Voice analysis support device, voice analysis support method, and voice analysis support program

The voice analysis support device semantically classifies VOCs based on product intentions, addressing misinterpretation issues in existing technologies and providing actionable insights for product development.

JP7579553B1Active Publication Date: 2024-11-08GENERIC SOLUTION CORP

Patent Information

Application Number
JP2024083012
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-05-22
Publication Date
2024-11-08
Estimated Expiration
2044-05-22

AI Technical Summary

Technical Problem

Existing voice of customer (VOC) analysis technologies struggle to classify customer feedback based on the product development team's specific intentions, leading to misinterpretation and inadequate insights for product improvement.

Method used

A voice analysis support device that classifies VOCs based on predefined product intentions by using a knowledge base to interpret and categorize customer feedback semantically, aligning it with the development team's goals.

Benefits of technology

Enables accurate semantic classification of VOCs, providing actionable insights for product development by aligning customer feedback with intended product features and intentions, enhancing the PDCA cycle for product improvement.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007579553000001_ABST
    Figure 0007579553000001_ABST
Patent Text Reader

Abstract

In voice analysis such as VOC, this enables the semantic classification of voices according to the analyst's specific intentions. [Solution] A voice analysis support device that analyzes voice information regarding a product or service collected from a voice subject, and includes an acquisition means for acquiring information regarding the analyst's specific intention regarding the product or service, an acquisition means for acquiring voice information, an extraction means for extracting phrases indicating a voice regarding the product or service from the voice information, a classification means for classifying the extracted phrases into semantic classifications indicated by the phrases based on the information regarding the specific intention, and a memory means for storing the voice information in correspondence with the phrases and the semantic classifications into which the phrases are classified.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a voice analysis support device, a voice analysis support method, and a voice analysis support program. [Background technology]

[0002] In the field of product development, VOC (Voice of the customer) has been utilized for a long time. Product developers analyze VOC from customers (customers) collected from, for example, questionnaires, inquiries to operators, complaints, EC site reviews, SNS, etc., to help them develop the next new product that meets customer needs, improve existing products, and plan marketing strategies (PDCA cycle of product development).

[0003] Specifically, when a new product is released, product developers can analyze the VOCs received from customers about the new product and analyze customer feedback on the new product. For example, if the product is a food product, various comments (or opinions, if you like) will be received, such as delicious / not delicious, soft / hard, chewy / bad, quantity is large / small, appearance is good / bad, flavor is good / bad, cheap / expensive, good / bad value for money, etc. Product developers can analyze not only positive comments but also negative comments to develop better new products in the future, improve existing products, and review product concepts.

[0004] However, on the other hand, with the widespread use of the Internet and IT tools, customer feedback has also become big data, and the current situation is that many companies are faced with challenges regarding VOC analysis, such as having too much VOC data to organize and classify it, not being able to consolidate the VOC data collected from each channel, and not knowing how to analyze and utilize it.

[0005] In recent years, attention has been focused on VOC analysis technology, which uses natural language processing technology to analyze huge amounts of text data (VOC data) and extract keywords (text mining), as well as sentiment analysis (positive / negative), to classify and evaluate text data for easier analysis.

[0006] As a related technology, for example, Patent Document 1 describes a document classification system that classifies text documents into categories by learning classification rules through machine learning without the need to specify keywords or the like for each category, and allows users to easily understand the reasons for the classification results. Also, for example, Patent Document 2 describes a text mining method that can compare emotional tendencies between multiple documents based on appropriate evaluation of emotional words in the documents with a small amount of calculation. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2011-170786 A [Patent Document 2] JP 2023-113268 A Summary of the Invention [Problem to be solved by the invention]

[0008] In recent years, in a context where customer needs and tastes for products are becoming increasingly diverse and fragmented, product developers may develop products that are targeted to specific customer needs and tastes, rather than developing products that are universally liked.

[0009] For example, suppose there is an instant powdered lemon tea product that dissolves well even in cold water. The product developer's intention (product concept) was to develop a powdered lemon tea that dissolves well even in cold water so that consumers could easily drink iced lemon tea. Next, users (consumers) reported the following VOC examples for the instant lemon tea powder product in question: VOC1: "Dissolves easily in hot water" VOC2: "The lemon flavor is delicious."

[0010] When analyzing such VOC1 and 2, if the technology of Patent Document 1 is applied, the text document of VOC1 is classified into a category such as "usage method (usage characteristics)" of the product by learning classification rules by machine learning, and according to Patent Document 2, VOC1 can be classified into a VOC with an emotional tendency such as "positive". Furthermore, the text document of VOC2 is classified into a category such as "flavor" of the product, and VOC2 can be classified into a VOC with an emotional tendency such as "positive". In this way, when analyzing VOCs, an analyst can easily pick up and analyze VOC1 and VOC2 classified into a category or emotional classification from a huge number of VOCs by specifying a category such as "usage method (usage characteristics)" or "flavor" or an emotional classification of "positive".

[0011] However, according to the invention described in the above Patent Document 2, for example, with regard to VOC1, the customer's voice states that it "dissolves well in hot water," and thus, even though this voice differs from the usage method and usage characteristics that the product developer intended, that is, that it dissolves well in cold water, it is classified into the emotion classification of "positive." In other words, there is no concept of VOC analysis from the perspective of the product intention that the product developer wants to analyze and evaluate, and it is limited to classifying the huge amount of VOC text documents into categories to make them easier to analyze, and evaluating emotions based only on the VOC text documents. For this reason, it is difficult to provide more advanced analysis results or further insights to the product developer.

[0012] When product developers develop a product with a specific intention (concept), they can confirm customer evaluations of the product intention by analyzing the VOC from users from the perspective of the product intention, and use this information to develop better new products in the future, and to improve and review existing products. Therefore, in the case of VOC1 "dissolves easily in hot water," when considering its relationship with the product intention (dissolves easily in cold water), the "positive" classification may not necessarily be appropriate. In this case, the true meaning of VOC1 to the product developer may not be "positive" or "negative," but may be, for example, "miscommunication." In this case, the action that the product developer should take from this realization is to improve promotion, such as reviewing the product feature introduction text or improving the package, so that the product concept is accurately conveyed to customers (see Figure 1, for example).

[0013] The present invention has been proposed in view of the above points, and has an object to enable semantic classification of voices according to the specific intention of the analyst in voice analysis of VOCs, etc. [Means for solving the problem]

[0014] In order to solve the above problems, the voice analysis support device according to the present invention is a voice analysis support device that analyzes voice information related to a product or service collected from a voice owner, and The phrase includes the product specification intended for the product and a phrase indicating the product intention according to the product specification. An acquisition means for acquiring information regarding a specific intention, an acquisition means for acquiring the voice information, and an acquisition means for indicating voices regarding the product or service from the voice information. voice An extraction means for extracting phrases; The product specification to which the voice phrase belongs is determined from the meaning indicated by the voice phrase, and based on the phrase indicating the product intention corresponding to the product specification and the voice phrase, it is determined whether the voice phrase has at least a positive meaning relationship, a negative meaning relationship, or a meaning relationship that is unintended with respect to the product intention, and the voice phrase is processed according to the result of the determination. A classification means for classifying the voice information into a semantic classification. voice Phrase and voice The phrase storing means stores the phrases in association with the semantic classifications into which the phrases are classified. Effect of the Invention

[0015] According to one aspect of the embodiment of the present invention, in voice analysis of VOC or the like, it is possible to perform semantic classification of voice according to a specific intention of an analyst. [Brief description of the drawings]

[0016] [Figure 1] FIG. 2 is a diagram illustrating the relationship between the VOC analysis results and the product development strategy according to the present embodiment. [Diagram 2] 1 is a diagram illustrating an example of the configuration of a VOC analysis support system 100 according to an embodiment of the present invention. [Diagram 3] 1 is a diagram illustrating an example of a functional configuration of a VOC analysis support device 10 according to an embodiment of the present invention. [Figure 4] 4A and 4B are diagrams illustrating an example of product information and information regarding product intention according to the embodiment. [Diagram 5] FIG. 4 is a diagram showing an example of VOC information according to the embodiment; [Figure 6] 1 is a flowchart showing a VOC context classification process according to the present embodiment. [Figure 7A] FIG. 1 is a diagram (part 1) for explaining a context classification process for a VOC according to the present embodiment. [Figure 7B] FIG. 2 is a diagram (part 2) for explaining the context classification process for VOC according to the present embodiment. [Figure 7C] FIG. 3 is a diagram (part 3) for explaining the context classification process for VOC according to the present embodiment. [Figure 8] FIG. 13 is a diagram showing an example of a VOC analysis tabulation screen according to the embodiment. [Figure 9] 1 is a diagram illustrating an example of a product improvement measure according to VOC and customer attributes of the commenter in this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0017] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described in detail with reference to the drawings. [First embodiment] <Summary> First, a product development manager inputs knowledge about a product or service (hereinafter also referred to as a product, etc.) for which a VOC analysis is to be performed into a knowledge base, and structures and formats it in advance as a DB. Knowledge about products, etc. is information about the product intentions of the product development manager, that is, information about the product analysis perspective that the product development manager wants to confirm through VOC analysis. When VOC text data is collected from customers, the VOC analysis support device according to this embodiment interprets, classifies, analyzes, aggregates, etc. the VOC text data in accordance with the knowledge about products, etc. input into the knowledge base, so that VOC analysis can be easily performed from a perspective that is in line with the product intentions of the product development manager.

[0018] In this way, by having a product developer input and learn knowledge such as product intention into a knowledge base in advance for VOC analysis, the VOC analysis support device according to this embodiment can interpret and determine the meaning (called context) indicated by the VOC in accordance with the product developer's product intention, and classify the VOC into the semantic classification (called context classification) indicated by the VOC for the product developer. This enables the product developer to perform VOC analysis in accordance with the analysis viewpoint of the product or service that he or she wishes to focus on during VOC analysis. Furthermore, since the quality of the semantic interpretation of VOC can be improved, it can be useful for further improving the PDCA cycle of product development.

[0019] In addition, the term "context" generally means the context, background, situation, and circumstances related to something, and the "context" in the sense of "context" includes vague and broad information such as the context and the culture behind each event. The context in this embodiment refers to the meaning of VOC interpreted in accordance with the product intention in which the VOC is placed. In this embodiment, the meaning of voice of the customer (VOC) is not the literal single (univocal) meaning of the VOC text, but the meaning of the voice of the customer (VOC) that a company wants to analyze can be determined only by considering the relationship with the "product intention" of the product development staff.

[0020] <System configuration> Fig. 2 is a diagram showing an example of the configuration of a VOC analysis support system 100 according to this embodiment. The VOC analysis support system 100 in Fig. 2 includes a VOC analysis support device 10, a knowledge base 20, and a terminal 30, which are connected via a network (not shown).

[0021] The VOC analysis support device 10 is a server device that supports the analysis of VOCs related to products submitted by customers. The VOC analysis support device 10 performs VOC analysis such as interpretation, judgment, classification, and aggregation of VOCs based on product information stored in a knowledge base 20, knowledge related to products intended by product developers, and VOC information.

[0022] The knowledge base 20 is a knowledge database that accumulates and builds knowledge information about products, such as product masters, information about product intentions of product developers, and VOC information collected from customers. A knowledge base is a database that collects in-house work experience and know-how in one place, making it easy to search and use.

[0023] The terminal 30 is, for example, a PC (personal computer), a smartphone, a tablet terminal, or the like, and is, for example, a user terminal used by a product development staff member in a product development department. A predetermined application program and a general-purpose web browser for accessing the VOC analysis support device 10 are pre-installed on the terminal 30. The product development staff member can access the VOC analysis support device 10 using the terminal 30, obtain the analysis results (interpretation, judgment, classification, aggregation, etc.) by the VOC analysis support device 10, and display them on the screen. The product development staff member can analyze the VOCs for products received from customers, and use them in the product development PDCA cycle, such as improving existing products to meet customer needs, developing new products, and planning marketing strategies.

[0024] Needless to say, users of the terminal 30 are not limited to product development personnel, but include personnel involved in product development, such as product development department, product planning department, product manufacturing department, public relations department, marketing department, etc. In addition, the VOC according to this embodiment is customer feedback on the product, but it may also be VOE (Voice of Employee) from employees in the distribution process, such as manufacturing, distribution, procurement, and retail (store clerks, etc.) and other personnel (delivery personnel, manufacturing personnel and engineers involved in the manufacturing process).

[0025] (Functional configuration) 3 is a diagram showing an example of a functional configuration of the VOC analysis support device 10 according to this embodiment. The VOC analysis support device 10 has, as main functional units, a specific intention acquisition unit 101, a VOC acquisition unit 102, a phrase extraction unit 103, a context classification unit 104, a display control unit 105, and a storage unit 109.

[0026] The specific intention acquisition unit 101 has a function of acquiring information regarding the analyst's specific intention regarding a product or service. The VOC acquisition unit 102 has a function of acquiring voice information (VOC). The phrase extraction unit 103 has a function of extracting phrases (words) indicating voices regarding a product or service from the voice information. The context classification unit 104 has a function of classifying phrases into meaning classifications (e.g., context classifications) indicated by the phrases based on the information regarding the specific intention. The display control unit 105 has a function of displaying the phrases and the meaning classifications into which the phrases are classified (e.g., context classification processing results) on the terminal 30. The storage unit 109 has a function of storing the voice information in the knowledge base 20 in association with the phrases and the meaning classifications into which the phrases are classified (e.g., context classification processing results).

[0027] The VOC analysis support device 10 can be realized by a general-purpose computer. Specifically, the VOC analysis support device 10 includes hardware such as an arithmetic processing unit (CPU, etc.), a memory, an input / output interface, and a communication interface. The functions of the VOC analysis support device 10 are realized by the arithmetic processing unit executing processing according to a computer program stored in a memory. That is, each functional unit is realized by a computer program executed on hardware resources such as the arithmetic processing unit and memory of the computer constituting the VOC analysis support device 10. The VOC analysis support device 10 may be called a computing machine for VOC analysis support. These functional units may also be read as "means," "module," "unit," or "circuit." The knowledge base 20 may be disposed in the memory of the VOC analysis support device 10 or an external storage device on a network. Each functional unit of the VOC analysis support device 10 may not only be realized by a single server device, but may also be realized as a system consisting of multiple devices with distributed functions. The computer program may also be stored in a computer-readable storage medium.

[0028] (Knowledge Base) The knowledge base 20 according to this embodiment is a knowledge database in which product information, information on product intentions of product developers, VOC information, and the like are accumulated and constructed.

[0029] 4A is a diagram showing an example of product information according to the present embodiment. The product information is product master information including, for example, a product code, a product name, a JAN code, a product category, a price, a content amount, a manufacturer, a release date, etc.

[0030] 4(b) is a diagram showing an example of information related to product intention according to this embodiment. In recent years, in a background in which customer needs and preferences for products are becoming increasingly diverse and fragmented, product developers use product intentions (e.g., product concepts) to develop products that target specific customer needs and preferences.

[0031] For example, a product developer wants to conduct a VOC analysis to see whether the instant lemon tea (powder type) product envisioned by the product developer has been evaluated by customers as intended by the concept. More specifically, what the product developer wants to analyze in a VOC analysis is the customer's opinion on the viewpoint of making the powder dissolve well in cold water or ice water, which was a particular focus of the development effort, and therefore in such a case, the information on the product intention is structured and formalized in advance as a set of product specifications (product attribute categories) and phrases indicating the product intention, such as "usage method / usage properties" dissolves well in cold water, "shape" powder, and "flavor" crisp and delicious, and is entered and stored in the knowledge base 20 in order to express what the product is about.

[0032] Any method of inputting information into the knowledge base 20 may be used, but the product development staff can, for example, access the VOC analysis support device 10 using a terminal 30 and input information via a predetermined dashboard screen or the like provided by the VOC analysis support device 10. The VOC analysis support device 10 can store, for example, product information, in which the product code of the product and information related to the product intention are associated with each other (FIG. 4).

[0033] Furthermore, the input method for the knowledge base 20 may be automatic extraction from a document containing information about the product intention (for example, the product development proposal shown in FIG. 4). The VOC analysis support device 10 executes natural language processing on the document to extract phrases indicating the product intention and determine the product specifications (product attribute category) to which the phrases belong. The extraction process can utilize libraries using conventional methods including machine-readable catalogs and corpora, morphological analysis, syntactic analysis, semantic analysis, and contextual analysis. Note that if any information not corresponding to the product intention is automatically extracted from the information about the product intention shown in FIG. 4, it may be possible for the product development staff to delete it via a predetermined dashboard screen or the like.

[0034] Figure 5 is a diagram showing an example of VOC information according to the present embodiment. The VOC information is collected from channels such as questionnaires, inquiries to operators, complaints, EC site reviews, and SNS, and is the voices sent by customers. The VOC information according to the present embodiment includes, for example, VOC_ID, product name, product code, channel (type), reception date, name, age, gender, voice content, and the like. Note that the VOC information includes information (such as product name and product code) that can identify which product the VOC is for by a method according to the channel for obtaining the VOC. For example, in the case of a web-based channel, the product name and product code are required inputs, or in the case of an inquiry channel to a call center, the operator always confirms the product name and product code.

[0035] Also, although the VOC information according to the present embodiment is text data, it may be data other than text (such as voice and image) by a method according to the channel for obtaining the VOC, as long as it is finally converted into text.

[0036] <Context Classification Processing of VOC (Semantic Interpretation Processing of VOC)> Figure 6 is a flowchart showing the context classification processing of VOC according to the present embodiment. By reading and executing a program that can be realized by the arithmetic processing unit of the VOC analysis support device 10, the following steps (hereinafter referred to as "S") can be realized.

[0037] S1: The VOC analysis support device 10 acquires information regarding the product intention of the target product from the knowledge base 20 using, for example, the product code as a key. The information regarding the product intention according to the present embodiment is, for example, a set of product specifications (product attribute categories) and phrases indicating product intentions in order to express what the product is like (Figure 4).

[0038] S2: The VOC analysis support device 10 acquires VOC information related to the target product using, for example, a product code as a key from the knowledge base 20. The VOC information according to this embodiment includes, for example, a VOC_ID, product name, product code, channel (type), receipt date, name, age, gender, and voice content (FIG. 5).

[0039] S3: The VOC analysis support device 10 executes natural language processing and extracts phrases that express customer voices (hereinafter referred to as VOC phrases) from the VOC information (voice content). The extraction process can use libraries using conventional methods, including machine-readable catalogs and corpora, morphological analysis, syntactic analysis, semantic analysis, and contextual analysis.

[0040] Generally, a phrase is an expression that combines a series of words and syllables, and is treated as a unit with grammatical meaning, larger than a word and smaller than a sentence. However, in this embodiment, the extraction target is not necessarily limited to a phrase consisting of multiple words, and may be one or more words as long as it expresses the voice of the V customer.

[0041] S4: The VOC analysis support device 10 executes a context classification process based on the information on product intention acquired in S1 and the VOC phrase extracted in S2. More specifically, it first determines the meaning of the VOC phrase and the word to which product specification the VOC phrase belongs. Next, it determines the context indicated by the VOC phrase (the meaning of the VOC phrase for the product development staff) based on the meaning of the VOC phrase and the phrase indicating the product intention according to the product specification to which the VOC phrase belongs. As a result, the VOC phrase is classified into the determined context classification.

[0042] The context classification according to this embodiment is a category for semantically classifying VOC, and examples of such categories include "positive (praise)", "negative (complaint)", "neutral", "miscommunication (unintended)", "simple impression", "question", "request", "other", etc. The meaning of VOC is interpreted and determined according to the product intent, and the VOC is classified into a context classification corresponding to the meaning indicated by the VOC.

[0043] S5: The VOC analysis support device 10 associates the product specifications and context classification for each VOC phrase as a result of the context classification process for each piece of VOC information, and stores them in the knowledge base 20. Note that when one VOC contains multiple VOC phrases, each VOC phrase is classified into a context classification corresponding to the meaning indicated by the VOC, so that one VOC may be classified into multiple context classifications at the same time. This is also illustrated in Figures 7A to 7C. Next, S3 and S4 will be specifically described in detail.

[0044] 7A is a diagram (part 1) for explaining the context classification process for VOC according to this embodiment. First, the VOC analysis support device 10 extracts VOC phrases 1002a, such as "it dissolves easily in hot water," "it has a rich taste (and a good aroma)," and "it also has a good aroma," from the voice content 1001a of the VOC information.

[0045] Next, the VOC analysis support device 10 determines which product specification (product attribute category) 1003a the extracted VOC phrase 1002a belongs to. In the example of FIG. 7A, the VOC phrase "dissolves well in hot water" is determined to be a word belonging to, for example, "usage method / usage properties" of the product specifications (product attribute category) based on the meaning of the VOC phrase. Also, the VOC phrase "rich taste (and aroma) is good" is determined to be a word belonging to, for example, "taste" of the product specifications (product attribute category) based on the meaning of the VOC phrase. Also, the VOC phrase "good aroma" is determined to be a word belonging to, for example, "aroma" of the product specifications (product attribute category) based on the meaning of the VOC phrase.

[0046] The VOC analysis support device 10 then determines the context 1005a indicated by the VOC phrase (the meaning that the VOC phrase has for the product development staff) based on the meaning indicated by each VOC phrase 1002a and the phrase 1004a indicating the product intention corresponding to the product specifications 1003a to which the VOC phrase 1002a belongs, and classifies the VOC phrase into the determined context 1005a.

[0047] In the example of Figure 7A, the VOC phrase "dissolves easily in hot water" is a word that belongs to the product specification "usage method / usage characteristics," and in relation to the phrase "dissolves easily in cold water" that indicates the product intention, they have the same topic but different meanings. Therefore, based on the meaning indicated by the VOC phrase, it is appropriate to semantically classify it into the context of "miscommunication (misguided intention)."

[0048] When product developers develop products with a specific intention, they can confirm customer evaluations of the product intention by analyzing VOCs from users from the perspective of the product intention, and use this information to develop better new products, improve and review existing products, etc. The product developers in question developed a powdered lemon tea that "dissolves well even in cold water," but the customer feedback did not mention whether it dissolves well in cold water in the "usage method / usage characteristics," but rather said that it "dissolves well in hot water," which is unrelated to the product intention. In other words, the VOC phrase "dissolves well in hot water" could be judged as "positive" based only on the meaning indicated by the VOC phrase, but when considering its relationship with the phrase "dissolves well in cold water," which indicates the product intention, it is not necessarily appropriate to classify it as "positive."

[0049] In this case, the insights and actions that product developers can gain from classifying the VOC phrase into the context of "miscommunication" could include improving promotion so that the product concept (e.g., "dissolves easily even in cold water") is accurately conveyed to customers, such as revising the product feature description or improving the packaging (e.g., C in Figure 1).

[0050] In addition, the VOC phrase “Rich in flavor (and good aroma)” is a word that belongs to the product specification “flavor,” and in relation to the phrase “crisp and delicious,” which indicates the product intention, it has the same topic but a different meaning. Therefore, based on the meaning indicated by the VOC phrase, it is appropriate to semantically classify it into the context of “miscommunication (misguided intent).”

[0051] The product developer in question had developed a lemon tea with a crisp and delicious taste, but the customer feedback did not refer to whether the "taste" was crisp and delicious, but rather to the "rich flavor (and aroma)", which is unrelated to the product's intention. In other words, the VOC phrase "rich flavor (and aroma) is good" could be judged as "positive" based only on the meaning of the VOC phrase, but when considering its relationship with the phrase "crisp and delicious", which indicates the product's intention, a "positive" classification is not necessarily appropriate.

[0052] In this case, the insights and actions that product developers can gain from classifying the VOC phrase into the context of "miscommunication" could include improving promotion so that the product concept (e.g., "crisp and delicious") is accurately conveyed to customers, such as revising the product feature introduction text or improving the packaging (e.g., C in Figure 1).

[0053] Here, for example, the technology described in the following non-patent document can be applied to VOC context classification processing (VOC semantic interpretation processing). This non-patent document describes a metric model (a mathematical model of meaning) that dynamically calculates the semantic and sensory equivalence, similarity, and relevance between data in accordance with the "situation and context," based on the idea that one word (for example, a VOC phrase) does not always have one meaning, but that the meaning is determined only when the situation and context (information related to product intent) are given, that is, the semantic and sensory identity, similarity, and relevance between data are not determined by a static relationship, but change dynamically depending on the context and situation.

[0054] Yasushi Kiyoki, "Database system for measuring sensibility and meaning: Memory systems of humans and information systems", "KEIO SFC JOURNAL", Keio University Shonan Fujisawa Society, 2013, Vol. 13, No. 2, pp. 19-26 On the other hand, the VOC phrase "The scent is good" is a word belonging to the product specification "scent" and does not correspond to the product specification indicating the product intention. In other words, the VOC phrase "The scent is good" is mentioned in relation to the topic / perspective of the product specification "scent" that is unrelated to the product intention, and may be semantically classified into a "positive" context based on the meaning of the VOC phrase. The meaning of the VOC phrase "The scent is good" is not determined by the VOC phrase alone, but is determined only when a situation or context is given, as in the above non-patent document, and is considered to change dynamically depending on the context or situation. It is desirable to apply a metric model (a mathematical model of meaning) that dynamically calculates the semantic and sensory equivalence, similarity, and relevance between data in the entire text sentence of the voice content 1001a depending on the "situation or context" and determine it.

[0055] 7B is a diagram (part 2) for explaining the context classification process for VOC according to this embodiment. First, the VOC analysis support device 10 extracts VOC phrases 1002b, such as "it dissolves easily in water," "the lemon flavor is not good," "the volume is small," "the price is a little high," and "it would be helpful if it was reasonably priced," from the voice content 1001b of the VOC information.

[0056] Next, the VOC analysis support device 10 judges which product specification (product attribute category) 1003b the extracted VOC phrase 1002b belongs to. In the example of FIG. 7B, the VOC phrase "dissolves quickly in water" is judged to be a word belonging to, for example, "usage method / usage properties" of the product specifications (product attribute category) based on the meaning of the VOC phrase. The VOC phrase "the lemon flavor is not delicious" is judged to be a word belonging to, for example, "flavor" of the product specifications (product attribute category) based on the meaning of the VOC phrase. The VOC phrase "small capacity" is judged to be a word belonging to, for example, "volume" of the product specifications (product attribute category) based on the meaning of the VOC phrase. The VOC phrases "the price is a little high" and "it would be helpful if it was reasonably priced" are judged to be words belonging to, for example, "price" of the product specifications (product attribute category) based on the meaning of the VOC phrase.

[0057] The VOC analysis support device 10 then determines the context 1005b indicated by the VOC phrase (the meaning that the VOC phrase has for the product development staff) based on the meaning indicated by each VOC phrase 1002b and the phrase 1004b indicating the product intention corresponding to the product specifications 1003b to which the VOC phrase 1002b belongs, and classifies the VOC phrase into the determined context 1005b.

[0058] In the example of Figure 7B, the VOC phrase "dissolves quickly in water" is a word that belongs to the product specification "usage method / usage properties" and, in relation to the phrase "dissolves easily even in cold water" that indicates the product intention, it has the same or similar meaning (positive meaning) to the same topic. Therefore, based on the meaning indicated by the VOC phrase, it is preferable to semantically classify it into a "positive" context.

[0059] The product developer in question had developed a powdered lemon tea that "dissolves well even in cold water," but the customer feedback was that it "dissolves quickly in water," which is exactly what the product intended. In other words, the VOC phrase "dissolves quickly in water" is appropriately classified as "positive" when considering its relationship with the phrase "dissolves well even in cold water," which indicates the product's intended purpose.

[0060] In this case, the product developer can confirm that the product intent was as intended based on the classification results of the VOC phrase and the “positive” context (e.g., A in Figure 1).

[0061] In addition, the VOC phrase “The lemon flavor is not good” is a word belonging to the product specification “flavor,” and in relation to the phrase “crisp and delicious,” which indicates the product intention, it has the same topic but a different meaning. Therefore, based on the meaning indicated by the VOC phrase, it is appropriate to semantically classify it into the context of “miscommunication (unintended).”

[0062] The product developer in question had developed the product with the aim of creating a lemon tea with a "crisp and delicious" taste, but the customer feedback did not refer to whether the product was crisp and delicious, but rather to the "lemon flavor not being tasty," which is unrelated to the product's intention. In other words, the VOC phrase "The lemon flavor is not tasty" could be judged as "negative" based solely on the meaning of the VOC phrase, but when considering its relationship with the phrase "crisp and delicious," which indicates the product's intention, a "negative" classification is not necessarily appropriate.

[0063] In this case, the insights and actions that product developers gain from classifying the VOC phrase into the context of “miscommunication” can be utilized in new product development as a separate need, such as improving the taste itself or developing a new flavor (e.g., D in Figure 1).

[0064] On the other hand, the VOC phrase "small capacity" is a word that belongs to the product specification "volume" and does not correspond to the product specification that indicates the product intention. In other words, the VOC phrase "small capacity" is mentioned in relation to the topic / perspective of the product specification "volume" that is unrelated to the product intention, and can be semantically classified into a "negative" context based on the meaning indicated by the VOC phrase.

[0065] In addition, the VOC phrase "The price is a little high" is a word that belongs to the product specification "price" and does not correspond to the product specification that indicates the product intention. In other words, the VOC phrase "The price is a little high" is mentioned in relation to the topic or viewpoint of the product specification "price" that is unrelated to the product intention, and can be semantically classified into a "negative" context based on the meaning indicated by the VOC phrase.

[0066] In addition, the VOC phrase "It would be helpful if it was reasonably priced" is a word that belongs to the product specification "price" and does not correspond to the product specification that indicates the product intent. In other words, the VOC phrase "It would be helpful if it was reasonably priced" is mentioned in relation to the topic or viewpoint of the product specification "price" that is unrelated to the product intent, and can be semantically classified into the context of "request" based on the meaning indicated by the VOC phrase.

[0067] 7C is a diagram (part 3) for explaining the context classification process for VOC according to this embodiment. First, the VOC analysis support device 10 extracts VOC phrases 1002c, such as "If you don't mix it well with ice water, the powder won't dissolve and some lumps will remain," "The package might be hard to open," and "I wonder if there's anything we can do about it," from the voice content 1001c of the VOC information.

[0068] Next, the VOC analysis support device 10 judges which product specification (product attribute category) 1003c the extracted VOC phrase 1002c belongs to. In the example of Fig. 7C, the VOC phrase "If you don't mix it well with ice water, the powder won't dissolve and some lumps will remain" is judged to be a word belonging to "usage method / usage characteristics" of the product specifications (product attribute category) based on the meaning of the VOC phrase. Also, the VOC phrases "The package might be hard to open" and "I wonder if there's anything we can do about it" are judged to be words belonging to "packaging" of the product specifications (product attribute category) based on the meaning of the VOC phrase.

[0069] The VOC analysis support device 10 then determines the context 1005c indicated by the VOC phrase (the meaning that the VOC phrase indicates to the product development staff) based on the meaning indicated by each VOC phrase 1002c and the phrase 1004c indicating the product intention corresponding to the product specifications 1003c to which the VOC phrase 1002c belongs, and classifies the VOC phrase into the determined context 1005c.

[0070] In the example of Figure 7C, the VOC phrase “If you don’t mix it well in ice water, the powder won’t dissolve and some lumps will remain” is a word that belongs to the product specification “Usage method / usage properties” and has a negative meaning in relation to the phrase “It dissolves well even in cold water” that indicates the product intention, and therefore it is appropriate to semantically classify it into a “negative” context based on the meaning indicated by the VOC phrase.

[0071] The product developer in question had developed a powdered lemon tea that "dissolves well even in cold water," but the customer feedback was that "if you don't mix it well with ice water, the powder doesn't dissolve and some lumps remain," which goes against the product's intention. In other words, the VOC phrase "if you don't mix it well with ice water, the powder doesn't dissolve and some lumps remain," is appropriately classified as "negative" when considering its relationship with the phrase "dissolves well even in cold water," which indicates the product's intention.

[0072] Also in this case, the insights and actions obtained by the product development staff from the classification results of the VOC phrases and the "negative" context include product improvements such as the development of a powder that does not leave lumps even with cold water (for example, B in FIG. 1).

[0073] On the other hand, the VOC phrase "Isn't there something we can do?" is a word belonging to the product specification "package" and does not correspond to the product specification indicating the product intention. That is, the VOC phrase "Isn't there something we can do?" is mentioned with respect to the topic / viewpoint of the product specification "package" that has nothing to do with the product intention, and may be semantically classified into the context of "mere impression" (or "request") based on the meaning indicated by the VOC phrase.

[0074] <VOC Analysis Aggregation> FIG. 8 is a diagram showing an example of a VOC analysis aggregation screen according to the present embodiment. The product development staff accesses the VOC analysis support device 10 using the terminal 30, acquires the VOC analysis aggregation information analyzed and aggregated by the VOC analysis support device 10, and displays it on the dashboard screen. The product development staff can analyze the VOCs related to the product sent from the customer and analyze the voice of the customer with respect to the product intention (for example, product concept).

[0075] Specifically, first, the product development staff searches for VOC analysis aggregation information related to the VOC analysis target product using, for example, the product code or product name of the product as a key. In response to the search request for the VOC analysis aggregation information from the terminal 30, the VOC analysis support device 10 can acquire and aggregate the context classification processing results in the product, and display them as the VOC analysis aggregation information shown in FIG. 8, for example.

[0076] Product developers want to perform VOC analysis to see whether their product has been evaluated by customers as intended by the product developer. Therefore, when product developers perform a search using input conditions such as the product code or product name, and product specifications related to the product's intent (for example, "method of use / usage properties," "shape," and "flavor"), the VOC collected about the product is displayed, categorized by product specifications and by the context that each VOC phrase represents.

[0077] Furthermore, VOC phrases are linked to the original VOC information that originated the VOC phrase, so if product development staff want to check and analyze customer feedback in more detail, they can quickly and easily view the original VOC information (full text) by simply clicking on the VOC phrase.

[0078] More specifically, a product developer has developed a powdered lemon tea that "dissolves well even in cold water," and according to the context classification processing results for that product, one of the customer comments is "dissolves well in hot water," which is classified as a context "miscommunication (unintended)" in "usage method / nature of use." After carefully reviewing and analyzing the original VOC information (full text), product developers can consider improving promotions based on that customer's feedback, such as revising the product feature introduction text or improving the packaging, so that the product concept (for example, "dissolves well even in cold water") is accurately conveyed to customers.

[0079] One of the customer comments is "It dissolves quickly in water," which is classified as a "positive" context in "usage method / usage characteristics." Product developers can confirm that the product has been successful as intended by receiving this customer's feedback. Another customer comment is "If you don't mix it well in ice water, the powder doesn't dissolve and some lumps remain," which is classified as a "negative" context in "usage method / usage characteristics." Product developers can use this customer's feedback to consider product improvements, such as developing a powder that does not dissolve in cold water after realizing that the powder does not dissolve sufficiently.

[0080] As described above, according to this embodiment, by predefining information about specific intentions that product developers want to focus on during VOC analysis and inputting and learning it into the knowledge base 20, the VOC analysis support device can classify a huge amount of VOC text data (customer voices) into the meanings (contexts) that the VOC indicates to the product developers. This enables the product developers to perform VOC analysis in line with the perspective of specific intentions regarding the products or services that they want to focus on during VOC analysis.

[0081] The following embodiments are also mentioned: Generally, a phrase is an expression that combines a series of words and syllables, and is treated as a unit with grammatical meaning, larger than a word and smaller than a sentence. However, the phrase in this embodiment is not necessarily limited to a combination of words that make sense, and it can be a single word or a phrase as long as it expresses the voice of the customer. In other words, a phrase can be a single word or a combination of words that make sense, and is a semantic unit that is determined by the result of judging its meaning.

[0082] · In the process of extracting VOC phrases in S3, the order of VOC sentence > divided sentence > phrase > word is analyzed, and meaningful VOC phrases are extracted taking into consideration the classification information of parts of speech such as nouns, verbs, adjectives, and adverbs that are given as initial information of the language. In addition, the meaning of a VOC phrase changes depending on the center of gravity of each word, the situation, and the context when it is combined to form a meaning, and the meaning is determined only when these are given. For example, in the VOC submitted for instant lemon tea, the true meaning of the VOC phrases "good value for money" and "bad value for money" cannot be determined simply from the price aspect, and the true context of the VOC is determined by various other situations and contexts such as the full text of the VOC, other phrases, and information about the product's intention. Therefore, depending on the situation and context, the true context of the VOC may mean a completely opposite context or miscommunication (misunderstanding of intention).

[0083] For example, when there is a large amount of VOC, some of the comments may overlap. On the VOC analysis summary screen, VOCs with the same meaning may be aggregated and the VOC phrases may be displayed together. In this case, the number of VOCs may be displayed together with the VOC phrase, for example, "sweet" (50 cases). Product developers can understand the importance of a VOC phrase based on the number of VOCs that indicate a large or small number of comments.

[0084] Product specifications (product attribute categories) vary depending on the product itself that is the subject of VOC analysis. Examples include other quality-related aspects, product design and labeling, container packaging and materials, content volume, size and quantity, design, manufacturing method and process, usage and storage methods, return and exchange methods, communication, product lineup and inventory status, etc. For example, if the product is an ingredient or seasoning, and the perspective of product intent that product developers want to focus on during VOC analysis is defined as whether the product intent is suitable for cooking or recipes, product specifications include genres such as Japanese, Western, Chinese, etc., and specific dish names.

[0085] Context classification is not limited to the above-mentioned embodiment, but varies depending on the viewpoint of specific intent that product developers want to focus on during VOC analysis, i.e., the information needs that companies want to know through VOC analysis. In other words, product developers can perform VOC analysis that meets the various information needs of companies depending on how they define the context to classify information related to specific intents and products, etc.

[0086] In VOC, for example, product evaluations may change between immediately after a product is released and after a certain period of time has passed since the product is released, due to customer understanding of the product concept becoming more widespread. In response to a request from the terminal 30, the VOC analysis support device 10 may analyze and aggregate VOC for a predetermined period (for example, monthly), and display the VOC analysis and aggregation information for each predetermined period in chronological order on the screen.

[0087] By utilizing the VOC analysis support system 100 according to this embodiment, not only for new product launches but also before and after product renewal, it is possible to analyze changes in VOCs before and after product renewal and whether the changes are close to or far from the intention behind the renewal.

[0088] The VOC analysis support system 100 (VOC analysis support device 10) of this embodiment is not limited to the utilization of VOCs in product and service development, but can also be applied to the utilization of feedback from VOEs of employees (store clerks, etc.) and other related parties (delivery staff, manufacturing staff and engineers involved in the manufacturing process, etc.) in the distribution process, including manufacturing, distribution, procurement, and retail.

[0089] Furthermore, by separating voices into VOC and VOE, and comparing and aggregating different voices from one source with other sources, it becomes possible to identify needs, issues, problems, etc. that would be difficult to identify from a single voice source alone.

[0090] [Second embodiment] As mentioned above, product developers can use VOC analysis to develop new products that meet customer needs, improve existing products, and plan marketing strategies. By understanding with high resolution who is expressing the VOC, product developers can more accurately consider how to improve products in the future.

[0091] FIG. 9 is a diagram for explaining an example of a product improvement measure according to the VOC and the customer attributes of the voice speaker according to this embodiment. For example, when VOCs with the context classification "flavor": salty (negative) and VOCs with the context classification "flavor": weak (negative) are received for the product "flavored meatballs," an important realization that a product development manager can obtain from the VOCs is that, in terms of "flavor," product improvement measures such as simply reducing the amount of salt or making the seasoning stronger can be mentioned. However, by understanding "who" has made the voice, a product development manager can consider how to improve the product in the future from a broader perspective based on VOCs with seemingly contradictory contents.

[0092] For example, regarding the product "flavored meatballs," if it is understood that the VOC commenting "taste" as "salty" (negative) came from a "mother with a kindergarten-aged child," it would be possible to consider more in-depth product improvement measures, such as considering a recipe with less salt, taking into account the growth and development of young children's sense of taste, changing the packaging design to a cute, pop design using characters, and adding the phrase "low in salt."

[0093] For example, regarding the product "flavored meatballs," if it is understood that the VOC commenting that "flavor" is weak (negative) was made by an "elderly person," it is possible to consider more in-depth product improvement measures, such as considering recipes that add umami flavor in consideration of the declining sense of taste and excessive salt intake of the elderly, as well as adding the statement "Can be eaten every day" to the packaging with large, easy-to-read letters that give a healthy impression.

[0094] Generally, VOC is collected from, for example, surveys, inquiries to operators, EC site reviews, SNS, etc., but in the case of VOC collected from, for example, surveys (particularly questionnaire forms) or inquiries to operators, the customer attributes of the VOC voices are often unknown or insufficient. On the other hand, in cases where customer IDs and customer attribute information (user profiles, etc.) are linked to the VOC, such as VOC collected from EC site reviews or SNS, it is possible to identify the customer attributes of the voices in that VOC.

[0095] Examples of customer attribute information that can be particularly useful in considering product improvement measures include age, gender, family structure, address (area of ​​residence), and occupation. Customer attributes of voices in VOC may also be classified into clusters. Examples of cluster classification information include young single people, DINKS, families with children, families with children (dual-income families), two-generation families, elderly single people, and elderly couples.

[0096] On the other hand, there are cases where customer attribute information (user profile, etc.) does not contain enough information to contribute to the consideration of product improvement measures, such as when family structure or occupation is left blank or not registered. In such cases, by applying Patent No. 6923890 and Patent No. 6971449 by the present applicant, if a customer is a member of an EC site that sells products, it is possible to estimate the customer's family structure, occupation, etc. based on the customer's activity data, such as a purchase history DB or transaction data, and to supplement the blank or not registered customer attribute information.

[0097] As shown in Figure 8, a VOC phrase is linked to the original VOC information of the VOC phrase, and by clicking on the VOC phrase, it is possible to quickly and easily check the original VOC information (full text), as well as the customer attribute information (user profile, etc.) and cluster classification information of the person speaking in that VOC.

[0098] Although the present invention has been described by showing specific examples according to the preferred embodiment of the present invention, it is apparent that various modifications and changes can be made to these examples without departing from the broad spirit and scope of the present invention as defined in the claims. In other words, the details of the examples and the accompanying drawings should not be construed as limiting the present invention.

[0099] (Appendix 1) A voice analysis support device (e.g., a VOC analysis support device) that analyzes voice information (e.g., VOC) about a product or service collected from a voice subject (e.g., a customer), An acquisition means (e.g., S1 in FIG. 6) for acquiring information on a specific intention of an analyst (e.g., a product development manager) for the product or service (e.g., a phrase indicating the product intention, or a set of product specifications and phrases indicating the product intention); An acquisition means (e.g., S2 in FIG. 6) for acquiring the voice information (e.g., VOC text data); An extraction means (e.g., S3 in FIG. 6) for extracting phrases (e.g., VOC phrases) indicating opinions regarding the product or service from the voice information; A classification means (e.g., S4 in FIG. 6) that classifies the extracted phrase into a semantic classification (e.g., a context classification) indicated by the phrase based on the information regarding the specific intention; A storage means (e.g., S6 in FIG. 6) for storing the voice information in association with the phrase and the semantic classification into which the phrase is classified (e.g., a context classification processing result); A voice analysis support device comprising:

[0100] (Appendix 2) a display control means for displaying the phrase and the semantic classification into which the phrase is classified (e.g., a result of a context classification process) on the terminal of the analyst; 2. A voice analysis support device as described in claim 1, comprising:

[0101] (Appendix 3) The classification means determining a semantic classification category into which the phrase is classified (e.g., "positive (compliment)", "negative (complaint)", "neutral", "miscommunication (misintentional)", "simple impression", "question", "request", "other") based on the information regarding the specific intent; 2. The voice analysis support device according to claim 1,

[0102] (Appendix 4) The predetermined semantic classification category includes a first semantic classification corresponding to the specific intention (e.g., “positive (praise)” and “negative (complaint)”) and a second semantic classification not corresponding to the specific intention (e.g., “miscommunication (misintention)”), The classification means If the meaning of the phrase corresponds to the specific intent, classify the phrase into the first semantic classification (e.g., the context classification “positive (praise)” or “negative (complaint)”); classifying the phrase into the second semantic classification (e.g., the context classification "miscommunication") if the meaning of the phrase does not correspond to the specific intent; 4. The voice analysis support device according to claim 3,

[0103] (Appendix 5) An acquisition means for acquiring attribute information of the voice source (for example, "a mother with a kindergarten child" or "an elderly person who is not aware of the decline in taste"); The display control means displaying attribute information of the voice owner on the terminal of the analyst; 3. The voice analysis support device according to claim 2, [Explanation of symbols]

[0104] 10 VOC analysis support equipment 20 Knowledge Base 30 Terminals 100 VOC analysis support system 101 VOC acquisition department 102 Phrase Extraction Section 103 Context Acquisition Unit 104 Context Classification Unit 105 Display control unit 109 Storage section

Claims

1. A voice analysis support device that analyzes voice information related to a product or service collected from a voice owner, An acquisition means for acquiring information regarding a specific intention including a product specification intended by an analyst for the product or service and a phrase indicating a product intention corresponding to the product specification; An acquisition means for acquiring the voice information; an extraction means for extracting a voice phrase indicating a voice regarding the product or service from the voice information; a classification means for determining the product specification to which the voice phrase belongs from the meaning indicated by the voice phrase, determining whether the voice phrase has at least a positive meaning relationship, a negative meaning relationship, or an unintended meaning relationship with the product intention based on the phrase indicating the product intention corresponding to the product specification and the voice phrase, and classifying the voice phrase into a semantic classification according to the result of the determination; a storage means for storing the voice information in association with the voice phrase and the semantic classification into which the voice phrase is classified; A voice analysis support device comprising:

2. a display control means for displaying the voice phrases and the semantic classifications into which the voice phrases are classified on the terminal of the analyst; 2. The voice analysis support device according to claim 1, further comprising:

3. An acquisition means for acquiring information on the family structure of the voice subject, The display control means Displaying information on the family structure of the voice subject on the terminal of the analyst; 3. The voice analysis support device according to claim 2,

4. A voice analysis support method for analyzing voice information related to a product or service collected from a voice owner, comprising: The voice analysis support device An acquisition step of acquiring information regarding a specific intention including product specifications intended by an analyst for the product or service and a phrase indicating a product intention corresponding to the product specifications; An acquisition step of acquiring the voice information; an extraction step of extracting a voice phrase indicating a voice regarding the product or service from the voice information; a classification step of determining the product specification to which the voice phrase belongs based on the meaning indicated by the voice phrase, determining whether the voice phrase has at least a positive meaning relationship, a negative meaning relationship, or an unintended meaning relationship with the product intention based on the phrase indicating the product intention corresponding to the product specification and the voice phrase, and classifying the voice phrase into a semantic classification according to the result of the determination; a storage step of storing the voice information in association with the voice phrase and the semantic classification into which the voice phrase is classified; A voice analysis support method comprising the steps of:

5. Computer, An acquisition means for acquiring information regarding a specific intention including product specifications intended by an analyst for a product or service and a phrase indicating a product intention corresponding to the product specifications; An acquisition means for acquiring voice information regarding the product or service collected from voice subjects; an extraction means for extracting a voice phrase indicating a voice regarding the product or service from the voice information; a classification means for determining the product specification to which the voice phrase belongs from the meaning indicated by the voice phrase, determining whether the voice phrase has at least a positive meaning relationship, a negative meaning relationship, or an unintended meaning relationship with the product intention based on the phrase indicating the product intention corresponding to the product specification and the voice phrase, and classifying the voice phrase into a semantic classification according to the result of the determination; a storage means for storing the voice information in association with the voice phrase and the semantic classification into which the voice phrase is classified; A voice analysis support program to make it function as a voice analysis system.

Citation Information

Patent Citations

  • Information processor, customer needs analysis method and program

    JP2007226568A

  • Document classification system, document classification program, and document classification method

    JP2011170786A

  • Document classifying device, document classifying method, program, and storage medium

    JP2011198203A

  • System and method for identifying and proposing emoticons

    JP2017527881A

  • Information processing device and information processing method

    JP2019215825A

Cited By

  • Information providing device, information providing method, and recording medium

    WO2026176507A1