregation results for 10 stores belonging to "Brand AA." In particular, this example displays the ratio of the number of segmented text information items classified into the second category "positive" among those classified into each first category "quality," "customer service," "cleanliness," and "atmosphere." Note that the first row of FIG. 6 displays the aggregation results for "all stores," which allows comparison with the average value. Note that aggregation may be performed by any store attribute, such as the store's "region (prefecture)" or "location," and the aggregation results may be displayed. In this case, the attribute of the store may be "store name," and each attribute of the store includes each store.

[0048] In the above example, the output unit 13 displays the ratio of the number of pieces of segmented text information classified into the second category to the number of all pieces of segmented text information classified into each first category using numerical values ​​and a graph. However, the output unit 13 may simply display the number of pieces of segmented text information classified into each category (first category or second category) using a graph or numerical values. For example, the output unit 13 may display the number of pieces of segmented text information classified into the first categories "quality," "customer service," "cleanliness," and "atmosphere" and the number of pieces of segmented text information classified into the second categories "positive" and "negative" using a graph or numerical values ​​for each store or each store attribute. Furthermore, the output unit 13 may display any information in any display format as long as the information is based on the number of pieces of segmented text information classified into each category.

[0049] [Operation] Next, the operation of the above-described information processing system, particularly the operation of the management server 10, will be described mainly with reference to the flowchart of FIG.

[0050] First, in a plurality of posting site servers 20, posting information about store P is posted by contributor 31 on each posting site and made public, and can be viewed from viewer terminal 40 of viewer 41.

[0051] The management server 10 periodically or at any timing acquires posted information published on each posting site from the multiple posting site servers 20 (step S1). Then, the management server 10 stores the posted information acquired from the multiple posting site servers 20 for each store or each store group.

[0052] The management server 10 then requests the text processing device 60 to analyze the text information included in the acquired posted information (step S2). Specifically, the management server 10 transmits the text information included in the posted information to the text processing device 60, and requests the text information to be divided, classified, and generated as a program. In response to this, the text processing device 60 divides the text information into pieces of divided text information, as shown in FIG. 3, classifies each piece of divided text information into categories according to the content of the divided text information, and generates program data that associates the divided text information with the categories into which the divided text information has been classified. The management server 10 then obtains the analysis results by the text processing device 60, i.e., the divided text information and category classification results and program data as shown in FIG. 3 (step S3).

[0053] Next, the management server 10 outputs the posted information to the administrator terminal 50 for display. At this time, the management server 10 outputs the analysis results of the text information included in the posted information for display (step S4). For example, as shown in FIG. 4, when displaying a list of the text information of the posted information, the management server 10 displays the divided text information into which the text information has been divided, and outputs the information so that the items into which each divided text information has been classified are associated and displayed. Furthermore, as shown in FIGS. 5 and 6, the management server 10 may tally the items into which the divided text information for each store has been classified for each store or for each attribute set for the store, and output the information based on the tallying results. As an example, a radar chart may be displayed for each store or for each attribute of the store, with four first items, "quality," "customer service," "cleanliness," and "atmosphere," as vertices, and the ratio of the number of divided text information classified into the second item to the number of divided text information classified into the first item may be displayed on the radar chart.

[0054] As described above, the information processing system of this embodiment divides sentences included in posted information, obtains classification results by classifying each divided sentence into categories according to its content, and outputs information based on the classification results. For example, the division and classification processes can be performed using a model generated by machine learning. As a result, in this embodiment, even if the number of posted information items is enormous and the content is diverse, the time required for analysis can be shortened and effective analysis can be performed.

[0055] In the above, we have given an example of dividing the text information contained in the posted information into divided text information and classifying each divided text information into categories, but it is also possible to classify the text information into categories without dividing it.

[0056] Furthermore, in the above, four items, namely, quality, customer service, cleanliness, and atmosphere, are given as examples of the first items, which are evaluation items for a store, but the content of the items is not limited to these four, and other items may be set in addition to these, or other items different from these may be set. Also, in the above, two items, positive and negative, are given as examples of the second items, which are expression items for sentences, but the content of the items is not limited to these two, and other items, such as "neither," may be set in addition to these, or other items different from these may be set.

[0057] <Embodiment 2> A second embodiment of the present disclosure will be described with reference to Figures 8 and 9. Figures 8 and 9 are diagrams for explaining the processing operation of the information processing system.

[0058] The management server 10 constituting the information processing system in this embodiment has the following configuration in addition to the same configuration as in the above-described embodiment 1. In particular, the management server 10 in this embodiment is configured such that the output unit 13 has the following functions in addition to the functions of the above-described embodiment 1.

[0059] First, as described in the first embodiment, the segmented sentence information of the posted information for each store or each attribute (each store group) set for the store is classified into four categories, namely, "quality," "customer service," "cleanliness," and "atmosphere," which are store evaluation categories set as first categories, and further classified into "positive" and "negative" which are sentence expression categories set as second categories. Then, the output unit 13 calculates, for each first category, aggregated information, which is a numerical value representing the proportion of the segmented sentence information classified into the second category "positive" among the segmented sentence information classified into the first category, and outputs the aggregated information as the aggregation result. As an example, as shown in FIG. 8, the aggregated result for "AAA Store" is displayed in the second row, and for each of the first categories "quality," "customer service," "cleanliness," and "atmosphere," the proportion of the number of segmented sentence information classified into the second category "positive" to the number of segmented sentence information classified into the corresponding first category is displayed. That is, in this example, for each of the first items "quality," "customer service," "cleanliness," and "atmosphere," the percentage of segmented text information classified into each first item that fell under the second item "positive" is displayed as aggregated values: "60(%)," "58(%)," "62(%)," and "60(%)." The first row of Figure 8 displays the aggregated results for "all stores," which allows comparison with the average value.

[0060] In this embodiment, the output unit 13 further displays the tally results as shown in FIG. 8 in a selectable manner, as indicated by the symbol L. When the output unit 13 receives the selection of a tally result, it outputs the segmented text information categorized into the item related to the selected value. That is, when a tally result corresponding to one of the first items "quality," "customer service," "cleanliness," or "atmosphere" is selected, it displays the segmented text information categorized into the selected first item. In this case, the output unit 13 outputs the segmented text information categorized into one of the selected first items "quality," "customer service," "cleanliness," or "atmosphere" so that it is further divided into segmented text information corresponding to the second item "positive" and segmented text information corresponding to the second item "negative." As an example, as shown by symbol L in Fig. 8, when a numerical value corresponding to the first item "quality" is selected, the divided text information classified into the first item "quality" will be displayed, but in particular, as shown in Fig. 9, among the divided text information classified into the first item "quality," the divided text information corresponding to the second item "positive" and the divided text information corresponding to the second item "negative" are displayed separately. That is, in the example of Fig. 9, among the divided text information classified into the first item "quality," the divided text information corresponding to the proportion "60(%)" corresponding to the second item "positive" is displayed in the "positive" column on the left, and the divided text information corresponding to the remaining proportion "40(%)" corresponding to the second item "negative" is displayed in the "negative" column on the right.

[0061] This allows the store to easily recognize the proportion of positive or negative opinions for each of the first evaluation items for the store, and also allows the store to easily distinguish between positive and negative comments in the actual posted information, thereby enabling the posted information to be analyzed quickly and effectively.

[0062] In the above description, the output unit 13 displays the divided sentence information when a numerical value, which is aggregate information such as a ratio, is selected, as shown by symbol L in Fig. 8, but the divided sentence information may be displayed in response to other operations. For example, when a first item or graph on the radar chart shown in Fig. 8 is selected, the divided sentence information classified into the first item corresponding to the selected portion may be displayed for each classified second item as shown in Fig. 9.

[0063] Furthermore, the function of displaying divided sentence information as shown in Figures 7 and 8 described above can also be applied to the case of displaying, for each store attribute, a summary result based on the number of divided sentence information classified into each item for all stores that belong to the corresponding attribute, as shown in Figure 6. For example, Figure 6 shows an example of summary by store attribute "brand," but similar to the example of Figure 8 described above, when a percentage value in the summary result or an item or graph on a radar chart is selected, the divided sentence information classified into a first item corresponding to the selected location may be displayed for each classified second item as shown in Figure 9.

[0064] <Embodiment 3> A third embodiment of the present disclosure will be described with reference to Fig. 10 to Fig. 13. Fig. 10 to Fig. 13 are diagrams for explaining the processing operation of the information processing system.

[0065] The management server 10 constituting the information processing system in this embodiment has the following configuration in addition to the same configuration as in the above-described embodiments 1 and 2. In particular, the management server 10 in this embodiment is configured such that the analysis unit 12 and the output unit 13 have the following functions in addition to the functions of the above-described embodiments 1 and 2.

[0066] First, as explained in the first and second embodiments, the segmented text information of the posted information for each store or for each attribute set for the store (for each store group) is classified into four items, namely, "quality," "customer service," "cleanliness," and "atmosphere," which are evaluation items for the store set as first items, and further classified into "positive" and "negative," which are emotion items (expression items) set as second items. In addition, in this embodiment, it is possible to add a first item that is an evaluation item for the store, and the segmented text information can also be classified into the added first evaluation item.

[0067] Specifically, as shown in FIG. 10 , the analysis unit 12 (setting means) outputs a classification setting screen including input fields for an “item name” and an “item description” of an evaluation item for a store to be newly added as a first item to the manager terminal 50 for display. Then, the analysis unit 12 accepts text information input from the manager terminal 50 into the input fields for the “item name” and the “item description” of the classification setting screen, and sets a new evaluation item identified by the text information of the “item name.” For example, as shown in FIG. 11 , “time” and “size” may be set as new evaluation items. Note that the “item description” is information that explains the content of the evaluation item. For example, “waiting time” is set as the explanation for the evaluation item “time,” and “size or quantity” is set as the explanation for the evaluation item “size.” Note that the evaluation item newly added as the first item is not limited to the above-mentioned items, and may be an evaluation item of any content, such as “taste” or “freshness.”

[0068] In this embodiment, the four items of "quality," "customer service," "cleanliness," and "atmosphere," which were exemplified as first items in the first and second embodiments, are set in advance as evaluation items for existing stores. Therefore, by setting new evaluation items in the analysis unit 12 as described above, evaluation items such as "time" and "size" are added to the four items as the first items, which are evaluation items for stores. However, the first items are not limited to being set in advance as the four evaluation items described above, and new evaluation items may be set in response to input from the administrator terminal 50 as described above when no evaluation items have been set.

[0069] The analysis unit 12 (classification means) then requests the text processing device 60 to analyze the text information included in the acquired posted information as described above. Specifically, the analysis unit 12 transmits the text information included in the posted information and the names of the first and second items to be classified to the text processing device 60, and requests the text processing device 60 to perform segmentation processing, classification processing, and program generation processing for the text information. At this time, the analysis unit 12 outputs a selection screen to the manager terminal 50, as shown in FIG. 12, for selecting the first item, which is an evaluation item for the store, and accepts the selection of the evaluation item from the manager terminal 50. For example, the analysis unit 12 displays the four existing evaluation items, "quality," "customer service," "cleanliness," and "atmosphere," as well as newly added evaluation items such as "time," "size," "taste," and "freshness," on the selection screen so that they can be selected, and accepts the evaluation item selected by the manager terminal 50. The analysis unit 12 then transmits character information such as the "item name" and "item description" of the selected evaluation item to the text processing device 60 as evaluation item information for the first item to be classified. Here, it is assumed that the existing evaluation items "quality," "customer service," "cleanliness," and "atmosphere" and the newly added evaluation items "time," "size," "taste," and "freshness" are selected. The analysis unit 12 also transmits to the text processing device 60 the item names of the second items to be classified, "positive" and "negative," and text information describing their contents.

[0070] However, the analysis unit 12 may send information on all evaluation items without receiving a selection of evaluation information from the administrator terminal 50. In this case, the text processing device 60 classifies texts based on all evaluation items.

[0071] As described above, the text processing device 60 first uses the text segmentation processing model to segment text information into segmented text information, and then uses the text classification processing model to classify each segmented text information into categories corresponding to the content of the segmented text information. Specifically, the text processing device 60 uses the text classification processing model to classify the segmented text information into evaluation items corresponding to the evaluation item information corresponding to the content of the text, among the evaluation items that are the selected and transmitted first items. For example, if the text contains characters representing the name or description of an evaluation item, the text information is classified into the evaluation item corresponding to the name or description of the evaluation item. In this way, the text processing device 60 classifies the segmented text information into the evaluation items described above—“quality,” “customer service,” “cleanliness,” “atmosphere,” “time,” “size,” “taste,” and “freshness”—according to its content. The text processing device 60 also classifies the segmented text information into second categories—“positive” and “negative”—according to its content. Furthermore, the text processing device 60 uses a program generation model to generate program data that associates the segmented text information with the categories into which the segmented text information is classified.

[0072] Then, the analysis unit 12 acquires the program data generated by the text processing device 60. In other words, the analysis unit 12 acquires the classification results in which each piece of divided text information obtained by dividing the text information included in the posted information is classified into first items and second items, and also acquires program data that associates the divided text information with the items that are the classification results.

[0073] As in the first and second embodiments described above, the output unit 13 outputs information corresponding to the processing results acquired from the text processing device 60 so as to be displayed. Specifically, the output unit 13 may output information regarding the categories into which the acquired segmented text information has been classified, so as to be displayed on the manager terminal 50 for each store or for each attribute set for the store. In this case, the output unit 13 tallies the number of segmented text information for each store or for each attribute set for the store, and outputs the tallied results for display. For example, as shown in FIG. 13 , the output unit 13 tallies, for each store, the number of segmented text information classified into each first item (evaluation item) selected from the first items and the number of segmented text information classified into each second item, calculates, for each first item, the ratio of the number of segmented text information classified into the second item to the total number of segmented text information classified into the first item, and displays this ratio as tallied information. As an example, in FIG. 13, the second row displays the aggregated results for "AAA Store." First, a radar chart is displayed with each of the eight selected first categories, "quality," "customer service," "cleanliness," "ambiance," "time," "size," "taste," and "freshness," as a vertex. Then, on the radar chart, the percentage of the number of segmented text information classified into each first category that is classified into either the second category "positive" or "negative" is displayed, along with the numerical value of this percentage. In particular, in this example, the percentage of the number of segmented text information classified into each of the selected first categories, "quality," "customer service," "cleanliness," "ambiance," "time," "size," "taste," and "freshness," that is classified into the second category "positive" is displayed.

[0074] Here, the first row of FIG. 13 displays the aggregated results for "all stores," which allows comparison of the average value with the value for each store. Specifically, the first row of FIG. 13 displays, on a radar chart with each of the eight selected first items as a vertex, the percentage of the number of segmented text information classified into the second item "positive" among the segmented text information classified into each first item for all stores, along with the numerical value of that percentage. Note that in the above example, the percentage of the number of segmented text information classified into the second item "positive" among the number of segmented text information classified into each of the selected first items "quality," "customer service," "cleanliness," "atmosphere," "time," "size," "taste," and "freshness" is calculated and displayed. However, it is also possible to calculate and display the percentage of the number of segmented text information classified into the second item "negative" among the number of segmented text information classified into each first item.

[0075] As shown in FIG. 6 described in the first embodiment, the output unit 13 may output, for each store attribute, aggregate information that aggregates the number of pieces of segmented text information for all stores belonging to the corresponding attribute when the pieces of segmented text information are classified into each item, so as to be displayed on the administrator terminal 50. That is, in FIG. 6, the output unit 13 may display, for each store attribute (each brand in FIG. 6), the ratio of the number of pieces of segmented text information classified into the second item "positive" to the number of pieces of segmented text information classified into each of the eight first items selected as shown in FIG. 13, and may also display the numerical value of this ratio. When "store name" is set as a store attribute, the example of FIG. 13 in which the aggregate value of the classification results for each store is output can also be said to output the aggregate value of the classification results for each store attribute.

[0076] Although the present invention has been described above with reference to the above-described embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. Furthermore, at least one or more of the functions possessed by the management server 10 described above may be executed by an information processing device installed and connected anywhere on the network, i.e., may be executed by so-called cloud computing.

[0077] The above-described program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer-readable media can supply the program to a computer via a wired communication path such as an electric wire or optical fiber, or via a wireless communication path.

[0078] <Additional Notes> A part or all of the above-described embodiments can be described as follows: The following provides an overview of the configurations of the information processing system, information processing method, and program according to the present invention. However, the present invention is not limited to the following configurations. (Appendix 1) An acquisition means for acquiring posted information posted about a predetermined store; A setting means for setting evaluation items for a store; a classification means for acquiring a classification result in which a sentence included in the posted information is classified into the evaluation items according to the content of the sentence; An information processing system comprising: (Appendix 2) 10. The information processing system of claim 1, the setting means accepts selection of at least one of the set evaluation items, the classification means acquires the classification result in which the sentence is classified into the evaluation item according to the content of the sentence among the selected evaluation items. Information processing system. (Appendix 3) 10. The information processing system of claim 1, the setting means sets new evaluation items that are different from the existing evaluation items that have been set in advance, the classification means acquires the classification result in which the sentence is classified into the evaluation items according to the content of the sentence, from among the existing evaluation items and the newly set evaluation items; Information processing system. (Appendix 4) 10. The information processing system of claim 1, the setting means receives character information corresponding to the content of the evaluation item as evaluation item information; the classification means acquires the classification result in which the sentence is classified into the evaluation item corresponding to the evaluation item information according to the content of the sentence; Information processing system. (Appendix 5) 5. The information processing system according to claim 4, the classification means transmits the sentence and the evaluation item information to a sentence processing device to request classification processing of the sentence into the evaluation items, and obtains from the sentence processing device the classification result in which the sentence is classified into the evaluation items corresponding to the evaluation item information according to the content of the sentence; Information processing system. (Appendix 6) 10. The information processing system of claim 1, the classification means acquires, together with the classification result in which the sentence is classified into the evaluation item, the classification result in which the sentence is classified into the emotion item according to the content of the sentence, among preset emotion items different from the evaluation items. Information processing system. (Appendix 7) 7. The information processing system according to claim 6, an output means for outputting information based on the sentences classified into predetermined emotion categories for each evaluation category based on the classification results; Information processing system. (Appendix 8) 8. The information processing system according to claim 7, the output means outputs, for each evaluation item based on the classification result, aggregate information based on the number of sentences classified into a predetermined emotion item among the sentences classified into the evaluation item. Information processing system. (Appendix 9) 9. The information processing system according to claim 8, the output means outputs the aggregate information indicating the ratio of the number of the sentences classified into a specific emotion item to the number of all the sentences classified into the evaluation item, for each evaluation item, based on the classification result. Information processing system. (Appendix 10) 9. The information processing system according to claim 8, the output means outputs the aggregated information based on the classification result obtained by classifying the sentences included in the posted information for the store that belongs to a specific store attribute among the store attributes set for each store. Information processing system. (Appendix 11) 11. The information processing system of claim 10, the output means outputs the aggregated information based on the classification result obtained by classifying the sentences included in the posted information for the store that belongs to the specific store attribute, and also outputs the aggregated information based on the classification result obtained by classifying the sentences included in the posted information for all the stores. Information processing system. (Appendix 12) 9. The information processing system according to claim 8, the output means outputs the aggregated information on a radar chart with each of the evaluation items as a vertex. Information processing system. (Appendix 13) 10. The information processing system of claim 1, the classification means acquires the classification results of the sentences obtained by dividing the sentence information constituting the posted information; Information processing system. (Appendix 14) The information processing device Acquires posted information about a specific store, Set evaluation criteria for the store, Obtaining a classification result in which the sentences included in the posted information are classified into the evaluation items according to the contents of the sentences. Information processing methods. (Appendix 15) Acquires posted information about a specific store, Set evaluation criteria for the store, Obtaining a classification result in which the sentences included in the posted information are classified into the evaluation items according to the contents of the sentences. A program that causes a computer to perform a process. (Appendix A1) An acquisition means for acquiring posted information posted about a predetermined store; a classification means for acquiring a classification result obtained by dividing a sentence included in the posted information into a plurality of predetermined categories and classifying each divided sentence into the category according to the content of the divided sentence; an output means for outputting, based on the classification results, summary information based on the number of classified segment sentences for each of the items, and outputting the segment sentences corresponding to the summary information; An information processing system comprising: (Appendix A2) An information processing system according to claim A1, the classification means acquires the classification result in which each of the divided sentences is classified into the first item among a plurality of first items which are preset evaluation items of the store according to the content of the divided sentence; the output means outputs, for each of the first items based on the classification results, the aggregate information based on the number of the segmented sentences classified into the first item, and outputs the segmented sentences classified into the first items corresponding to the aggregate information. Information processing system. (Appendix A3) 1. An information processing system according to claim 1, further comprising: the classification means further acquires the classification result in which each of the divided sentences is classified into the second item among a plurality of second items which are sentence expression items different from the first item set in advance, according to the content of the divided sentence; The output means outputs, for each of the first items based on the classification results, the aggregate information based on the number of the segmented sentences classified into the second items among the segmented sentences classified into the first items, and outputs the segmented sentences classified into the first items corresponding to the aggregate information in accordance with the classification results into the second items. Information processing system. (Appendix A4) 1. An information processing system according to claim 1, further comprising: the output means outputs the aggregate information representing the ratio of the number of the segmented sentences classified into a specific item among the second items to the number of all the segmented sentences classified into the first item, for each of the first items, based on the classification result. Information processing system. (Appendix A5) An information processing system according to Appendix A4, the output means outputs the divided sentences classified into the first items corresponding to the selected aggregate information from the output aggregate information, by distinguishing the divided sentences from the second items into which the divided sentences are classified; Information processing system. (Appendix A6) An information processing system according to claim A1, the classification means acquires the classification result in which each of the divided sentences is classified into a first category corresponding to the content of the divided sentence out of a plurality of first categories in which evaluation items of at least quality, customer service, cleanliness, and atmosphere of the store are set; The output means outputs, based on the classification results, the aggregate information based on the number of segmented sentences classified into each of the first categories, namely, quality, customer service, cleanliness, and atmosphere, and outputs the segmented sentences classified into the first category corresponding to the aggregate information. Information processing system. (Appendix A7) An information processing system according to Appendix A6, the classification means acquires the classification result in which each of the divided sentences is classified into the second item according to the content of the divided sentence from among a plurality of second items in which at least positive and negative expression items are set, The output means outputs the summary information based on the number of segmented sentences classified into the second item, positive or negative, among the segmented sentences classified into the first item, for each of the first items, quality, customer service, cleanliness, and atmosphere, based on the classification results, and outputs the segmented sentences classified into the first item corresponding to the summary information in accordance with the classification results into the second item. Information processing system. (Appendix A8) 1. An information processing system according to claim 7, The output means outputs the aggregate information based on the ratio of the number of segmented sentences classified into the second item, which is a positive item, to the number of all segmented sentences classified into the first item, for each of the first items, which are quality, customer service, cleanliness, and atmosphere, based on the classification results. Information processing system. (Appendix A9) 9. The information processing system according to claim 8, the output means outputs the divided sentences classified into the first item corresponding to the selected aggregate information from the output aggregate information, distinguishing them by the affirmative or negative item, which is the second item into which the divided sentences are classified; Information processing system. (Appendix A10) The information processing device Acquires posted information about a specific store, Obtaining a classification result in which each of the divided sentences obtained by dividing the sentence included in the posted information is classified into the category according to the content of the divided sentence from among a plurality of predetermined categories; outputting, for each item based on the classification result, aggregate information based on the number of classified segment sentences, and outputting the segment sentences corresponding to the aggregate information; Information processing methods. (Appendix A11) Acquires posted information about a specific store, Obtaining a classification result in which each of the divided sentences obtained by dividing the sentence included in the posted information is classified into the category according to the content of the divided sentence from among a plurality of predetermined categories; outputting, for each item based on the classification result, aggregate information based on the number of classified segment sentences, and outputting the segment sentences corresponding to the aggregate information; A program that causes a computer to perform a process. [Explanation of symbols]

[0079] 10 Management Server 11 Acquisition Department 12 Analysis Department 13 Output section 16 Store information storage unit 17 Posted information storage unit 20 Submission site server 30 Contributor terminal 31 contributors 40 Viewer Devices 41 viewers 50 Administrator terminal 51 Administrator 60 Text Processing Device P store

Claims

1. An acquisition means for acquiring posted information posted about a predetermined store; a setting means for setting new evaluation items different from the existing evaluation items that have been set in advance when setting evaluation items for a store, and for accepting selection of at least one of the existing evaluation items and the newly set evaluation items; a classification means for acquiring a classification result in which a sentence included in the posted information is classified into the evaluation items selected according to the content of the sentence; An information processing system comprising:

2. 2. The information processing system according to claim 1, the classification means acquires the classification result in which the sentence is classified into an emotion item according to the content of the sentence from among preset emotion items different from the evaluation items, Further, the device further comprises an output means for outputting, for each of the selected evaluation items based on the classification results, aggregate information based on the number of sentences classified into a predetermined emotion item among the sentences classified into the evaluation item. Information processing system.

3. 3. The information processing system according to claim 2, the output means outputs the aggregated information on a radar chart with the selected evaluation items as vertices. Information processing system.

4. 2. The information processing system according to claim 1, The classification means transmits the sentence and information on the selected evaluation items to a sentence processing device generated by machine learning, requests classification processing of the sentence into the evaluation items, and obtains from the sentence processing device the classification result in which the sentence is classified into the evaluation items selected according to the content of the sentence. Information processing system.

5. The information processing device Acquires posted information about a specific store, When setting evaluation items for a store, a new evaluation item different from the existing evaluation items that have been set in advance is set, and a selection of at least one of the existing evaluation items and the newly set evaluation item is accepted; Obtaining a classification result in which the sentences included in the posted information are classified into the evaluation items selected according to the contents of the sentences. Information processing methods.

6. 6. The information processing method according to claim 5, The information processing device, obtaining the classification result in which the sentence is classified into an emotion category according to the content of the sentence from among preset emotion categories different from the evaluation category; outputting, for each of the selected evaluation items based on the classification results, aggregate information based on the number of the sentences classified into a predetermined emotion item among the sentences classified into the evaluation item; Information processing methods.

7. In the information processing device, Acquires posted information about a specific store, When setting evaluation items for a store, a new evaluation item different from the existing evaluation items that have been set in advance is set, and a selection of at least one of the existing evaluation items and the newly set evaluation item is accepted; Obtaining a classification result in which the sentences included in the posted information are classified into the evaluation items selected according to the contents of the sentences. A program that executes a process.

8. 8. The program according to claim 7, The information processing device further includes: obtaining the classification result in which the sentence is classified into an emotion category according to the content of the sentence from among preset emotion categories different from the evaluation category; outputting, for each of the selected evaluation items based on the classification results, aggregate information based on the number of the sentences classified into a predetermined emotion item among the sentences classified into the evaluation item; A program that executes a process.

Images