Information processing system

Abstract

To address such a problem that analysis of posted information is time consuming and difficult to do effectively.SOLUTION: An information processing system 10 includes acquisition means 11 for acquiring posted information posted about a prescribed store, classification means 12 for acquiring a classification result obtained by classifying a text included in the posted information into items corresponding to content of the text out of a plurality of preset items, and output means 13 for outputting information based on the classification result.SELECTED DRAWING: Figure 2

Description

Technical Field

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

Background Art

[0002] In recent years, a plurality of posting sites, which are websites that disclose posting information representing evaluations and usage status by users for stores and products, have been opened on the Internet. On such posting sites, for example, when posting information such as photos of the interior of a store or dishes, articles describing the atmosphere of the store and the impressions of use, etc. are posted by users, such posting information is publicly available for general users to view in a state where it is grouped by store or product. As a result, general users can refer to the posting information and select stores or products.

[0003] Also, on the store side, by collecting posting information from users, it can be used as a reference for store operation. For example, Patent Document 1 discloses a system that acquires and displays in a list posting information from users for a store to be operated from a plurality of posting sites.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] In the above-described situation, on the store side, by analyzing the content of the collected posting information in detail, it can be further used as a reference for store operation. However, since the number of posting information is enormous and its content is also diverse, there arises a problem that it takes time for analysis and it is difficult to perform effective analysis.

[0006] For this reason, an object of the present disclosure is to solve the above-described problems, namely, that the analysis of posted information takes time and effective analysis is difficult.

Means for Solving the Problems

[0007] An information processing system according to one aspect of the present disclosure includes an acquisition unit that acquires posted information posted for a predetermined store, a classification unit that obtains a classification result obtained by classifying the text included in the posted information into the items corresponding to the content of the text among a plurality of preset items, and an output unit that outputs information based on the classification result. It has the following configuration. That is the structure. In addition, an information processing method according to one aspect of the present disclosure is configured such that an information processing apparatus acquires posted information posted for a predetermined store, obtains a classification result obtained by classifying the text included in the posted information into the items corresponding to the content of the text among a plurality of preset items, and outputs information based on the classification result. That is the structure. In addition, a program according to one aspect of the present disclosure acquires posted information posted for a predetermined store, obtains a classification result obtained by classifying the text included in the posted information into the items corresponding to the content of the text among a plurality of preset items, outputs information based on the classification result, and causes a computer to execute the processing. That is the structure.

Advantages of the Invention

[0008] With the present disclosure configured as described above, it is possible to quickly and effectively analyze posted information.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

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

[0011] [Configuration] The information processing system in the present invention is mainly for managing post information posted on a posting site called a so-called word-of-mouth site. As shown in FIG. 1, the information processing system is composed of a management server 10, a plurality of posting site servers 20, a poster terminal 30, a viewer terminal 40, an administrator terminal 50, and an article processing device 60, which are connected via a network N. Hereinafter, each configuration will be described in detail.

[0012] The submission site server 20 is an information processing device managed by an operator that provides a service for publishing submission information, and operates a website such as a submission site on the Internet. In this embodiment, the submission site provided by the submission site server 20 publishes, for example, a page on which information about a store P such as a restaurant is posted, and a page on which submission information from a submitter 31 who is a user who has used such a store P is posted. And the submission information submitted and published by the submitter 31 includes, for example, a photo (captured image) of the interior of the store P (target) or the food, text information (character information) such as impressions regarding the service or food received at the store P, and further, numerical evaluation information representing an evaluation of the store P.

[0013] At this time, the evaluation information is a numerical evaluation value representing the degree of evaluation of the store by the user. As an example, the evaluation value is set to a value of "0 to 5", and the higher the numerical value, the higher the evaluation. However, the evaluation value may be represented by a value in any range, and may be represented not only by a numerical value but also by any information. Further, the evaluation information includes time information. For example, the time information is information representing time such as the year, month, and day when the user used the store, or the year, month, and day when the evaluation information was submitted by the user. And the time information is included in the evaluation information, for example, by being input together with the evaluation information at the time of submission by the user, or being assigned when the evaluation information is submitted by the submission site server 20.

[0014] As an example of the submission site provided by the submission site server 20, there is Google (registered trademark) Business Profile. However, the submission site provided by the submission site server 20 may be any submission site such as a search site, a reservation site, a review site, a questionnaire site, a weblog, an SNS (Social Networking Service) site. As an example of an SNS site, there is Instagram (registered trademark).

[0015] In addition, in this embodiment, there are a plurality of posting site servers 20, each of which operates a different posting site. For this reason, posting information regarding the same store P is posted and publicly available on each posting site operated by each posting site server 20.

[0016] Also, the posting site server 20 is not necessarily limited to publicly posting posting information on a website or the like. For example, the posting site server 20 may simply operate a questionnaire site or a payment site, and acquire and store the above-described posting information from users.

[0017] Note that the posting information handled on the posting site provided by the posting site server 20 is not limited to information regarding a store P such as a restaurant, and may be information regarding stores of any business type, or may be posting information regarding products and services (targets). Furthermore, the posting information is not limited to information regarding stores or products, and may be information regarding any target. Also, the posting site server 20 is not necessarily limited to publicly posting posting information separately for each target such as for each store or each product, and may publicly post the posting information without distinguishing targets. For example, the posting information may be publicly posted separately for each poster 31.

[0018] The poster terminal 30 (user terminal) is an information processing terminal such as a smartphone or a notebook personal computer operated by a poster 31 who is a user who has used a target such as a store P. Then, when the poster 31 operates the poster terminal 30, it has a function of accessing a posting site on the Internet and posting posting information to such a posting site. For example, the poster terminal 30 posts, as posting information, a photo of the inside of the store P taken by the poster 31 or a photo of the food provided at the store P, or posts, as posting information, evaluation information obtained by the poster 31 evaluating the store P with numerical values in multiple levels or impressions expressed in text as text information.

[0019] Note that the contributor terminal 30 may directly access the submission site, or may be guided from an access destination based on address information such as a QR code installed in the store P to access the submission site. Further, when the access destination of the address information such as the QR code installed in the store P is the questionnaire site of the store P, the contributor terminal 30 also has a function of transmitting an answer to the questionnaire presented on such a questionnaire site.

[0020] The viewer terminal 40 is an information processing terminal such as a smartphone or a notebook computer operated by the viewer 41. Then, when the viewer 41 operates, the viewer terminal 40 has a function of accessing a submission site on the Internet and viewing the submission information published on such a submission site. For example, the viewer terminal 40 can view a photo inside the store P submitted by the contributor 31, a photo of the food provided in the store P, evaluation information obtained by evaluating the store P with numerical values in multiple stages, and text information expressing impressions in text.

[0021] The administrator terminal 50 is an information processing terminal operated by the administrator 51 who manages the submission information of the store in the business operator who operates the store. Then, the administrator terminal 50 accesses the management server 10, displays and monitors the submission information of the store obtained by the management server 10 as described later, analyzes the submission information, and manages the submission information for the store. In particular, as will be described later, the administrator terminal 50 obtains a classification result classified into preset items according to the content of the text information (divided text information) of the submission information, displays such a classification result, and analyzes the submission information. Further, the administrator terminal 50 generates a reply text for the submission information via the management server 10 and posts it to the submission site server 20. In addition, the administrator terminal 50 manages information such as questionnaires regarding the store obtained by the management server 10. Furthermore, the administrator terminal 50 can also post information about the store to each submission site via the management server 10. Note that the number of stores for which the administrator 51 manages the submission information is not limited to one, and may be plural.

[0022] Here, in this embodiment, it is assumed that the operator who operates store P operates a plurality of stores P. For example, it is assumed that the operator operates 50 stores, monitors and analyzes the posted information for these stores, and further posts a reply text for the posted information. However, the operator who operates store P may only operate one store, and may also monitor and analyze the posted information of a plurality of stores including its own store and the stores of other operators.

[0023] The text processing device 60 (text processing device) is connected to the management server 10 via the network N, and is an information processing device managed by an operator that provides services such as performing the requested processing on the input text information and outputting the processing result to the management server 10. As an example, the text processing device 60 is realized by an artificial intelligence chatbot such as ChatGPT provided by OpenAI, Inc. in the United States or VertexAI provided by Google LCC in the United States.

[0024] In this embodiment, the text processing device 60 implements a text segmentation processing model generated by machine learning. The text segmentation processing model is generated by performing machine learning on learning data composed 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 such text information into segmented text information consisting of character strings of a shorter length in response to a request for text information segmentation processing. However, the text processing device 60 may segment the text information into a plurality of segmented text information by any method without using the text segmentation processing model. For example, the text processing device 60 may generate segmented text information by morphological analysis of the character strings in the text information according to the order and concatenation status of the morphemes, or may also generate literary text information by segmenting the text information at punctuation marks or paragraphs within the text information.

[0025] In addition, in the present embodiment, the document processing apparatus 60 implements a document classification processing model generated by machine learning. The document segmentation processing model is generated by performing machine learning on learning data consisting of a combination of pre-prepared document information (segmented document information) and items corresponding to the content of the document information (segmented document information). As a result, the document classification processing model is configured to perform a process of classifying document information into an item corresponding to the content of the document information among a plurality of preset items in response to a request for classification processing of the document information. In the present embodiment, the document classification processing model is configured to classify each piece of segmented document information segmented from the document information by the document segmentation processing model as described above into an item corresponding to the content of the segmented document information.

[0026] Here, it is assumed that in the document classification processing model, four contents, namely, "quality", "customer service", "cleanliness", and "atmosphere", are set as items to be classified. The item "quality" is the quality (Quality (Q)) in the store, and represents, for example, the quality of products (e.g., dishes) provided in the store, the menu, the price, and other contents related to quality. The item "customer service" is the service (Service (S)) in the store, and represents, for example, the customer service and consideration for customers in the store and other contents related to service. The item "cleanliness" is the hygiene condition (Cleanliness (C)) in the store, and represents, for example, the cleanliness in the store, the cleaning situation, the handling of products, and other contents related to hygiene. The item "atmosphere" is the atmosphere (Atmosphere (A)) in the store, and represents, for example, the appearance, interior, and employee uniforms in accordance with the store concept and other contents related to the environment. Then, the document classification processing model analyzes the content of the above-described segmented document information and classifies it into the items "quality", "customer service", "cleanliness", and "atmosphere" corresponding to such content.

[0027] In addition, in the text classification processing model of this embodiment, it is further assumed that in addition to the above four items, items of "affirmative" and "negative" contents are set. That is, the text classification processing model classifies the segmented text information into the items of "affirmative" and "negative" according to the content of the text. Therefore, the text classification processing model classifies one piece of segmented text information into any one of the four items of "quality", "customer service", "cleanliness", and "atmosphere", and further classifies it into any one of the two items of "affirmative" and "negative". Here, "affirmative" represents content that is affirmative towards the store, and "negative" represents content that is negative towards the store. Then, the text classification processing model analyzes the content of the above-mentioned segmented text information and classifies it into "affirmative" and "negative", which are the items corresponding to such content.

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

[0029] Also, in the present embodiment, the document processing apparatus 60 implements a program generation model generated by machine learning. The learning data, which is composed of a combination of pre-prepared document information (segmented document information) and items, and program data of the content associated therewith, is generated by performing machine learning. As a result, the program generation model is configured to perform a process of generating program data associating the document information with the item obtained by classifying the document information, in response to a request for program generation processing of the document information, as described above. In the present embodiment, the program generation model performs a process of generating program data associating the segmented document information segmented from the document information by the document segmentation processing model as described above with the item obtained by classifying the segmented document information. As an example, as shown in FIG. 3 described later, the program generation model generates program data associating the segmented document information with the classified items (one of "quality", "customer service", "cleanliness", "atmosphere" and one of "positive", "negative") in a program language in JSON (JavaScript Object Notation) format. However, the format of the program generated by the program generation model may be in any format or language.

[0030] However, the document processing apparatus 60 may generate program data by any method without using the program generation model. For example, the document processing apparatus 60 may have a rule for converting the associated segmented document data and items into program data set, or a template of program data set, and convert the associated segmented document data and items into program data using such rules and templates.

[0031] The management server 10 is composed of one or more information processing devices including an arithmetic unit 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. Each function of the acquisition unit 11, the analysis unit 12, and the output unit 13 can be realized by the arithmetic unit executing a program for realizing each function stored in the storage device. Further, the management server 10 includes a store information storage unit 16 and a posting information storage unit 17. The store information storage unit 16 and the posting information storage unit 17 are constituted by the storage device. Each configuration will be described in detail below.

[0032] First, the store information storage unit 16 stores information of store P input from the administrator terminal 50 of the operator who operates store P. At this time, when the operator operates a plurality of stores P, information of each of the plurality of stores P is registered.

[0033] The information of the store to be registered includes the store name, store address, store attribute, information of the posting site server 20 to which posting information for the store is posted, and the like. The store name functions as identification information for identifying the store. The store address represents the location of the store. For example, the location can be specified by prefecture or region, and it also functions as an attribute of the store. The store attribute is information such as the location of the store (roadside, downtown, tourist destination, suburb, commercial facility, etc.), the presence or absence of a parking lot, the person in charge of the store on the operator side, the franchise of the store, the brand of the store, and the like. The information of the posting site server 20 to which the posting information of the store is posted is information for identifying the posting site or information for obtaining the posting information posted to the posting site server 20 from the posting site server 20. For example, it is information for specifying the posting site server 20 and the store, and as an example, it is the address information of the posting site where the posting information for the store is publicly available.

[0034] Further, in the store information storage unit 16, for example, a plurality of stores operated by the same operator or operators forming a group are associated to form a store group and registered.

[0035] The acquisition unit 11 (acquisition means) accesses each posting site server 20 based on the information of the stores registered as described above, acquires the posting information publicly available on each posting site, and stores it in the posting information storage unit 17. At this time, the acquisition unit 11 acquires the posting information related to each store from each posting site server 20 separately by distinguishing for each store and each store group, and stores it in the posting information storage unit 17 by associating the store information and the posting site information. That is, the acquired posting information will be associated with the information of the corresponding store and the information of the posting site where the posting was made. Note that the acquisition unit 11 may acquire posting information from any posting site such as a search site, a reservation site, a review site, a questionnaire site, a weblog, an SNS site, etc. as described above.

[0036] The analysis unit 12 (classification means) requests the text processing device 60 to perform analysis processing on the text information included in the posting information acquired as described above. Specifically, the analysis unit 12 transmits the text information included in the posting information to the text processing device 60 and requests the text information splitting process, classification process, and program generation process. In response to this, in the text processing device 60, as described above, first, the text information is split into split text information using the text splitting processing model, and each split text information is classified into items according to the content of the split text information using the text classification processing model. Further, in the text processing device 60, program data associating the split text information and the items into which the split text information is classified is generated using the program generation model. Then, the analysis unit 12 acquires the program data generated by the text processing device 60. That is, the analysis unit 12 acquires the classification result in which each split text information obtained by splitting the text information included in the posting information is classified into preset items, and also acquires the program data associating the split text information and the items that are the classification result.

[0037] Note that the analysis unit 12 may sequentially obtain the above-described processing results from the document processing device 60, or may sequentially issue the above-described processing requests to the document processing device 60. That is, the analysis unit 12 may first issue a document information splitting processing request to obtain split document information, and then issue a classification processing request for the split document information to obtain a classification result, and further issue a program generation request to obtain program data.

[0038] Here, with reference to FIG. 3, an example of the document information included in the posting information for which the analysis unit 12 requests analysis processing from the document processing device 60 and the analysis processing by the document processing device 60 will be described. First, assume that the document information included in the posting information is as shown by reference numeral D1 in FIG. 3 and has the content "You can eat delicious grilled meat for 1,000 yen! The clerk is a bit unfriendly and scary, but be careful not to slip because the floor is slippery. It has a calm atmosphere and is comfortable." The document processing device 60 splits the document information shown by reference numeral D1 in FIG. 3 into the split document information shown in each row of reference numeral D2 in FIG. 3, and further classifies it into the items shown at the left end of each row according to the content of the split document information. For example, regarding the split document information "You can eat delicious grilled meat for 1,000 yen!" shown in the first row of reference numeral D2 in FIG. 3, it is classified into the item "Quality (Q)" and the item "Positive (Pos)" according to its content. Also, regarding the split document information "The clerk is a bit unfriendly and scary" shown in the second row, it is classified into the item "Customer service (S)" and the item "Negative (Neg)" according to its content. Also, regarding the split document information "Be careful not to slip because the floor is slippery." shown in the third row, it is classified into the item "Cleanliness (C)" and the item "Positive (Pos)" according to its content. Also, regarding the split document information "It has a calm atmosphere and is comfortable." shown in the fourth row, it is classified into the item "Atmosphere (A)" and the item "Positive (Pos)" according to its content.

[0039] Then, as shown by reference numeral D3 in FIG. 3, the document processing apparatus 60 further generates program data associating the segmented document information shown by reference numeral D2 in FIG. 3 with the classified items. For example, the segmented document information “Delicious grilled meat can be eaten for 1000 yen!” shown in the first line of reference numeral D2 in FIG. 3 is associated with the item “Quality (Q)” and the item “Positive (Pos)” to generate program data like the first paragraph of reference numeral D3 in FIG. 3. In the program data, the segmented document information is indicated by “character information” following “sentence”, and the items are indicated by “quality” (quality), “service” (customer service), “cleanliness” (cleanliness), or “Atmosphere” (atmosphere) following “category”. Further, another item is indicated by “positive” (positive) or “negative” (negative) following “sentiment”.

[0040] Note that the analysis unit 12 acquires the program data shown by reference numeral D3 in FIG. 3 from the document processing apparatus 60, but may also acquire each segmented document information obtained by dividing the document information as shown by reference numeral D2, and information associating the segmented document information with the items that are the classification results.

[0041] Also, the analysis unit 12 requests the document processing apparatus 60 to perform the analysis process of the document information and acquires the processing result by the document processing apparatus 60, but the analysis unit 12 itself may perform the above-described analysis process of the document information. For example, the analysis unit 12 is equipped with each model provided in the above-described document processing apparatus 60, and may perform the above-described segmentation process, classification process, and program generation process using such a model. Alternatively, the analysis unit 12 may perform segmentation of the document information, classification of the segmented document information, and generation of program data according to the content of the document information. For example, the analysis unit 12 may generate segmented document information according to the result of morphological analysis of the document information, may classify it into items according to the keywords included in the segmented document information, and may generate a program for associating the segmented document information with the classified items using a template.

[0042] The output unit 13 outputs the posted information for a specific store acquired from the posting site server 20 as described above so as to be displayed on the administrator terminal 50. At this time, when there are a plurality of posted information corresponding to a specific store respectively acquired from a plurality of posting site servers 20, the output unit 13 outputs so as to collectively display these plurality of posted information in a list. Further, when a plurality of specific stores are associated as described above to form and register a store group, the output unit 13 outputs so as to collectively display in a list the posted information corresponding to each of the plurality of specific stores. Note that the output unit 13 associates and displays information such as the store name that identifies the store to which such posted information was posted, information such as the posting site name that identifies the posting site, and further information of the poster in the posted information.

[0043] For example, as shown in FIG. 4, the output unit 13 outputs so as to display a list of evaluation information and text information among the posted information on the administrator terminal 50. The example of FIG. 4 is a case where "Store AAA" and "Store BBB" are associated as group stores, and the output unit 13 lists the evaluation information and text information as posted information posted to a plurality of posting sites such as "Posting Site A" and "Posting Site B" for each of these plurality of stores. In FIG. 4, the "star mark" is evaluation information, and the evaluation value is quantified by the number, and the larger the number, the higher the evaluation of the store. Also, in FIG. 4, the output unit 13 displays text information such as impressions of the store included in the evaluation information, but when the posted information includes captured images such as photos, the output unit 13 may output so as to display a list of the captured images.

[0044] Then, when displaying the above-described posted information, the output unit 13 outputs to display information according to the processing result acquired from the document processing device 60. Specifically, the output unit 13 outputs to display the segmented sentence information and the item into which the segmented sentence information is classified in association with each other. As an example, as shown in FIG. 4, the output unit 13 displays in association the segmented sentence information "Delicious grilled meat can be eaten for 1000 yen!" with the item "Quality (Q)" and the item "Positive (Posi)", and also displays in association the segmented sentence information "Although the clerk is a bit unfriendly and scary" with the item "Customer service (S)" and the item "Negative (Neg)". At this time, by using the program data acquired from the document processing device 60, the output unit 13 can easily display the segmented sentence information and the item into which the segmented sentence information is classified in association with each other.

[0045] Further, the output unit 13 may output to display, on the administrator terminal 50, information regarding the item obtained by classifying the segmented sentence information acquired as described above, for each store or for each attribute set for the store. At this time, the output unit 13 totals the items obtained by classifying the segmented sentence information for the store for each store or for each attribute set for the store, and outputs to display information based on the total result. For example, as shown in FIG. 5, the output unit 13 totals, for each store, the number of segmented sentence information for the store and the number for each item obtained by classifying the segmented sentence information, calculates the ratio of the number for each item to the number of all segmented sentence information, and may display the ratio for each such item. As an example, in FIG. 5, the total result of "AAA Store" is displayed in the second row, but a radar chart with the four items "Quality", "Customer service", "Cleanliness", and "Atmosphere" as vertices is displayed, and the ratio of the number of segmented sentence information classified into each item calculated on the radar chart is displayed, and the numerical value of such ratio is also displayed. In particular, in this example, the ratio of the number of segmented sentence information classified into the item "Positive (Posi)" among those classified into each item "Quality", "Customer service", "Cleanliness", and "Atmosphere" is displayed. Note that the total result of "All stores" is displayed in the first row of FIG. 5, whereby a comparison with the average value can be made.

[0046] Also, in FIG. 6, for each attribute of the stores, the number of divided sentence information for all stores belonging to the corresponding attribute and the number for each item into which the divided sentence information is classified are aggregated, and the ratio of the number for each item to the number of all divided sentence information is calculated, and an example of displaying the ratio for each such item is shown. As an example, FIG. 6 shows an example aggregated for each store attribute of "brand", and the second row shows the aggregation result for 10 stores belonging to "Brand AA". In particular, in this example, among those classified into each item of "quality", "customer service", "cleanliness", and "atmosphere", the ratio of the number of divided sentence information classified into the item "positive" is shown. Note that the first row of FIG. 6 shows the aggregation result of "all stores", and thus, comparison with the average value can be made. Note that the aggregation can be performed for any store attribute such as "region (prefecture)" and "location" of the store, and the aggregation result can be displayed.

[0047] Note that in the above, the output unit 13 has been exemplified as a case of displaying the ratio of the number for each item to the number of all divided sentence information in a graph, but simply the number for each item into which the divided sentence information is classified may be displayed in a graph. For example, the output unit 13 may display, for each store or each store attribute, the number classified into the items of "quality", "customer service", "cleanliness", "atmosphere", and the number classified into the items of "positive" and "negative" in a graph or numerically. Also, the output unit 13 may display any information in any display form as long as it is information based on the number for each item into which the divided sentence information is classified.

[0048] [Operation] Next, the operation of the above-described information processing system, particularly the operation of the management server 10, will be mainly described with reference to the flowchart of FIG. 7.

[0049] First, on a plurality of posting site servers 20, posting information regarding store P has been posted from a poster 31 to each posting site and made publicly available, and can be viewed from a viewer terminal 40 of a viewer 41.

[0050] The management server 10 periodically or at any arbitrary timing acquires posting information published on each posting site from a plurality of posting site servers 20 (step S1). Then, the management server 10 stores the posting information acquired from the plurality of posting site servers 20 for each store or for each store group.

[0051] Then, the management server 10 requests the text processing device 60 to perform analysis processing on the text information included in the acquired posting information (step S2). Specifically, the management server 10 transmits the text information included in the posting information to the text processing device 60 and requests text information splitting processing, classification processing, and program generation processing. In response, in the text processing device 60, as shown in FIG. 3, the text information is split into split text information, each split text information is classified into items according to the content of the split text information, and further, program data associating the split text information and the items into which the split text information is classified is generated. Then, the management server 10 acquires the analysis result by the text processing device 60, that is, the split text information and the classification result and program data for the items as shown in FIG. 3 (step S3).

[0052] Subsequently, the management server 10 outputs the posting information so as to be displayed on the administrator terminal 50. At this time, the management server 10 outputs the analysis result of the text information included in the posting information so as to be displayed (step S4). For example, as shown in FIG. 4, when the management server 10 displays a list of the text information of the posting information, it outputs to display the split text information obtained by splitting the text information and to display the items into which each split text information is classified in association. Further, as shown in FIGS. 5 and 6, the management server 10 may aggregate the items obtained by classifying the split text information for the store for each store or for each attribute set for the store and output to display information based on the aggregation result. As an example, for each store or for each attribute of the store, a radar chart with the four items of "quality", "customer service", "cleanliness", and "atmosphere" as vertices may be displayed, and the ratio of the number of split text information classified into each calculated item may be displayed on such a radar chart.

[0053] As described above, in the information processing system according to the present embodiment, the text included in the posted information is divided, the classification result of classifying each divided text into items according to the content is obtained, and the information based on such classification result is output. For example, the division process and the classification process can be performed using a model generated by machine learning. Thereby, in the present embodiment, even if the number of posted information is enormous and its content is various, it is possible to shorten the time required for analysis and perform effective analysis.

[0054] Note that, in the above, the case where the text information included in the posted information is divided into divided text information and classified into items for each divided text information is exemplified, but the text information may be classified into items without dividing the text information.

[0055] As described above, the present invention has been described with reference to the above-described embodiments and the like. However, the present invention is not limited to the above-described embodiments. Various changes 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. Further, at least one or more of the functions of the management server 10 described above may be executed by an information processing apparatus installed and connected at any location on the network, that is, may be executed by so-called cloud computing.

[0056] Incidentally, the above-described program can be stored using various types of non-transitory computer readable media and supplied to a computer. 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-ROM (Read Only Memory), CD-R, CD-R / W, semiconductor memories (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). Also, the program may 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. Transitory computer readable media can supply the program to a computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

[0057] <Supplementary Note> Some or all of the above embodiments may also be described as follows. Hereinafter, an outline of the configuration of the information processing system, information processing method, and program in the present invention will be described. However, the present invention is not limited to the following configurations. (Supplementary Note 1) An acquisition means for acquiring posted information posted for a predetermined store, A classification means for obtaining a classification result obtained by classifying the text included in the posted information into the item corresponding to the content of the text among a plurality of preset items, An output means for outputting information based on the classification result, and an information processing system. (Supplementary Note 2) The information processing system according to Supplementary Note 1, The classification means obtains the classification result of classifying each segmented sentence obtained by segmenting the sentence into the items according to the content of each segmented sentence. The output means outputs information based on the classification result for each segmented sentence. An information processing system. (Appendix 3) The information processing system according to Appendix 2, wherein the classification means transmits the sentence to a sentence processing device, requests segmentation processing of the sentence and classification processing for each segmented sentence, and obtains the classification result for each segmented sentence by the segmentation processing and classification processing of the sentence performed by the sentence processing device. An information processing system. (Appendix 4) The information processing system according to Appendix 2, wherein the output means outputs so as to display in association the segmented sentence and the item into which the segmented sentence is classified. An information processing system. (Appendix 5) The information processing system according to Appendix 2, wherein the classification means obtains program data in which the segmented sentence and the item into which the segmented sentence is classified are associated. the output means outputs so as to display in association the associated segmented sentence and item on a display device based on the program data. An information processing system. (Appendix 6) The information processing system according to Appendix 2, wherein the classification means obtains the classification result of classifying each segmented sentence into the item according to the content of the segmented sentence among the items in which quality, customer service, cleanliness, and atmosphere in the store are set. An information processing system. (Appendix 7) The information processing system according to Appendix 6, wherein the classification means further obtains the classification result of classifying each segmented sentence into the item according to the content of the segmented sentence among the items in which affirmation and negation are set. Information processing system. (Appendix 7) The information processing system according to Appendix 6, wherein the output means outputs information based on the number for each item obtained by classifying each of the segmented sentences of the text included in the contribution information for the store, for each store. Information processing system. (Appendix 9) The information processing system according to Appendix 6, wherein the output means outputs information based on the number for each item obtained by classifying each of the segmented sentences of the text included in the contribution information for the store belonging to the attribute, for each attribute set for the store. Information processing system. (Appendix 10) An information processing apparatus acquires contribution information posted for a predetermined store, obtains a classification result obtained by classifying the text included in the contribution information into the items corresponding to the content of the text among a plurality of preset items, and outputs information based on the classification result. Information processing method. (Appendix 11) acquires contribution information posted for a predetermined store, obtains a classification result obtained by classifying the text included in the contribution information into the items corresponding to the content of the text among a plurality of preset items, and outputs information based on the classification result. A program for causing a computer to execute the processing.

Explanation of Signs

[0058] 10 Management server 11 Acquisition unit 12 Analysis unit 13 Output unit 16 Store information storage unit 17 Contribution information storage unit 20 Contribution site server 30 Contributor terminal 31 Contributor 40 Viewer terminal 41 Viewer 50 Administrator terminal 51 Administrator 60 Document processing device P Store

Claims

1. An acquisition means for acquiring posted information posted for a specified store; A classification means for obtaining a classification result obtained by classifying the text included in the posted information into the items corresponding to the content of the text among a plurality of preset items; An output means for outputting information based on the classification result; An information processing system comprising: the above.

2. The information processing system according to Claim 1, wherein the classification means obtains a classification result obtained by classifying each divided text obtained by dividing the text into the items corresponding to the content of each divided text, the output means outputs information based on the classification result for each divided text, An information processing system.

3. The information processing system according to Claim 2, wherein the classification means transmits the text to a text processing device, requests a division process of the text and a classification process for each divided text, and obtains the classification result for each divided text by the division process and classification process of the text performed by the text processing device, An information processing system.

4. The information processing system according to Claim 2, wherein the output means outputs so as to display in association the divided text and the item into which the divided text is classified, An information processing system.

5. The information processing system according to Claim 2, wherein the classification means obtains program data associating the divided text and the item into which the divided text is classified, the output means outputs so as to display in association the associated divided text and item on a display device based on the program data, An information processing system.

6. The information processing system according to Claim 2, wherein the classification means obtains a classification result obtained by classifying each divided text into the items corresponding to the content of each divided text among the items in which quality, customer service, cleanliness, and atmosphere in the store are set, An information processing system.

7. The information processing system according to Claim 6, wherein the classification means further obtains a classification result obtained by classifying each divided text into the items corresponding to the content of each divided text among the items in which affirmation and negation are set, An information processing system.

8. The information processing system according to Claim 6, wherein the output means outputs information based on the number of each item obtained by classifying each divided text of the text included in the posted information for the store for each store, An information processing system.

9. An information processing system according to claim 6, wherein the output means outputs information based on the number for each item obtained by classifying each of the segmented sentences of the text included in the posted information for the stores belonging to the attribute, for each attribute set for the stores. Information processing system.

10. An information processing apparatus acquires posted information posted for a predetermined store, obtains a classification result obtained by classifying a text included in the posted information into an item corresponding to the content of the text among a plurality of preset items, and outputs information based on the classification result. Information processing method.

11. acquires posted information posted for a predetermined store, obtains a classification result obtained by classifying a text included in the posted information into an item corresponding to the content of the text among a plurality of preset items, and outputs information based on the classification result. A program causing a computer to execute the processing.

Images