Customer experience value analysis device and customer experience value analysis method

Abstract

To provide a customer experience value analysis device capable of grasping how much an emotional value experienced by a customer is changed before and after an event.SOLUTION: The CX analysis device 10 includes a data acquisition unit 101 that acquires text data including information on a specific facility based on social media information posted on a social media platform, an emotion analysis unit 102 that analyzes an emotion of a poster who has posted the social media information based on a predefined emotional score based on the text data, a CX analysis unit 103 that analyzes a customer experience value based on an analysis result of the emotion, and a processed data display unit 104 that outputs a calculation result of a customer experience value analysis score calculated based on an analysis result of the customer experience value.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a customer experience value analysis device and a customer experience value analysis method. [Background technology]

[0002] Conventionally, various commercial facilities have held events aimed at attracting customers and raising awareness as a measure to increase the value received by customers who visit the facility. Event organizers have confirmed how many people attended the facility by counting the number of customers who participated in the event. Event organizers have also confirmed changes in customers' purchasing motivation by counting changes in sales before and after the event. Furthermore, event organizers have distributed and collected questionnaires at the end of the event to understand customer satisfaction, interests, etc., and thereby infer how customer value received has changed.

[0003] However, all of the above methods require manual intervention, making compilation time-consuming. Furthermore, since survey responses are based on pre-prepared question items, it is difficult to obtain responses that do not fall within the pre-prepared items. Even if free responses were provided, determining whether customers were satisfied based on the responses required the knowledge and experience of the event organizer. For this reason, some event organizers may over- or under-rate their events, making it difficult to obtain objective indicators.

[0004] In recent years, social media information, including customer impressions of commercial facilities, is often posted on microblogs and other social media platforms using SNS (Social Networking Service). As a result, there is a need from commercial facility operators to analyze their facilities using social media information, and the use of social media information to obtain objective indicators for events has been considered.

[0005] For example, a technology for accurately detecting information about an event from among various pieces of information posted when that event occurs is described in Patent Document 1. Patent Document 1 describes the following: "The information is divided into multiple segments using attribute information, the emotional tendencies contained in the information are analyzed, the information is classified based on the analysis results, a quantitative evaluation value is calculated based on the analysis results and classification results of the information contained in the segments, the segments are mapped to the quantitative evaluation value, some of the segments are selected based on the quantitative evaluation value, the features of the segments are extracted, and the selected segments and their features are output." [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-257677 Summary of the Invention [Problem to be solved by the invention]

[0007] Generally, if a customer has neither a bad nor a good experience with a product or service provided by a manufacturer or facility, it is considered that the customer has only received reasonable value from the product or service, such as its function, performance, or price. However, reasonable value is easily commoditized, and it is difficult to distinguish a manufacturer or facility that provides a product or service from other commercial facilities using that alone.

[0008] For this reason, in recent years, an indicator called Customer Experience (CX) has come into use, which indicates the emotional value of the customer experience. CX allows for an objective view of the value that a product or service itself provides to customers. By adding experiential value to the rational value mentioned above, the overall value received by the customer increases.

[0009] Therefore, it is expected that emotional value will increase if manufacturers or facilities highlight the characteristics of the products or services they offer and differentiate them from other companies. Applying this to the events mentioned above, it is thought that customer experience value can be increased by making the event distinctive or by making the event held by one company more attractive than events held by other companies.

[0010] However, despite the fact that customers who participate in an event or use a product have a variety of emotions, conventional methods have not been able to grasp which emotions an event appealed to.As a result, it has not been possible to grasp the level of customer experience value that the event provided, or how much emotional value changed before and after the event.

[0011] The technology disclosed in Patent Document 1 does not grasp the emotional value described above. Therefore, even if the technology disclosed in Patent Document 1 is used, it is not possible to grasp the extent to which the customer experience value has changed before and after the event.

[0012] The present invention has been made in view of the above circumstances, and aims to make it possible to objectively grasp customer experience value. [Means for solving the problem]

[0013] The customer experience value analysis device of the present invention includes a data acquisition unit that acquires text data including information about a specific facility based on social media information posted on a social media platform, a sentiment analysis unit that analyzes the sentiment of the poster who posted the social media information based on the text data and a predefined sentiment score, a customer experience value analysis unit that analyzes customer experience value based on the sentiment analysis results, and an output unit that outputs the calculation result of a customer experience value analysis score calculated based on the customer experience value analysis results. [Effects of the Invention]

[0014] According to the present invention, it is possible to objectively grasp customer experience value using the customer experience value analysis score. Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief explanation of the drawings]

[0015] [Figure 1] FIG. 1 is a block diagram showing an example of the functional configuration of a CX analyzer according to an embodiment of the present invention. [Figure 2] FIG. 1 is a block diagram showing an example of the hardware configuration of a CX analyzer according to an embodiment of the present invention. [Figure 3] FIG. 1 is a diagram illustrating an example of text according to an embodiment of the present invention. [Figure 4] FIG. 10 is a diagram illustrating an example of a customer experience index according to an embodiment of the present invention. [Figure 5] 10 is a flowchart illustrating an example of an operation of a data acquisition unit according to an embodiment of the present invention. [Figure 6] 10 is a flowchart illustrating an example of the operation of a sentiment analysis unit and a CX analysis unit according to an embodiment of the present invention. [Figure 7] 10 is a flowchart illustrating an example of a CX analysis process according to an embodiment of the present invention. [Figure 8] 10 is a flowchart illustrating an example of a CX determination process according to an embodiment of the present invention. [Figure 9] FIG. 10 is a diagram showing a classification result of a customer experience value index according to an embodiment of the present invention. [Figure 10] FIG. 2 is a diagram showing an example of processed data that is a processing result of a CX analysis unit according to one embodiment of the present invention. [Figure 11] 10 is a flowchart illustrating an example of an operation of a processed data display unit according to an embodiment of the present invention. [Figure 12] FIG. 1 illustrates an example of a dashboard according to an embodiment of the present invention. [Figure 13]FIG. 10 is a diagram illustrating another example of a radar chart displayed on a dashboard according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functions or configurations are designated by the same reference numerals, and redundant description will be omitted.

[0017] [One embodiment] FIG. 1 is a block diagram showing an example of the functional configuration of a CX analyzer 10. As shown in FIG.

[0018] The CX analysis device 10 includes a data acquisition unit 101, a sentiment analysis unit 102, a CX analysis unit 103, a processed data display unit 104, and an information storage unit 105. The information storage unit 105 also includes a media data storage unit 111, a sentiment analysis data storage unit 112, a CX analysis data storage unit 113, and an other data storage unit 114.

[0019] Each unit of the CX analyzer 10 is realized using the hardware configuration shown in Fig. 2. For example, at least one of the units of the CX analyzer 10 may be realized by the processor 11 reading and executing a program stored in the main storage device 12 or the auxiliary storage device 13. Also, at least one of the units of the CX analyzer 10 may be realized using hardware such as an ASIC (Application Specific Integrated Circuit).

[0020] The CX analyzer 10 is also connected to an external media device 20 so that they can communicate with each other. The external media device 20 is, for example, a storage device that stores a collection of text data, and is usually provided separately from the CX analyzer 10. In this embodiment, the external media device 20 stores media data (an example of social media information) posted to social media such as microblogs as text data.

[0021] The CX analyzer 10 may also include a text uploader 30. The text uploader 30 is a terminal device or the like, and is a device that uploads text data to the CX analyzer 10.

[0022] The data acquisition unit 101 is an example of a data acquisition unit that acquires text data including information about a specific facility based on social media information posted on a social media platform. Specifically, the data acquisition unit 101 transmits a query 201 to the external media device 20. The query 201 is a search query that defines extraction conditions for extracting media data from the external media device 20. The data acquisition unit 101 then acquires media data 202 that matches the extraction conditions of the query 201 from the external media device 20.

[0023] The query 201 is a query statement that the data acquisition unit 101 sends to the external media device 20 to acquire media data 202. The query 201 indicates, for example, a search keyword as an extraction condition. For example, the search keyword may be "Commercial facility name XXX." In this case, the external media device 20 returns media data containing the search keyword to the data acquisition unit 101 as media data 202. Note that the media data 202 is provided with metadata indicating the date and time the media data 202 was created, the creator, the source of the media data 202, and the like.

[0024] The data acquisition unit 101 may acquire text 203, which is text data uploaded from the text uploader 30. In this embodiment, the text 203 is a CSV (Comma Separated Values) file, but is not limited to a CSV file. The data acquisition unit 101 compiles the acquired media data 202 and text 203 as acquired data 204 and stores it in the media data storage unit 111 of the information storage unit 105.

[0025] The information storage unit 105 stores information on the type of event and emotions in addition to media data. The information storage unit 105 includes a media data storage unit 111, an emotion analysis data storage unit 112, a CX analysis data storage unit 113, and an other data storage unit 114.

[0026] The emotion analysis unit 102 analyzes the emotion of a poster who posted social media information based on text data and a predefined emotion score. To this end, the emotion analysis unit 102 acquires, as text 205, text data stored as acquired data 204 in the media data storage unit 111. The emotion analysis unit 102 executes emotion analysis processing to evaluate the emotion appearing in the text 205, i.e., the emotion of the creator of the text 205. The emotion analysis unit 102 then associates emotion-attached information, which is the result of the emotion analysis processing, with the text 205 to generate processed data 206, which is stored in the emotion analysis data storage unit 112 of the information storage unit 105. The creator is, for example, a poster who posted text data to social media. In this embodiment, the emotion-attached information includes an emotion score that quantifies the emotion of the creator.

[0027] The CX analysis unit 103 is an example of a customer experience value analysis unit that analyzes customer experience value based on the emotion analysis results by the emotion analysis unit 102. For this purpose, the CX analysis unit 103 acquires processed data 206 stored in the emotion analysis data storage unit 112 as text 207. The text 207 is an example of text data read from the emotion analysis data storage unit 112. Thereafter, the CX analysis unit 103 executes a CX analysis process that analyzes the text 207 based on a customer experience value index that indicates the type of emotional value due to the customer's experience. After the CX analysis process, the CX analysis unit 103 stores processed data 208, in which the processing results of the CX analysis process are associated with the text 207, in the CX analysis data storage unit 113 of the information storage unit 105.

[0028] The CX analysis process is performed based on customer experience value indicators 209, which are data that define indicators related to customer experience value. Here, customer experience value indicators are types of emotional value organized by Bernd H. Schmidt, author of "Customer Experience Management." Emotional value is classified into five types: "Sense (sensory)," "Feel (emotional)," "Think (intellectual)," "Act (behavioral, lifestyle)," and "Relate (social)." The CX analysis unit 103 classifies customer experience value words based on Bernd H. Schmidt's five classifications of emotional value.

[0029] The customer experience index 209 may be set inside the CX analysis device 10 from outside the CX analysis device 10. In the CX analysis process, each word in the text 207 read from the emotion analysis data is classified into a customer emotion category depending on whether or not each word in the text 207 matches a word in the customer experience index 209.

[0030] The processed data display unit 104 outputs the calculation result of the customer experience value analysis score calculated based on the analysis result of the customer experience value. To this end, the processed data display unit 104 provides search conditions 210 to the other data storage unit 114 and acquires processed data 211, which is processed data 208 that matches the search conditions 210. The search conditions 210 are assumed to be, for example, the date range entered in a search area 301 in FIG. 12, which will be described later. Then, the processed data display unit 104 quantitatively analyzes the customer experience value of the processed data 211.

[0031] After the CX analysis unit 103 analyzes the customer experience value, the processed data display unit 104 displays the analysis results on the output device 100 shown in FIG. 2, which will be described later. Here, the processed data display unit 104 outputs the calculation results of the customer experience value analysis score in the form of a radar chart with the customer experience value items as the vertices. In this way, the processed data display unit 104 is an example of an output unit that can visualize the value received by the customer and show it to the user.

[0032] The information storage unit 105 stores various information. Specifically, the media data storage unit 111 stores acquired data 204. The emotion analysis data storage unit 112 stores processed data 206. The CX analysis data storage unit 113 stores processed data 208. The other data storage unit 114 stores other data. The other data is, for example, user data related to users who use the CX analysis device 10.

[0033] FIG. 2 is a block diagram showing an example of the hardware configuration of the CX analyzer 10 according to an embodiment of the present disclosure.

[0034] 1 is, for example, an information processing device. The CX analyzer 10 may be realized using a cloud server provided by a cloud system, or may be realized using a terminal device such as a PC (personal computer).

[0035] 2 includes a processor 11, a main memory device 12, an auxiliary memory device 13, an input device 14, an output device 15, and a communication device 16. These are connected to each other so as to be able to communicate with each other via a communication means such as a bus (not shown).

[0036] The processor 11 is configured using, for example, a CPU (Central Processing Unit) and an MPU (Micro Processing Unit). The processor 11 realizes various functions of the CX analyzer 10 by reading and executing programs (computer programs) stored in the main memory device 12. The main memory device 12 is a device that stores programs and data, and is, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), and a nonvolatile semiconductor memory (NVRAM: Non Volatile RAM).

[0037] The auxiliary storage device 13 is configured, for example, with an HDD (Hard Disk Drive), an SSD (Solid State Drive), an optical storage device (for example, a CD (Compact Disc) or a DVD (Digital Versatile Disc)), an IC card, an SD memory card, or the like. A storage system or a cloud server may also be used as the auxiliary storage device 13. The auxiliary storage device 13 stores programs and data. The programs and data stored in the auxiliary storage device 13 are loaded into the main storage device 12 as needed.

[0038] The input device 14 is configured using, for example, a keyboard, a mouse, a touch panel, a card reader, and an audio input device. The input device 14 accepts various information from a user who uses the CX analyzer 10. The output device 15 provides the user with various information such as the progress and results of processing. The output device 15 is configured using, for example, a screen display device (such as a liquid crystal monitor, LCD (Liquid Crystal Display), and a graphics card), an audio output device (such as a speaker), and a printer.

[0039] The communication device 16 is a wired or wireless communication interface that enables communication with other devices via communication means such as a LAN (Local Area Network) or the Internet, and is configured using, for example, a NIC (Network Interface Card), a wireless communication module, a USB (Universal Serial Interface) module, and a serial communication module.

[0040] Note that input and output of information may be performed between other devices (not shown) via the communication device 16. The CX analyzer 10 may also include hardware such as an ASIC (Application Specific Integrated Circuit) in addition to the above configuration. Some or all of the computer programs and data included in the present disclosure may be stored in a non-volatile storage medium.

[0041] The output device 100 is connected to the CX analyzer 10 and can print radar charts and the like that are the processing results of the CX analyzer 10. The output device 100 can also be connected to the CX analyzer 10 via a LAN or the like, and can provide the user with the same information as that output from the output device 15.

[0042] Fig. 3 is a diagram showing an example of text 203. The text 203 shown in Fig. 3 is a CSV file and has fields 203a and 203b.

[0043] Field 203a stores text data. Field 203b stores time information related to the text data in field 203a. The time information indicates, for example, the date and time when the text data was created or the date and time when the text data was updated.

[0044] 4 is a diagram showing an example of the customer experience value index 209. The customer experience value index 209 has a type 209a and fields 209b, 209c, 209d, 209e, and 209f.

[0045] The type 209a has a description and a meaning. The description is an item that explains each of the experience values ​​in the fields 209b to 209f. The meaning is an item that indicates the meaning of each of the experience values ​​in the fields 209b to 209f.

[0046] Field 209b classifies words with meanings related to sense. A description of sense is an experience that stimulates the senses (five senses), such as sight, hearing, touch, taste, and smell. Meanings of sense are, for example, good appearance, good music, good smell, delicious, good touch, etc.

[0047] Field 209c classifies words with a meaning related to "feel." A description of "feel," for example, is an experience that appeals to a customer's inner senses or emotions. Examples of "feel" meanings include cool, cute, happy, thoughtful, beautiful, reassuring, trustworthy, attractive, and inspiring scenery.

[0048] Field 209d classifies words with meanings related to "Think (intellectual)." A description of "Think (intellectual)," for example, is an experience that appeals to a customer's creativity or intellectual desire. Meanings of "Think (intellectual)," for example, are intellectually stimulating, interesting, intriguing, educational, and self-improvement.

[0049] Field 209e classifies words with meanings related to Act (behavior / lifestyle). An Act (behavior / lifestyle) description is, for example, an experience that appeals to the customer's behavior or lifestyle. The meaning of Act (behavior / lifestyle) is, for example, a different life than before, something you want to try, something you want to experience, etc.

[0050] Field 209f classifies words that are related in meaning to the social. The explanation for "Relate (social)" is, for example, an experience that appeals to the customer's sense of belonging to a particular group, culture, or ideology. The meaning of "Relate (social)" is, for example, membership, geek status, participation in and sharing of activities, etc.

[0051] As an example, fields 209b to 209f of the customer experience index 209 store content based on the Bernd H. Schmidt customer experience index. However, instead of or in addition to the type and field name, the name and identification information of another customer experience index may be stored in the customer experience index 209.

[0052] 5 is a flowchart for explaining an example of the operation of the data acquisition unit 101. The following operation is executed periodically or when instructed by the user.

[0053] First, the data acquisition unit 101 acquires a search keyword (step S101). For example, the data acquisition unit 101 may acquire a word input by a user to the input device 14 as a search keyword, or may acquire a word transmitted by a user using a user terminal device (not shown) via the communication device 16. A facility name, an event name, or the like may be input as a search keyword.

[0054] Next, the data acquisition unit 101 generates a query 201, which is a search query, based on the acquired search keyword (step S102). The data acquisition unit 101 transmits the generated query 201 to the external media device 20 (step S103).

[0055] The external media device 20 transmits media data 202, which is text data (for example, text data including a search keyword) corresponding to the query 201. The data acquisition unit 101 acquires the media data 202 (step S104).

[0056] Then, the data acquisition unit 101 stores the received media data 202 as acquired data 204 in the media data storage unit 111 (step S105), and ends the process.

[0057] 6 is a flowchart for explaining an example of the operation of the emotion analysis unit 102 and the CX analysis unit 103. The following operation by the emotion analysis unit 102 and the CX analysis unit 103 is executed, for example, periodically.

[0058] First, the emotion analysis unit 102 acquires text 205, which is the acquired data 204 to be analyzed in the emotion analysis process, from the media data storage unit 111 (step S201). The text 205 is, for example, text data from the acquired data 204 stored in the media data storage unit 111 that has not been subjected to emotion analysis processing or CX analysis processing.

[0059] The emotion analysis unit 102 performs emotion analysis processing on the acquired text 205. Then, the emotion analysis unit 102 assigns emotion assignment information, which is the processing result of the emotion analysis processing, to the text 205 and stores the processed data 206 in the emotion analysis data storage unit 112 (step S202).

[0060] The sentiment analysis process includes a process of calculating, for each text 205, a sentiment score that quantifies the sentiment expressed in the social media information within a predetermined range based on each word contained in the text 205. Here, the sentiment score is a number between -1 and 1. A sentiment score closer to -1 indicates a "negative sentiment," and a score closer to 1 indicates a "positive sentiment."

[0061] The emotion analysis unit 102 calculates, as the emotion analysis result, a value obtained by subtracting a negativity indicating the degree of a negative emotion from a positivity indicating the degree of a positive emotion, based on the emotion score. For example, the emotion analysis unit 102 can calculate, as the emotion analysis result, a value obtained by subtracting a negativity indicating the degree of a negative emotion, which is a numerical value between 0 and 1, from a positivity indicating the degree of a positive emotion. The emotion analysis unit 102 can perform emotion analysis processing using, for example, a machine learning model. The processed data 206 is data in which emotion-annotated information including an emotion score is associated with the text 205.

[0062] Next, the CX analysis unit 103 executes the CX analysis process (S203). An example of the procedure for the CX analysis process will now be described with reference to Fig. 7. Fig. 7 is a flowchart for explaining an example of the CX analysis process in step S203 of Fig. 6.

[0063] In the CX analysis process, first, the CX analysis unit 103 reads the customer experience index 209 (step S301). Next, the CX analysis unit 103 acquires the processed data 206 to be analyzed in the CX analysis process as text 207 from the emotion analysis data storage unit 112 (step S302).

[0064] Next, the CX analysis unit 103 executes word segmentation processing to break down the text 207 into words (step S303). The CX analysis unit 103 can perform word segmentation processing using, for example, a machine learning model. Alternatively, the word segmentation processing may be processing that does not use a machine learning model, such as morphological decomposition.

[0065] Next, the CX analysis unit 103 executes a word segmentation correction process that corrects the processing result of the word segmentation process (step S304). The word segmentation correction process is a process in which the CX analysis unit 103 corrects each word broken down in the word segmentation process to the format of a word included in the customer experience value index 209. For example, assume that the word "interesting" is registered in the customer experience value index 209. In this case, if the word "interesting" exists in the processing result of the word segmentation process, the CX analysis unit 103 checks whether "i" exists next to "interesting" in the text 207. If "i" exists next to "interesting" in the text 207, the CX analysis unit 103 corrects the word "interesting" in the processing result of the word segmentation process to "interesting".

[0066] Next, the CX analysis unit 103 compares the words obtained by breaking down the text data through the word segmentation process with the word dictionary included in the customer experience index, and extracts words that match the word dictionary (CX-related words) as customer experience words (step S305). For example, the CX analysis unit 103 compares each customer experience index in the word dictionary included in the customer experience index 209 with each word in the text 207 corrected through the word segmentation correction process, and extracts words from the text 207 that match words in the customer experience index as customer experience words.

[0067] The CX analysis unit 103 ends the process if one or more customer experience words are not extracted from the text 207. On the other hand, if the CX analysis unit 103 extracts one or more customer experience words from the text 207, it executes a CX determination process (see FIG. 8 described later) that prioritizes classification based on the expected customer experience (step S306), and ends the process.

[0068] FIG. 8 is a flowchart for explaining an example of the CX determination process in step S306 of FIG.

[0069] In the CX determination process, first, the CX analysis unit 103 acquires an emotion score from the text 207 (step S401). As described above, emotion-attaching information including an emotion score is attached to the text 205 by the emotion analysis unit 102 and stored as processed data 206 in the emotion analysis data storage unit 112, so an emotion score has also been attached to the text 207 read by the CX analysis unit 103.

[0070] The CX analysis unit 103 executes a classification process to classify the customer experience words extracted from the text 207 into types (Sense, Feel, Think, Act, Relate) that match the customer experience index based on the classification conditions related to the emotion score (step S402). The CX analysis unit 103 generates classification information, which is the processing result of the classification process, as CX information, and ends the process.

[0071] When the CX determination process is completed, returning to FIG. 6, the CX analysis unit 103 stores the processed data 208 in the CX analysis data storage unit 113 (step S204), and ends the emotion analysis process.

[0072] 9 is a diagram showing the classification results of the customer experience value index 209. The configuration of the customer experience value index 209 is the same in FIG.

[0073] Among the customer experience words that match the customer experience index, the words shaded in FIG. 9 are information that the CX analysis unit 103 can use to easily classify customer experience based on the analysis results of social media information. For example, suppose there is a post about a diffuser used in a certain facility that smells nice. The CX analysis device 10 classifies this post as Positive. Furthermore, if the post is Positive and contains the word "smell," it is counted as Sense (nice smell). Note that words not shaded in FIG. 9 represent information that is difficult to classify customer experience. Furthermore, the words in brackets and underlined in FIG. 9 are keywords.

[0074] In the field 209b, Sense, good music (music), good smell (smell, aroma), and delicious are words that can be used to classify customer experience value. In the field 209c, Feel (emotional), words that can be classified as customer experience value include cool (cool), cute (cute), happy, relief, and excitement. In the field 209d, Think (intellectual), interesting (interesting) and educational (study, learning) are words that can be classified as customer experience value. In the field 209e, Act (behavior / lifestyle), "experience" is a word that can be used to classify customer experience value. In the field 209f, Relate (social), membership (member) is a word that can be used to classify customer experience value.

[0075] Any item may be added to each of the fields 209b to 209f. For example, the emotion "enjoy" may be added to the Feel (emotional) category. A radar chart shown in FIG. 12, which will be described later, may be constructed based on the emotions added to each of the fields 209b to 209f.

[0076] Fig. 10 is a diagram showing an example of processed data 208, which is the processing result of the CX analysis unit 103. The processed data 208 shown in Fig. 10 has fields 208a to 208i.

[0077] The field 208a stores a message ID, which is identification information for identifying text data. A unique code is assigned to the message ID, such as UPLOADED_22758_774.

[0078] Field 208b stores a CXID (Cx_Id) that identifies the customer experience index to which the customer experience words included in the text data belong. A unique code, such as UPLOADED_22758_774, is assigned to the CXID. Alternatively, a branch number CXID may be assigned to one message ID in consideration of the case where one post contains multiple customer experience words. For example, if the message ID is UPLOADED_22758_774 described above, a record may be added for each customer experience word extracted from the same message, and the branch numbers "1," "2," ... of the records may be used as the CXID. Alternatively, the CXID may be a unique identifier assigned to each type shown in FIG. 4, such as "1" for Sense and "2" for Feel.

[0079] Fields 208c to 208g store classification information that is the processing result of the CX analysis process for customer experience words. Specifically, fields 208c to 208e store emotional level 1 (Emotional_level1) to emotional level 3 (Emotional_level3), which are indices that indicate the customer experience index of the customer experience word. Emotional level 1 (Emotional_level1), for example, stores "Positive." Emotional level 2 (Emotional_level2) and emotional level 3 (Emotional_level3), for example, stores "praise / admiration." The information stored in emotional level 2 and emotional level 3 may be different.

[0080] Fields 208f to 208h store level 1 (Field_level1) to level 3 (Field_level3), which are indices of customer experience value words. Level 1 (Field_level1) stores, for example, "enjoy." Level 2 (Field_level2) and level 3 (Field_level3) store, for example, "music." The information stored in levels 2 and 3 may be different.

[0081] Field 208i stores words and phrases to be matched with keywords entered in search area 301 of Fig. 12, which will be described later. For example, field 208i stores the name of a singer (A-chan), the name of a commercial facility, the name of an event, etc. Note that processed data 208 may also have fields for storing other data.

[0082] FIG. 11 is a flowchart for explaining an example of the operation of the processed data display unit 104.

[0083] The processed data display unit 104 displays a dashboard 300 (see FIG. 12 described later) for displaying the analysis results obtained by quantitatively analyzing the customer experience value of the processed data 211 (step S501). Next, the processed data display unit 104 accepts search conditions 210 input by the user from a search area 301 of the dashboard 300 (step S502).

[0084] Next, the processed data display unit 104 searches for the processed data 208 stored in the CX analysis data storage unit 113 based on the search conditions 210, and acquires the processed data 211, which is the processed data 208 that matches the search conditions 210 (step S503).

[0085] Next, the processed data display unit 104 performs an analysis process to quantitatively analyze the customer experience value of the text data corresponding to the processed data 211 (the text data identified by the message ID stored in field 208a in FIG. 10) based on the customer experience value of the processed data 211 (S504). In the quantitative analysis of the customer experience value, for example, a process of counting each emotion analyzed from the post is performed.

[0086] Then, the processed data display unit 104 generates the analysis results of the analysis process (for example, a radar chart shown in FIG. 12, which will be described later), displays them on the dashboard 300 (step S505), and ends the process.

[0087] In this embodiment, in the analysis process, the processed data display unit 104 analyzes the customer experience based on the number of customer experience words included in the processed data 211.

[0088] Here, posts and counting emotions based on the results of CX analysis processing will be described with reference to a specific example. The media data 202 acquired by the data acquisition unit 101 may include posts containing multiple emotions. For example, consider the following example post as media information posted by the same person regarding multiple events held at the same time at the same commercial facility.

[0089] Example post: "A-chan, you were so cute today and it was a great live performance. The game tournament here looked fun too."

[0090] In the above example post, the part corresponding to "cute" is personal information unrelated to the event. On the other hand, the part corresponding to "it looked fun" is information related to the event. For posts like this that contain multiple emotions, the processed data display unit 104 does not count "Feel: cute" and "Feel: enjoy" one by one, but only counts "Feel: enjoy," which is the emotion related to the game sales promotion that customers are looking forward to. In this way, only the counts of emotions that represent the effect of the sales promotion event are counted, so users can accurately judge the effectiveness of the sales promotion.

[0091] In addition, counts may be calculated according to the sales promotion effect expected by the user. For example, multiple emotions (Feel, Act) may be detected from a single piece of posted media information. If the user expects emotion (Act) as a sales promotion effect, only one emotion (Act) may be calculated.

[0092] Fig. 12 is a diagram showing an example of dashboard 300. Dashboard 300 is used, for example, to compare customer experience values ​​before and after an event is held. Fig. 12 shows the customer experience values ​​of an event held at one's own facility.

[0093] The processed data display unit 104 outputs, as the calculation result of the customer experience value analysis score, an image in which a radar chart for the event period of the event held at the facility and a radar chart based on normal values ​​calculated for a certain period in the past corresponding to the event period are arranged side by side. The radar chart is displayed on the dashboard 300.

[0094] The dashboard 300 includes a search area 301 and search result display areas 302a and 302b.

[0095] The search area 301 displays a calendar, allowing the user to specify a search period. The user can also input keywords, etc., for comparing customer experience values ​​into the search area 301. Keywords are searched for from social media information using the specified period and keywords input into the search area 301. Examples of keywords that can be used include the name of a commercial facility, the name of an event, or the name of a sport played at an event.

[0096] Search result display areas 302a and 302b display information that visualizes the search results. The search results are a processed count of customer experience value words contained in processed data 211. In FIG. 12, a radar chart is displayed. Other charts such as bar graphs and pie charts may also be displayed. The radar chart also displays reference lines indicating, for example, 10, 20, 30, and 40 posts, making it easy for users to grasp the approximate number of posts.

[0097] The counts of each item displayed on the radar chart are calculated as monthly average values ​​based on data accumulated in media data storage unit 111 for, for example, approximately one year prior to the date the event was held. These monthly average values ​​are taken as normal values ​​and are displayed in search result display area 302a as a radar chart showing the customer experience value before the event. For example, a radar chart of normal values ​​for the search period specified in search area 301 is displayed in search result display area 302a.

[0098] The processed data display unit 104 may set the average value for the period corresponding to the event date as the normal value. For example, if the event is held from April 1 to April 10, 2024, the average value for April 1 to April 10, 2023 is displayed as the normal value on the radar chart.

[0099] The search result display area 302b displays a radar chart showing the customer experience value after the event. For example, suppose the event held at this commercial facility was a hands-on experience program for a sport that is unfamiliar to the general public. Therefore, during the event, there will be an increase in posts from customers wanting to try out the sport (Act: want to try it), and an increase in posts from customers who actually exercised in the sport and ate at a restaurant in the commercial facility. The display also shows an increase in posts from customers who watched athletes demonstrate their skills (Feel: cool). These contents are read from the radar chart in the search result display area 302b, and although they are not actually displayed, they may be displayed on the dashboard 300. The comments added to the radar chart in FIG. 12 may be displayed together with the radar chart as analysis results.

[0100] The search results may be displayed in different formats in the search result display areas 302a and 302b. For example, search results for the same facility may be displayed in a radar chart in the search result display area 302a and in a bar graph in the search result display area 302b.

[0101] In this way, changes in emotions before and after an event are displayed on a radar chart, making it easy to see how customer emotions have changed as a result of a sales promotion event held at a commercial facility. Furthermore, if the change in customer emotions expected at the commercial facility where the event is held is not what the event organizer intended, the event organizer can take measures such as changing the content of the new event.

[0102] A threshold may be set for changes in the radar chart. For example, the interval between reference lines (one scale mark) may be set as the threshold, and when the value of an item on the radar chart changes by more than the threshold, the item name may be highlighted to indicate that the value has changed, or the amount of change may be shown numerically and the text color may change. By making changed items more visible to the user in this way, the user can more easily understand which customer experience items have changed before and after the event.

[0103] Alternatively, a radar chart consisting of only items of emotions that the user is particularly interested in may be displayed. The radar chart shown in Fig. 12 is formed of 12 items, but the radar chart may be displayed with only 3 to 5 items selected by the user, for example.

[0104] 13 is a diagram showing another example of a radar chart displayed on the dashboard 300. Here, an example of a radar chart that allows a user to compare and consider different events held at different commercial facilities will be described.

[0105] The processed data display unit 104 outputs an image of multiple radar charts arranged for each of multiple facilities as the calculation result of the customer experience value analysis score. However, if the number of customers visiting each commercial facility differs significantly between facilities, it would be difficult for users to grasp the number of cases if the reference lines of the radar charts for each commercial facility were set to the same value. For example, if there are 10 posts expressing a certain emotion at one facility and 100 posts at another facility, the number of posts related to the facility would be buried, making it difficult for users to grasp the change in emotion.

[0106] Therefore, the processed data display unit 104 performs a process to normalize the radar charts of different commercial facilities by the maximum number of posts (for example, divide the other posts by the maximum number of posts and then multiply by 100). This process makes it easier for users to compare the bumps and dips in the radar charts of each facility. Note that in this process, the number of posts does not need to be displayed on the reference line of the radar chart.

[0107] Radar chart (1) in Figure 13 shows the reputation of tenants in Facility A. Radar chart (1) shows that there are many posts saying that the cakes in the food court in Facility A are delicious.

[0108] Radar chart (2) in Figure 13 shows the state of an event held at facility B. Radar chart (2) shows that there were many posts saying that person B, who appeared at the event held at facility B, was cute.

[0109] Radar chart (3) in Figure 13 shows the reputation of tenants in facility C. Radar chart (3) shows that there are many posts saying that the ramen at ramen shop D located in facility C is delicious.

[0110] The comments added to each radar chart in Figure 13 may be displayed as the analysis results along with the radar chart. As shown in each radar chart in Figure 13, the content of customer interest revealed from customer posts varies for each facility. This makes the differences in customer experience value at each facility clear, making it easier for users to consider measures to improve the targeted customer experience value.

[0111] The CX analysis device 10 according to the embodiment described above can analyze customer emotions based on social media information posted during an event. Changes in customer emotions before and after an event are represented by changes in the shape of a radar chart analyzed based on Bernd H. Schmidt's five classifications of emotional value, which are based on "experience value management." In this way, by linking the results of customer emotion analysis with classification indicators based on experience value management, changes in emotions due to the event can be objectively shown. This allows users to know how the event affected customer emotions.

[0112] Furthermore, the user can grasp changes in customer emotions that were previously unrecognizable by looking at changes in the shape of the radar chart.

[0113] Customer experience value can be considered emotional value that can be added to conventional rational value. Therefore, by increasing the overall "customer received value," which includes rational value and customer experience value, it is possible to differentiate from other companies.

[0114] Furthermore, if multiple analyzed emotions exist, the type of customer experience desired by the user is counted among the five categories of customer experience indexes. This makes it clear whether the customer experience desired by the user increases or decreases before and after the event.

[0115] The present invention is not limited to the above-described embodiment, and it goes without saying that various other applications and modifications are possible without departing from the gist of the present invention as set forth in the claims. For example, the above-described embodiment has described the system configuration in detail and specifically to clearly explain the present invention, and is not necessarily limited to a system including all of the described configurations. Furthermore, it is also possible to add, delete, or replace part of the configuration of this embodiment with other configurations. In addition, the control lines and information lines shown are those that are considered necessary for the explanation, and do not necessarily show all the control lines and information lines in the product. In reality, it can be assumed that almost all components are interconnected. [Explanation of symbols]

[0116] 10...CX analysis device, 20...external media device, 30...text uploader, 100...storage medium, 101...data acquisition unit, 102...sentiment analysis unit, 103...CX analysis unit, 104...processed data display unit, 105...information storage unit, 111...media data storage unit, 112...sentiment analysis data storage unit, 113...CX analysis data storage unit, 114...other data storage unit, 209...customer experience value index, 300...dashboard

Claims

1. a data acquisition unit that acquires text data including information about a specific facility based on social media information posted on a social media platform; an emotion analysis unit that analyzes the emotion of a poster who posted the social media information based on the text data, based on a predefined emotion score; a customer experience value analysis unit that analyzes customer experience value based on the emotion analysis result; an output unit that outputs a calculation result of the customer experience value analysis score calculated based on the analysis result of the customer experience value. Customer experience value analysis device.

2. The emotion analysis unit calculates an emotion analysis result by subtracting a negativity indicating the degree of negative emotion from a positivity indicating the degree of positive emotion based on an emotion score obtained by quantifying the emotion expressed in the social media information within a predetermined numerical range based on words included in the text data. The customer experience value analysis device according to claim 1 .

3. The customer experience value analysis unit compares words obtained by breaking down the text data using word segmentation processing with a word dictionary included in a customer experience value index that indicates the type of emotional value due to the customer's experience, and extracts the words that match the word dictionary as customer experience value words. The customer experience value analysis device according to claim 2 .

4. The customer experience value analysis unit classifies the customer experience value words into types that match the customer experience value index based on classification conditions related to the emotion scores. The customer experience value analysis device according to claim 3 .

5. The customer experience value analysis unit classifies the customer experience value words based on Bernd H. Schmidt's five classifications of emotional values. The customer experience value analysis device according to claim 4.

6. The output unit outputs the calculation result of the customer experience value analysis score in a radar chart with the customer experience value item as a peak. The customer experience value analysis device according to claim 5 .

7. The output unit outputs, as a calculation result of the customer experience value analysis score, an image in which the radar chart for the event period of the event held at the facility and the radar chart based on normal values ​​calculated for a certain period in the past corresponding to the event period are arranged side by side. The customer experience value analysis device according to claim 6.

8. The output unit outputs an image in which a plurality of the radar charts are arranged for each of the plurality of facilities as a calculation result of the customer experience value analysis score. The customer experience value analysis device according to claim 6.

9. acquiring text data including information about a specific facility based on social media information posted on a social media platform; analyzing the emotions of a poster who posted the social media information based on the text data, based on a predefined emotion score; analyzing a customer experience value based on the emotion analysis result; and outputting a calculation result of the customer experience value analysis score calculated based on the analysis result of the customer experience value. Customer experience value analysis method.

Images