Methods of evaluating makeup behavior and cosmetics

Abstract

To provide methods of evaluating cosmetics and makeup behavior.SOLUTION: Provided is a makeup behavior evaluation method for evaluating a target makeup behavior on the basis of voice feature quantities during utterance before and after the target makeup behavior of a user.SELECTED DRAWING: None

Description

Technical Field

[0001] The present invention relates to a method for evaluating makeup behavior and a method for evaluating cosmetics.

Background Art

[0002] Conventionally, the development of cosmetics focusing on makeup behavior has been carried out. For example, Patent Document 1 describes a cleansing product that can reduce makeup behavior. Also, for example, Patent Document 2 describes a base cosmetic that is excellent in the feeling of use when applied to the skin, has good makeup retention, and can be easily removed (that is, can reduce makeup behavior).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] The present inventors have found that the change in the user's emotion due to the use of cosmetics is affected by various factors such as not only the characteristics (scent, feeling of use, effectiveness) of the cosmetics (contents), but also the appearance of the container and the contents, the method of use, etc. If it is possible to evaluate the makeup behavior by comprehensively grasping a plurality of factors without distinguishing them, a broad perspective can be obtained in the development of the entire cosmetic product (not only the contents but also the proposal of the appearance design and the method of use, etc.). Therefore, an object of the present invention is to provide a novel method for evaluating cosmetics and makeup behavior from the perspective of the emotion of the user of the cosmetics.

Means for Solving the Problems

[0005] The present invention for solving the above problems is a method for evaluating a target makeup behavior based on voice feature amounts during speech before and after the target makeup behavior of a user. According to the present invention, it is possible to evaluate a makeup behavior by using speech data of a user.

[0006] In a preferred form of the present invention, based on voice feature amounts during speech before and after the target makeup behavior, a change in an emotion estimation value before and after the target makeup behavior of the user is calculated, and the target makeup behavior is evaluated using the change as an index. According to the present invention, it is possible to evaluate the influence of a makeup behavior on the emotion of a user.

[0007] In a preferred form of the present invention, the emotion estimation value is derived by collating voice feature amounts during speech of the user with an estimation model showing the relationship between voice feature amounts during speech and emotions during speech created in advance. Thereby, an emotion estimation value can be obtained simply and objectively using speech data.

[0008] In a preferred form of the present invention, the emotion estimation value is an estimation value of any emotion selected from joy, sorrow, calm, anger, and energy level.

[0009] In a preferred form of the present invention, the voice feature amount includes any one of an interval of speech (interval), loudness of sound (volume), pitch of sound (pitch), length of speech (talk length), speed of speech (talk speed), and frequency of pauses in speech (pause).

[0010] Further, in a preferred form of the present invention, the makeup behavior includes use of a skin care cosmetic by the user himself / herself.

[0011] In addition, the present invention is a method for evaluating a cosmetic product, which evaluates a target cosmetic behavior using the above-described method for evaluating a cosmetic behavior of the present invention, and evaluates the cosmetic product used in the cosmetic behavior based on the evaluation result of the target cosmetic behavior.

Advantages of the Invention

[0012] According to the present invention, it is possible to evaluate the influence of a cosmetic behavior on the user's emotion. Further, according to the present invention, it is also possible to comprehensively grasp various elements included in a cosmetic behavior that can serve as a guideline for the product development of a cosmetic product, and evaluate the cosmetic product.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Embodiments for Carrying Out the Invention

[0014] In the present invention, "cosmetic behavior" means an action that a user can take in relation to the use of a cosmetic product. In addition, "actions that a user can take in relation to the use of a cosmetic product" include a series of normal actions for using the cosmetic product, such as opening the container, picking up the contents by hand, taking the contents with a cosmetic tool, applying to the skin, making the skin familiar with the hand, dropping (rinsing off) the cosmetic product, massaging, etc. Further, the part where the cosmetic product is used is not limited to the face, and the whole body such as the neck, décolletage, hands, arms, feet, etc. is targeted. For example, cosmetic behaviors including the use of general cosmetic products such as makeup using makeup cosmetics (e.g., foundation, eyeshadow, mascara, etc.), skin care using skin care cosmetics (e.g., cleansing agent, lotion, emulsion, etc.), and sun care using sun care cosmetics (e.g., sunscreen, etc.) can be mentioned. The targeted makeup behavior in the evaluation method according to the present invention is not particularly limited, but preferably includes the use of skin care cosmetics by the user himself / herself.

[0015] In the present invention, "emotion" refers to the feeling that occurs when one feels something, and it is a subjective thing that represents the mood inside the heart. Also, in the present invention, "emotion estimation value" refers to a value objectively estimated based on some external factors as to what kind of "emotion" the user has.

[0016] The evaluation method of the makeup behavior of the present invention evaluates the targeted makeup behavior based on the voice feature amounts during the user's speech before and after the targeted makeup behavior.

[0017] In the evaluation method according to the present invention, preferably, the change in the emotion estimation value obtained from the voice feature amounts during the user's speech before and after the targeted makeup behavior is used as an index to evaluate the targeted makeup behavior.

[0018] In the present invention, "voice feature amount" refers to information that can be obtained from the uttered voice. Examples of voice feature amounts include the interval between utterances (interval), the loudness of the sound (volume), the pitch of the sound (pitch), the length of the utterance (talk length), the speed of the utterance (talk speed), the frequency of pauses in the utterance (pause), and the like.

[0019] That is, before having the user perform the targeted makeup behavior to be evaluated and after having the user perform the targeted makeup behavior to be evaluated, the user is prompted to speak. By extracting the voice feature amounts during this speech, the emotion estimation values before and after the targeted makeup behavior can be obtained, and the change can be observed. At this time, the emotion estimation value can be derived using an estimation model showing the relationship between the voice feature amounts during speech and the emotion during speech created in advance.

[0020] Here, the above-mentioned "estimation model showing the relationship between the pre-created voice feature amounts during speech and the emotions during speech" can use, for example, an estimation model (multiple regression formula, discriminant formula, etc.) obtained by analyzing a plurality of voices expressing different emotions and finding the correlation between the voice feature amounts and the emotions by a statistical method. Also, as the above-mentioned estimation model, an estimation model (learning model) obtained by analyzing, by machine learning, a plurality of voice data expressing different emotions with the expressed emotions and the voice data paired can be used. As the estimation model, for example, a model that has learned the acoustic characteristics for each emotion, such as those described in Japanese Patent No. 6647722 and Japanese Patent No. 6664757, can be adopted. By obtaining an emotion estimation value using such an estimation model, it is possible to estimate, with a certain degree of objectivity, changes in emotions that the user does not clearly express with facial expressions or words.

[0021] Also, in the present invention, the emotion estimated as the emotion estimation value serving as an index is not particularly limited, but preferably includes at least any one of joy, sorrow, calm, anger, and energy.

[0022] Here, "energy" represents the degree of the power that is the source of mental and physical activities, such as human energy, vitality, activity power, and action power, which are required when a human generally engages in activities. In the present invention, it is defined as the relative degree in each person's subjectivity.

[0023] For example, after the targeted makeup action, if the emotion estimation values of joy, energy, and calm increase, the targeted makeup action can be evaluated as good. Also, after the targeted makeup action, if the estimation values of sorrow and anger decrease, the targeted makeup action can be evaluated as good. Also, when the change direction of the emotion estimation value is opposite to that described above, the targeted makeup action can be evaluated as not good. Also, from the perspective of evaluation in the development of cosmetics (products) assuming a wide range of users, it is preferable to use an estimated value of vitality (energy). This is because among the various purposes of users' makeup actions (wanting to be beautiful, wanting to be tightened, wanting to be healed, etc.), in relation to any of these purposes, an increase in vitality (energy) can be positioned as a positive emotion.

[0024] A system (software program) for obtaining an estimated value of emotion from voice data, including an evaluation model of the estimated value of emotion, can use, for example, voice emotion analysis AI (WEB Empath API) commercialized by Empath Co., Ltd.

[0025] The evaluation method of the present invention can be implemented, for example, by the following method. First, record the voice of the user during speech (pre-use voice) before the target makeup action. The pre-use voice is not particularly limited in terms of the content of the speech and the length of the speech as long as voice feature amounts can be obtained in the process of analyzing the voice described later. For example, a voice (template speech voice) obtained by having the user speak a preset template sentence may be acquired, or a voice (free speech voice) obtained by freely having the user answer (speak) to a certain question may be acquired. Preferably, both the template speech voice and the free speech voice are acquired.

[0026] Next, have the user perform the target makeup action. Next, in the same manner as the above pre-use voice, record the voice of the user during speech (post-use voice) after the target makeup action. Regarding the recording method and the content of the speech to be recorded, the matters described for the recording method and the recording content of the above pre-use voice can be applied.

[0027] Next, the pre-use voice and the post-use voice recorded above are each analyzed to obtain voice feature amounts. The method for analyzing the voice feature amounts is not particularly limited and can be determined according to the voice feature amounts to be obtained. For example, by obtaining the spectrogram of the recorded voice and analyzing this, voice feature amounts can be obtained. Also, the extraction of the voice feature amounts can generally be performed using commercially available voice analysis software.

[0028] Next, from the voice feature amounts for the pre-use voice obtained and the voice feature amounts for the post-use voice, emotion estimation values are each derived using the above-described estimation model. By comparing the derived emotion estimation values, it is possible to analyze the change in the user's emotion before and after the targeted makeup action.

[0029] By performing the above analysis on a plurality (for example, 5 or more, preferably 10 or more) of users, it becomes possible to generalize the evaluation of the targeted makeup action.

[0030] The above method is an example, and any method may be used as long as "the emotion estimation value derived from the voice feature amounts obtained from the pre-use voice and the emotion estimation value derived from the voice feature amounts obtained from the post-use voice can be compared".

[0031] In the evaluation method according to the present invention, for the recording of the voice, the analysis of the voice, the extraction of the voice feature amounts, the calculation of the emotion estimation value, and the analysis of the change, all different devices may be used, or a plurality of steps (for example, the analysis of the voice, the extraction of the voice feature amounts, the calculation of the emotion estimation value, the analysis of the change in the emotion estimation value) may be performed by one device, or all the steps may be performed by one device. Also, among the above steps, the extraction of the voice feature amounts, the derivation of the emotion estimation value using the estimation model, the analysis of the change in the emotion estimation value, etc. can be performed by causing a general-purpose computer to function using a computer program.

Example

[0032] Hereinafter, the present invention will be described more specifically based on examples. However, the technical scope of the present invention is not limited to the following examples.

[0033] <Test Example> Based on the change in the estimated emotional value of the user by continuously using a group of cosmetics (cleansing agents, facial washes, lotions, and moisturizing liquids), the cosmetic behavior of using this group of cosmetics was evaluated.

[0034] The users were 10 women aged 35 to 49.

[0035] <Evaluation Method> (1) A questionnaire survey was conducted on 10 users. All users were in a made-up state. (2) For each user, the pre-use voice was recorded. As the pre-use voice, two types were obtained for each user: a fixed-form speech voice in which a plurality of fixed short texts were spoken, and a free-form speech voice in which free answers (speeches) were given to questions based on the questionnaire survey conducted in (1) above. (3) The 10 users were each made to use the above group of cosmetics. Specifically, each of the 10 users removed their makeup using a cleansing agent and then washed their face using a facial wash. After that, each person used a lotion and a moisturizing liquid. (4) For each user, the post-use voice was recorded. As the post-use voice, two types were obtained for each user: a fixed-form speech voice in which the same plurality of fixed short texts as in (2) above were spoken, and a free-form speech voice in which free answers (speeches) were given about the actual feelings of using each of the group of cosmetics used in (3) above. (5) Separately, a questionnaire survey was conducted on the users regarding the satisfaction after use of the facial wash, lotion, and moisturizing liquid. The questionnaire items included items about various elements of the cosmetics, and the satisfaction after use was calculated by scoring these. (6) The obtained pre-use voice and post-use voice were analyzed using voice analysis software manufactured by Empath Co., Ltd. to obtain voice feature quantities. The voice feature quantities were the interval between utterances (interval), the loudness of the voice (volume), the pitch of the voice (pitch), the length of the utterance (talk length), the speed of the utterance (speed), and the frequency of pauses in the utterance (pause). (7) For each user, an estimated value of the emotion of "energy" before and after using the target cosmetic was calculated based on the voice feature quantities obtained in (6). The analysis results are shown in FIGS. 1 to 3.

[0036] (Result 1) Comparison of energy levels before and after makeup application Regarding the fixed-form utterance voice, no change was observed in the estimated value of energy before and after use. However, as a result of the analysis of the free-form utterance voice, the estimated value of the energy of the user after using the target cosmetic was found to be higher than the estimated value of the energy of the user before using the target cosmetic (that is, it is clear that the makeup behavior of using the above group of cosmetics tends to improve the energy of the user) (FIG. 1). Also, when the analysis was performed with the user's age limited to 43 to 45 years old (5 users), the energy level was improved by the use of the target cosmetic in both the fixed-form utterance voice and the free-form utterance voice (FIG. 2). That is, it can be evaluated as good that the makeup behavior of using the above group of cosmetics, or the above group of cosmetics, tends to improve the energy of the person who uses them. From the above, it has become clear that according to the evaluation method according to the present invention, it is possible to evaluate makeup behavior and cosmetics based on the voice obtained from the user's utterance.

[0037] (Result 2) Relationship between satisfaction after using cosmetics and estimated emotion value The relationship between the results of the questionnaire survey conducted in (5) of the above <Test Method> and the estimated value of the energy of the user is shown in FIG. 3. Both users who were highly satisfied after using each cosmetic product (labeled "high" in Figure 3) and users who were dissatisfied after using each cosmetic product (labeled "low" in Figure 3) showed a positive difference in vitality levels before and after makeup application (the value of vitality level after using the cosmetic product - the vitality level before using the cosmetic product). That is, it was revealed that using the above group of cosmetic products tended to improve the vitality level. From the above, it became clear that according to the evaluation method of the present invention, it is possible to evaluate the target cosmetic product by considering potential factors that do not manifest in questionnaire surveys such as satisfaction levels for users.

Industrial Applicability

[0038] The present invention can be applied to the development of cosmetic products.

Claims

【Claim 1】 A method for evaluating a makeup behavior, which evaluates the target makeup behavior based on voice feature amounts during speech before and after the target makeup behavior in a user.

Images