method

Abstract

Improve the technology for estimating changes in customer satisfaction. [Solution] A method to be executed by an information processing device 10 comprising a control unit 102 and a storage unit 104 that stores a machine learning-trained estimation model, wherein the control unit 102 uses one or more sensors 20 to acquire behavioral information indicating the behavior of one or more customers who have visited the store, and uses the estimation model to estimate the change in customer satisfaction from arrival to departure based on the change in behavioral information.

Description

Technical Field

[0001] This disclosure relates to a method.

Background Art

[0002] Conventionally, techniques for estimating changes in customer satisfaction have been known. For example, Patent Document 1 discloses a technique related to an apparatus that can appropriately provide a sample to customers targeted by a manufacturer or the like that distributes samples and can obtain responses to a questionnaire regarding the appropriate sample.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] With a method of requesting customers to respond to a questionnaire, there may be cases where responses cannot be obtained because answering the questionnaire is troublesome or the questionnaire itself is forgotten. Further, when requesting customers who visit a store to respond to a questionnaire at a later date, the accuracy of the response content may decrease due to the time difference between the visit and the response.

[0005] In view of such circumstances, an object of the present disclosure is to improve the technique for estimating changes in customer satisfaction.

Means for Solving the Problems

[0006] A method according to an embodiment of the present disclosure is a method executed by an information processing apparatus including a control unit and a storage unit that stores a machine-learned estimation model, wherein the control unit Using one or more sensors, acquire behavioral information indicating the behavior of one or more customers who visit the store, Using the estimation model described above, the change in customer satisfaction from arrival to departure is estimated based on the changes in the behavioral information. Includes. [Effects of the Invention]

[0007] According to one embodiment of this disclosure, the technique for estimating changes in customer satisfaction is improved. [Brief explanation of the drawing]

[0008] [Figure 1] This block diagram shows a schematic configuration of a system according to one embodiment of the present disclosure. [Figure 2] This is a flowchart showing the operation of an information processing device according to one embodiment of this disclosure. [Modes for carrying out the invention]

[0009] The embodiments of this disclosure will be described below with reference to the drawings.

[0010] (Summary of the embodiment) Referring to Figure 1, an overview of System 1 according to one embodiment of this disclosure will be described. System 1 comprises an information processing device 10 and one or more sensors 20. The information processing device 10 and the sensors 20 are connected to each other via a network 30 such as the Internet.

[0011] The information processing device 10 is one or multiple computers that can communicate with each other. The information processing device 10 communicates with the sensor 20 and continuously acquires information detected by the sensor 20.

[0012] Sensor 20 is a device capable of monitoring behavioral information indicating the actions of one or more customers who visit the store, such as a camera or microphone. Examples of stores include fixed stores and mobile stores.

[0013] First, an overview of this embodiment will be described, and details will be described later. The method according to this embodiment is executed by an information processing device 10 comprising a control unit 102 and a storage unit 104 that stores a machine learning-trained estimation model. The method includes the control unit 102 acquiring behavioral information indicating the behavior of one or more customers who have visited the store using one or more sensors 20, and using the estimation model to estimate the change in customer satisfaction from arrival to departure based on the change in behavioral information.

[0014] According to this embodiment, changes in customer satisfaction can be estimated immediately and on the spot. This reduces the need to ask customers to answer questionnaires, thereby eliminating the stress customers experience from answering questionnaires and the decrease in the accuracy of their answers due to the time lag between their visit and when they answer the questionnaire.

[0015] Next, we will describe each component of System 1 in detail.

[0016] (Configuration of the information processing device 10) The information processing device 10 comprises a communication unit 100, a control unit 102, and a storage unit 104.

[0017] The communication unit 100 includes at least one communication interface connected to the network 30. The communication interface supports, for example, mobile communication standards such as 4G (4th generation) or 5G (5th generation), or wired LAN (Local Area Network) communication standards or wireless LAN communication standards, but is not limited to these and may support any communication standard.

[0018] The control unit 102 includes one or more processors, one or more programmable circuits, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for specific processing, but is not limited thereto. The programmable circuit is, for example, an FPGA (Field-Programmable Gate Array), but is not limited thereto. The dedicated circuit is, for example, an ASIC (Application Specific Integrated Circuit), but is not limited thereto. The control unit 102 controls the operation of the entire information processing device 10.

[0019] The storage unit 104 includes one or more memories. Each memory included in the storage unit 104 may function as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 104 stores any information used for the operation of the information processing device 10. The storage unit 104 stores in advance a learned estimation model for estimating customer satisfaction. Further, the storage unit 104 may store, for example, a system program, an application program, embedded software, and any data used for estimating customer satisfaction. The information stored in the storage unit 104, for example, the estimation model, may be updated by information acquired from the network 30 via the communication unit 100, for example.

[0020] (Configuration of Sensor 20) The sensor 20 includes a camera capable of imaging one or more customers who have come to the store, and / or a microphone capable of acquiring the voices of customers. The sensor 20 may include a vital sensor 20 capable of measuring the pulse of a customer. In the present embodiment, the sensor 20 includes a surveillance camera installed inside or outside the store, and a microphone worn by a store clerk. The microphone may be installed inside or outside the store.

[0021] (Operation Flow of Information Processing Device 10) Referring to FIG. 2, the operation of the information processing apparatus 10 according to the present embodiment will be described. Hereinafter, the communication between the information processing apparatus 10 and the sensor 20 is performed via the communication unit 100 and the network 30.

[0022] S101: The control unit 102 uses one or more sensors 20 to acquire behavior information indicating the behavior of one or more customers who have visited the store.

[0023] The behavior information may include information indicating the expression or gesture of the customer detected by the camera and / or information indicating the volume, pitch, intonation, tone of voice or speech content of the customer's voice acquired by the microphone. The behavior information may include information indicating the pulse of the customer detected by the vital sensor 20. A gesture indicates the movement of the customer's face, hands, arms, legs or torso.

[0024] S102: The control unit 102 uses the estimation model to estimate the change in the customer's satisfaction level based on the change in the behavior information from the time of entering the store to the time of leaving the store.

[0025] When the customer's expression becomes a smiling face, when the tone of voice becomes a cheerful tone, when a favorable phrase (e.g., "good" or "excellent") appears in the speech content, etc., when the customer's reaction is favorable, the control unit 102 may estimate that the satisfaction level has increased. When the customer's expression becomes gloomy, when the tone of voice becomes a regretful tone, when the customer yawns or suppresses a yawn, etc., when the customer's reaction is not favorable, the control unit 102 may estimate that the satisfaction level has decreased.

[0026] The change in the satisfaction level includes the change in the satisfaction level for each scene. The scene may include, for example, the scenes at the time of the customer's arrival at the store, during customer service, when serving food and drinks (e.g., tea), when browsing products, during business negotiations, and when leaving the store, but is not limited thereto.

[0027] For example, when a customer enters or leaves the store, the control unit 102 may estimate changes in satisfaction based on changes in the customer's facial expressions and gestures. For example, when serving customers, providing food and beverages, browsing products, and conducting business negotiations, the control unit 102 may estimate changes in satisfaction based on the customer's facial expressions and gestures, as well as the volume, pitch, intonation, tone of voice, and content of what the customer says.

[0028] As described above, the method according to this embodiment is executed by an information processing device 10 comprising a control unit 102 and a storage unit 104 that stores a machine learning-trained estimation model. The method includes the control unit 102 acquiring behavioral information indicating the behavior of one or more customers who have visited the store using one or more sensors 20, and using the estimation model to estimate the change in customer satisfaction from arrival to departure based on the change in behavioral information.

[0029] This configuration allows for the immediate and on-the-spot estimation of changes in customer satisfaction. This reduces the need to request customers to answer questionnaires, thereby eliminating the stress customers experience from answering questionnaires and the decrease in the accuracy of their responses due to the time lag between their visit and when they answer the questionnaire.

[0030] While this disclosure has been described based on the drawings and embodiments, it should be noted that those skilled in the art can make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions included in each component or step can be rearranged in a logically consistent manner, and multiple components or steps can be combined into one or separated. For example, in the embodiments described above, an embodiment is also possible in which the configuration and operation of the information processing device 10 or sensor 20 are distributed among multiple computers that can communicate with each other.

[0031] The control unit 102 may estimate the cause of the change in satisfaction for each scene based on the change in satisfaction for each scene for multiple customers. This allows for the statistical estimation of the cause of the change in satisfaction.

[0032] The control unit 102 may estimate that the store's exterior, interior, or cleanliness is the cause of the change if the percentage of customers whose satisfaction level increased or decreased during their visit exceeds a predetermined percentage. The control unit 102 may estimate that the quality of the product (e.g., taste) is the cause of the change if the percentage of customers whose satisfaction level increased or decreased during the provision of food and beverages exceeds a predetermined percentage. The control unit 102 may estimate that the quality of the product, the display method, or the description is the cause of the change if the percentage of customers whose satisfaction level increased or decreased during product browsing exceeds a predetermined percentage. The control unit 102 may estimate that the employee's response is the cause of the change if the percentage of customers whose satisfaction level increased or decreased during customer service or negotiations with a particular employee exceeds a predetermined percentage. The control unit 102 may estimate that the materials used in negotiations are the cause of the change if the percentage of customers whose satisfaction level decreased during negotiations with any employee exceeds a predetermined percentage.

[0033] The control unit 102 may estimate the cause of the change in satisfaction level from the customer's gaze at the time the satisfaction level changes. For example, if the customer's gaze at a specific object (e.g., store interior, merchandise, staff, or sales materials) is directed at a specific object when the satisfaction level changes, and if the frequency of this gaze is greater than a predetermined frequency, or if the duration of this gaze is greater than a predetermined duration, the control unit 102 may estimate that the object is the cause of the change. To detect the customer's gaze, the sensor 20 may include a device such as an eye tracker, or the control unit 102 may process images acquired by a camera.

[0034] The control unit 102 may estimate the cause of the change in satisfaction level from the customer's utterances when the satisfaction level changes. For example, if keywords related to a specific object (e.g., store interior, specific product name, product price) appear in the customer's utterances when the satisfaction level changes, or if they appear at a frequency greater than a predetermined frequency, the control unit 102 may estimate that the object referred to by those keywords is the cause of the change.

[0035] The control unit 102 may update its estimation model using supervised learning, with changes in behavioral information as input data and response information from customer satisfaction surveys as training data. This can improve the accuracy of customer satisfaction estimation. [Explanation of Symbols]

[0036] 1 System 10 Information Processing Devices 100 Communications Department 102 Control Unit 104 Storage section 20 sensors 30 Networks

Claims

1. A method to be performed by an information processing device comprising a control unit and a storage unit for storing a machine learning-based estimation model, wherein the control unit, Using one or more sensors, behavioral information is acquired that shows the behavior of one or more customers who visit the store. Using the estimation model described above, the change in customer satisfaction from arrival to departure is estimated based on the changes in the behavioral information. Methods that include...

2. A method according to claim 1, wherein the sensor includes a camera capable of capturing images of one or more customers, and / or a microphone capable of acquiring the voices of one or more customers, The method wherein the behavioral information includes information indicating the customer's facial expression or gestures detected by the camera, and / or the volume, pitch, intonation, tone of voice, or content of speech of the customer detected by the microphone.

3. A method according to claim 1, wherein the change in satisfaction includes the change in satisfaction for each scene, and the scenes include the customer's arrival, customer service, provision of food and beverages, browsing of products, business negotiations, and departure from the store.

4. A method according to claim 3, further comprising estimating the cause of the change in satisfaction for each scene based on the change in satisfaction for each scene for a plurality of customers.

5. A method according to claim 4, wherein estimating the cause includes presuming that there is a problem with the exterior, interior, or cleanliness of the store if the proportion of customers who have low or decreased satisfaction with their visit exceeds a predetermined proportion.

Images