Information processing system and program

The information processing system addresses the challenge of managing customer emotions in automated sales by using emotion detection and adaptive talk scripts to improve satisfaction through personalized interactions.

JP2024158683APending Publication Date: 2024-11-08SOFTBANK GROUP CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2023074078
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-28
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Existing systems fail to effectively manage customer emotions during sales interactions, leading to suboptimal customer satisfaction in automated sales environments.

Method used

An information processing system that includes a storage unit for talk scripts, an emotion detection mechanism, and a selection unit to adapt sales talk based on customer emotions and attributes, using machine learning to optimize the sales process.

Benefits of technology

Enhances customer satisfaction by dynamically adjusting sales strategies to address negative emotions and align with customer needs, mimicking the performance of a skilled salesperson.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024158683000001_ABST
    Figure 2024158683000001_ABST
Patent Text Reader

Abstract

To allow a robot to provide sales talk with high customer satisfaction such as sales talk of a salesperson with the highest business performance to a user.SOLUTION: In a system in which a server controls a robot through a communication network, the server 100 includes: a storage unit for storing a talk step including a plurality of talk scripts in which talk contents of a sales talk to a customer by an electronic device is determined; an emotion value determination unit for determining an emotion value indicating emotion of the customer while the electronic device talks with the customer based on one talk step in the plurality of talk steps stored in the storage unit; and a selection unit for selecting a talk step next to one talk step from the plurality of talk steps stored in the storage unit so that customer satisfaction of business activity by the electronic device becomes higher based on the emotion value of the customer, which is determined by the emotion value determination unit.SELECTED DRAWING: Figure 2
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing system and a program. [Background technology]

[0002] Patent Document 1 describes a robot device that is capable of acting autonomously in response to external stimuli and its own internal state. [Prior art document] [Patent documents] [Patent Document 1] JP 2007-125629 A Summary of the Invention [Means for solving the problem]

[0003] According to one embodiment of the present invention, an information processing system is provided. The information processing system may include a storage unit that stores talk steps including a plurality of talk scripts that define talk content of a sales talk to a customer by an electronic device. The information processing system may include an emotion value determination unit that determines an emotion value indicating an emotion of the customer while the electronic device is talking with the customer based on one talk step of the plurality of talk steps stored in the storage unit. The information processing system may include a selection unit that selects a talk step next to the one talk step from the plurality of talk steps stored in the storage unit based on the emotion value of the customer determined by the emotion value determination unit so as to increase customer satisfaction with the sales activity by the electronic device.

[0004] In the information processing system, the selection unit may select the next talk step so that the customer's emotion transitions from a negative emotion to a positive emotion when the emotion value indicates that the customer's emotion is negative while the electronic device is talking to the customer based on the one talk step.

[0005] In any of the information processing systems, the selection unit may select that the electronic device asks the customer a question to clarify the factor that caused the customer to feel negative emotions while the electronic device was talking to the customer based on the one talk step.

[0006] Any of the information processing systems may further include an information acquisition unit that acquires customer-related information related to the customer, and an attribute identification unit that identifies attributes of the customer based on the customer-related information acquired by the information acquisition unit, and the selection unit may select the next talk step further based on the attributes of the customer identified by the attribute identification unit.

[0007] In any of the information processing systems, the memory unit may further store marketing research results related to the products that the electronic device sells to the customer, and the selection unit may select the next talk step further based on the research results stored in the memory unit.

[0008] In any of the information processing systems, the memory unit may further store learning data including attribute data indicating a customer's attributes, an emotional value of the customer while the electronic device is talking with the customer based on a talk step, and an emotional value of the customer while the electronic device is talking with the customer based on the talk step next to the talk step, and the information processing system further includes a model generation unit that uses the multiple learning data stored in the memory unit as teacher data to generate by machine learning a selection model that selects the next talk step after the one talk step from the customer's attributes indicated by the customer's attribute data and the emotional value of the customer while the electronic device is talking with the customer based on the one talk step so that the emotional value of the customer is higher, and the selection unit may use the selection model generated by the model generation unit to select the next talk step from the attributes of the customer identified by the attribute identification unit and the emotional value of the customer determined by the emotional value determination unit.

[0009] In any of the above information processing systems, the memory unit may further store target demographic information indicating the target demographic of each product that the electronic device sells to the customer, and the selection unit may select the next talk step based further on the target demographic information stored in the memory unit so that the electronic device sells to the customer a product whose target demographic includes the attribute of the customer identified by the attribute identification unit, and the information processing system may further include an update unit that updates the target demographic information stored in the memory unit so that the target demographic of the product purchased by the customer includes the attribute of the customer when, as a result of sales activities by the electronic device to the customer, the customer purchases a product whose target demographic does not include the attribute of the customer.

[0010] Any of the information processing systems may further include an information acquisition unit that acquires response information indicating the customer's response to a question posed to the customer by the electronic device while the electronic device is talking with the customer based on the one talk step, and the emotion value determination unit may determine the emotion value of the customer based on the response information of the customer acquired by the information acquisition unit.

[0011] Any of the information processing systems may further include the electronic device.

[0012] According to one embodiment of the present invention, there is provided a program for causing the information processing system to function.

[0013] The above summary of the invention does not list all of the necessary features of the present invention. Also, subcombinations of these features may also be inventions. [Brief description of the drawings]

[0014] [Figure 1] 1 shows an example of the overall configuration of a system 10 according to the present embodiment. [Diagram 2] 1 shows a schematic functional block configuration of a robot 200 and a server 100. [Diagram 3] An example of a hardware configuration of a computer 1200 that functions as at least a part of the server 100 or the robot 200 is shown in schematic form. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0016] 1 illustrates an example of an overall configuration of a system 10 according to the present embodiment. The system 10 may include a server 100 and a robot 200. The system 10 may include a plurality of robots 200. The server 100 may function as an information processing system. The system 10 may be an example of an information processing system.

[0017] The robot 200 is placed, for example, in a car dealership. The robot 200 is placed, for example, in a home showroom. The robot 200 is placed, for example, in a home electronics retail store. The robot 200 is placed in any other store. FIG. 1 shows an example in which the robot 200 is placed in a car dealership.

[0018] The server 100 is provided remotely from the robot 200. The server 100 can control the robot 200 through a communication network 50. For example, the server 100 acquires sensor information detected by the robot 200 through the communication network 50, determines an action to be performed by the robot 200 based on the acquired sensor information, and transmits control information through the communication network 50 to instruct the robot 200.

[0019] For example, the robot 200 acquires various types of information detected by sensors, such as the voice and image of the user 20 and information on an external force received by the robot 200, and transmits the information to the server 100. Based on the information acquired from the robot 200, the server 100 generates control information for controlling the robot 200.

[0020] In the system 10, the server 100 may execute processes for processing various information to determine the behavior of the robot 200, and processes for determining the behavior of the robot 200 based on the results of processing the various information. Note that part or all of these processes may be executed by the robot 200. In this case, part of the robot 200 functions as an information processing system.

[0021] The system 10 according to the present embodiment executes a process of conducting sales activities for a user 20 using a robot 200. The robot 200 may be a humanoid robot. The robot 200 may be a non-humanoid robot. The robot 200 may be an example of an electronic device. The user 20 is a user who uses the robot 200. The user 20 may be an example of a customer.

[0022] The server 100 has a function of selecting, for example, a sales talk to be given to the user 20 by the robot 200. For example, the server 100 pre-stores talk steps including a plurality of talk scripts in which the talk contents of the sales talk to be given to the user 20 by the robot 200 are defined. The server 100 selects one talk step from the plurality of pre-stored talk steps, and causes the robot 200 to talk to the user 20 using the one talk step.

[0023] The talk steps are classified, for example, by talk theme. The talk theme includes, for example, "greetings". The talk theme includes, for example, "small talk". The talk theme includes, for example, "information gathering". The talk theme includes, for example, "product proposal". The talk theme includes, for example, "explanation of the proposed product". The talk theme includes, for example, "question and answer session". The talk theme includes, for example, "confirmation of product purchase". The talk theme includes, for example, "explanation of accounting procedures". The talk theme includes, for example, "seeing someone off". The talk theme may include any other theme.

[0024] For example, a talk step whose talk theme is classified as "greetings" includes multiple talk scripts such as "Good morning," "Welcome," "Thank you for coming on this rainy day," etc. For example, a talk step whose talk theme is classified as "small talk" includes multiple talk scripts such as "It's hot again today!", "Yesterday's Japan national soccer team match was exciting!", etc.

[0025] For example, a talk step whose talk theme is classified as "information gathering" includes a plurality of talk scripts that collect information for directly specifying a car that the user 20 wants to purchase, such as "What is your favorite car color?", "What type of car do you want?", "Which is better, a hybrid car or an electric car?", etc. Also, for example, a talk step whose talk theme is classified as "information gathering" includes a plurality of talk scripts that collect information for indirectly specifying a car that the user 20 wants to purchase, such as "Do you have children?", "Are you interested in the outdoors?", "Do you spend your days off camping?", etc.

[0026] For example, a talk step with a talk theme classified as "product proposal" includes multiple talk scripts such as "For customers who like black, we recommend this car A!", "Since you have two small children, this family car B is definitely the right choice!", "How about SUV-type car C, which has become a hot topic due to the commercial featuring ▽▽?", and "For customers who are considering purchasing an electric car, we think electric car D, which is currently very popular among young people, is perfect!".

[0027] For example, a talk step whose talk theme is classified as "explanation of the proposed product" includes multiple talk scripts for explaining the merits of the proposed product, such as "The advantage of car A is that it is maneuverable and has a large trunk," and "Family car B has sliding doors, so you can easily carry children in it." Also, for example, a talk step whose talk theme is classified as "explanation of the proposed product" includes multiple talk scripts for explaining the demerits of the proposed product, such as "The disadvantage of car A is that it has slightly poor fuel efficiency compared to cars of the same size," and "The price of family car B is slightly above the customer's budget."

[0028] For example, a talk step whose talk theme is classified as "Question and Answer" includes a plurality of talk scripts in which the robot 200 answers questions from the user 20, such as "The price of car A is XXX million yen," "The fuel efficiency of family car B is △△ km / L," "The color variations of SUV-type car C are white, black, and silver," "The continuous driving distance of electric car D is □□ km," etc. Also, for example, a talk step whose talk theme is classified as "Question and Answer" includes a plurality of talk scripts in which the robot 200 asks questions to the user 20, such as "We can add a car navigation system as an option. What do you think?", "Didn't you like the car we proposed?", "Are you looking for a car with better fuel efficiency?", "We can give you a 10% discount now. What do you think?", etc.

[0029] For example, a talk step with a talk theme classified as "Confirmation of product purchase" includes multiple talk scripts such as "Is it correct that you would like to purchase car A?", "Thank you for purchasing family car B!", "We understand that you will not purchase SUV type car C this time.", etc. For example, a talk step with a talk theme classified as "Explanation of accounting procedures" includes multiple talk scripts such as "Payment can be made by electronic money, credit card, or cash.", "Please wait a moment as a salesperson will assist you separately.", etc. For example, a talk step with a talk theme classified as "Seeing off" includes multiple talk scripts such as "We look forward to seeing you again.", "Thank you very much for using our store today.", etc.

[0030] The server 100 has, for example, a function of determining an emotion value indicating an emotion of the user 20. The server 100 determines, for example, an emotion value of the user 20 while the robot 200 is talking with the user 20 based on one talk step selected by the server 100.

[0031] The emotion value of the user 20 may include a type of emotion of the user 20 and a value indicating the positive or negative emotion of the user 20. The types of emotions of the user 20 include "joy", "pleasure", "comfort", "relief", "excitement", "relief", "fulfillment", "anger", "sorrow", "discomfort", "anxiety", "sadness", "concern", and "emptiness". Note that these are merely examples and are not limited to these. The value indicating the positive or negative emotion of the user 20 indicates a positive value if the emotion of the user 20 is a positive emotion accompanied by a sense of pleasure or comfort, such as "joy", "pleasure", "comfort", "relief", "excitement", "relief", and "fulfillment", and the more positive the emotion, the larger the value. If the emotion of the user 20 is a negative emotion such as "anger", "sorrow", "discomfort", "anxiety", "sadness", "concern", and "emptiness", the value indicates a negative value, and the more negative the emotion, the larger the absolute value of the negative value. If the emotion of the user 20 is not any of the above ("normal"), the value indicating the positive or negative indicates a value of 0.

[0032] The server 100 selects a talk step next to one talk step based on, for example, an emotional value of the user 20 while the robot 200 is talking to the user 20 based on the one talk step selected by the server 100. The server 100 selects the next talk step so that, for example, customer satisfaction in the sales activity by the robot 200 is increased.

[0033] The server 100 selects one talk step from among a plurality of talk steps based on, for example, a story of a sales talk given by the robot 200 to the user 20. Here, an example will be described in which the server 100 selects one talk step from among a plurality of talk steps when the sales talk is a story in the order of "greeting", "information gathering", "product proposal", "explanation of the proposed product", "confirmation of product purchase", and "seeing off".

[0034] For example, the server 100 selects a first talk step from among a plurality of talk steps whose talk theme is classified as "greetings." The server 100 selects the first talk step based on, for example, the emotion value of the user 20 before the robot 200 starts talking with the user 20.

[0035] Next, the server 100 selects a second talk step from among the multiple talk steps whose talk theme is classified as "information gathering". For example, the server 100 selects the second talk step based on the emotion value of the user 20 while the robot 200 is talking with the user 20 based on the first talk step whose talk theme is classified as "greeting".

[0036] Next, the server 100 selects a third talk step from among the multiple talk steps whose talk theme is classified as "product proposal". For example, the server 100 selects the third talk step based on the emotion value of the user 20 while the robot 200 is talking with the user 20 based on the second talk step whose talk theme is classified as "information gathering".

[0037] Next, the server 100 selects a fourth talk step from among the multiple talk steps whose talk theme is classified as "explanation of proposed product". For example, the server 100 selects the fourth talk step based on the emotion value of the user 20 while the robot 200 is talking with the user 20 based on the third talk step whose talk theme is classified as "product proposal".

[0038] Next, the server 100 selects a fifth talk step from among the multiple talk steps whose talk theme is classified as "confirmation of product purchase". For example, the server 100 selects the fifth talk step based on the emotion value of the user 20 while the robot 200 is talking with the user 20 based on the fourth talk step whose talk theme is classified as "explanation of the proposed product".

[0039] Finally, the server 100 selects a final talk step from among the multiple talk steps whose talk theme is classified as "seeing off." For example, the server 100 selects the final talk step based on the emotion value of the user 20 while the robot 200 is talking to the user 20 based on the fifth talk step whose talk theme is classified as "confirming product purchase."

[0040] The server 100 may interrupt the story of the sales talk given by the robot 200 to the user 20 based on the emotion value of the user 20 while the robot 200 is talking to the user 20. For example, in a case where the sales talk is a story of "product proposal", "explanation of the proposed product", and "confirmation of product purchase" in that order, if the emotion value of the user 20 while the robot 200 is talking to the user 20 based on one talk step whose talk theme is classified as "explanation of the proposed product" indicates that the emotion of the user 20 is negative, the server 100 may select the next step of the one talk step from among multiple talk steps whose talk theme is classified as "question and answer", rather than from among multiple talk steps whose talk theme is classified as "confirmation of product purchase". Thereafter, in response to the fact that the emotion value of the user 20 during the robot 20's talk with the user 20 based on one talk step whose talk theme is classified as "question and answer" indicates that the emotion of the user 20 is positive, the server 100 may select the next step of the one talk step from among a plurality of talk steps whose talk theme is classified as "confirmation of product purchase". In this way, the robot 200 may resume the sales talk story to the user 20.

[0041] According to the system 10 of the present embodiment, the robot 200 selects a talk step following one talk step in consideration of the feelings of the user 20 while the robot 200 is talking to the user 20 based on the one talk step, and causes the robot 200 to talk with the user 20 in the selected talk step. As a result, the system 10 of the present embodiment allows the robot 200 to provide the user 20 with sales talk that has high customer satisfaction, just like the sales talk of the best-performing salesperson.

[0042] 2 shows a schematic functional block configuration of the robot 200 and the server 100. First, the functional block configuration of the robot 200 will be described. The robot 200 includes a sensor unit 210, an information processing unit 220, a control target 230, and a communication unit 240. The information processing unit 220 may be a processor such as an MPU. The communication unit 240 is responsible for communication with the server 100. The communication unit 240 may be a communication device such as a network IF.

[0043] The control target 230 includes a speaker. The control target 230 includes a display unit. The display unit may be disposed at any position of the robot 200, such as the chest of the robot 200. The control target 230 includes LEDs installed in the eyes or the like. The control target 230 includes motors and the like that drive movable parts of the robot 200, such as the limbs and head.

[0044] The sensor unit 210 has various sensors such as a microphone 211, a gyro sensor 212, a motor sensor 213, a camera 214, an infrared sensor 215, and a battery remaining amount sensor 216. It is not essential that the sensor unit 210 has all of these sensors, and the sensor unit 210 may have sensors other than these.

[0045] The microphone 211 acquires surrounding sounds. For example, the microphone 211 acquires the voice of a customer. The gyro sensor 212 detects the angular velocity of the entire robot 200 and each part of the robot 200. The motor sensor 213 detects the rotation angle of the drive shaft of the motor that drives the movable part of the robot 200. The camera 214 captures images using visible light and generates image data for videos and still images. The infrared sensor 215 detects surrounding objects using infrared rays. The battery remaining capacity sensor 216 detects the remaining capacity of the battery equipped in the robot 200.

[0046] The sensor unit 210 outputs various types of sensor information, such as voice data acquired by the microphone 211, an image captured by the camera 214, an angular velocity detected by the gyro sensor 212, a rotation angle detected by the motor sensor 213, a remaining capacity detected by the battery remaining amount sensor 216, and object information detected by the infrared sensor 215, to the information processing unit 220. The information processing unit 220 supplies the acquired sensor information to the communication unit 240, and transmits the information to the server 100. Furthermore, based on the control information acquired from the server 100, the information processing unit 220 causes the speaker of the robot 200 to speak, causes an LED of the robot 200 to emit light, and causes limbs and the like of the robot 200 to operate.

[0047] Next, a functional block configuration of the server 100 will be described. The server 100 includes an information processing unit 110, a communication unit 120, and a storage unit 130. The information processing unit 110 includes a control unit 111, an emotion value determination unit 112, a selection unit 113, an attribute identification unit 114, a model generation unit 115, and an update unit 116. Note that it is not essential that the information processing unit 110 includes all of these units.

[0048] The communication unit 120 is responsible for communication with various devices. For example, the communication unit 120 is responsible for communication with the robot 200. The communication unit 120 may be responsible for communication with external devices other than the robot 200. The communication unit 120 may be a communication device such as a network IF.

[0049] The information acquisition unit 122 acquires various types of information. For example, the information acquisition unit 122 acquires sensor information detected by the sensor unit 210 of the robot 200.

[0050] The information acquisition unit 122 acquires, for example, customer-related information related to a customer. The customer-related information includes, for example, image data of the customer. The customer-related information includes, for example, voice data of the customer. The customer-related information may include any other data related to the customer.

[0051] The information acquisition unit 122 acquires, for example, the results of marketing research related to the product that the robot 200 sells to the customer. The research results are, for example, statistical information published on the Internet. More specifically, the research results are information such as "XX% of men in their 40s are willing to purchase car Y made by company X."

[0052] The information acquisition unit 122 acquires, for example, product-related information related to each product sold by the robot 200 to a customer. The product-related information includes, for example, the price of each product. The product-related information includes, for example, advantages of each product. The product-related information includes, for example, disadvantages of each product. The product-related information includes, for example, target demographic information indicating the target demographic of each product sold by the robot 200 to a customer. The target demographic may be "women in their 20s," "families," "camping lovers," "outdoorsy," etc. The product-related information may include any other information related to each product.

[0053] The storage unit 130 has a storage medium such as a hard disk device, a flash memory, etc. The storage unit 130 also has a volatile storage device such as a RAM. The storage unit 130 stores information necessary for the execution of processing by the information processing unit 110, in addition to program codes and various temporary data read by the information processing unit 110 at execution time. The storage unit 130 may store so-called large-scale language models (LLMs). The storage unit 130 stores information acquired by the information acquisition unit 122 from various devices.

[0054] The control unit 111 uses the information stored in the memory unit 130 and the information acquired by the information acquisition unit 122 to determine the behavior of the robot 200, and transmits control information for executing the determined behavior to the robot 200 via the communication unit 120.

[0055] The storage unit 130 stores, for example, a plurality of talk steps. The storage unit 130 stores, for example, a plurality of talk steps classified by talk theme.

[0056] The storage unit 130 stores story information indicating a story of a sales talk in which, for example, an order of talk topics that the robot 200 will talk about with a customer is determined. The storage unit 130 stores story information for each sales talk, for example.

[0057] The story of the sales talk is constructed, for example, so as to increase customer satisfaction with the sales activities by the robot 200. The story of the sales talk is constructed, for example, so as to increase the emotional value of the customer. The story of the sales talk is constructed, for example, so as to always keep the emotional value of the customer positive.

[0058] The storage unit 130 stores, for example, an output mode in which the robot 200 outputs one talk script included in a talk step. The output mode may include the content of the display output. The output mode may include the content of the audio output. The output mode may include the tone of the voice of the robot 200. The output mode may include the speaking speed of the robot 200. The output mode may include information on the amount of pausing of the robot 200. The output mode may include the content of the body movement of the robot 200. The output mode may include information on the gestures and hand movements of the robot 200. The output mode may include information on the amount of mumbling to match the target of the robot 200's service.

[0059] The emotion value determination unit 112 determines the emotion value of the customer. For example, the emotion value determination unit 112 determines the emotion value of the customer before the robot 200 starts talking with the customer. For example, the emotion value determination unit 112 determines the emotion value of the customer while the robot 200 is talking with the customer based on one talk step of a plurality of talk steps stored in the storage unit 130.

[0060] The emotion value determination unit 112 recognizes the emotion of a customer based on the information acquired by the information acquisition unit 122. The emotion value determination unit 112 recognizes the emotion of a customer based on, for example, the facial expression of the customer recognized by analyzing image data captured by the camera 214. The emotion value determination unit 112 recognizes the emotion of a customer by, for example, analyzing voice data of the customer detected by the microphone 211. In this case, the emotion value determination unit 112 extracts, for example, feature amounts such as frequency components of the voice, and recognizes the emotion of the customer based on the extracted feature amounts. The emotion value determination unit 112 may determine the emotion value of the customer based on the recognized emotion of the customer.

[0061] The information acquisition unit 122 acquires, for example, response information indicating a response of the customer to a question posed to the customer by the robot 200 while the robot 200 is talking to the customer based on one of the multiple talk steps stored in the storage unit 130. The response information may be included in the customer-related information.

[0062] The customer's response includes, for example, giving a correct answer to a question posed by the robot 200. The customer's response includes, for example, giving an inappropriate answer to a question posed by the robot 200. The customer's response includes, for example, repeating a question posed by the robot 200. The customer's response includes, for example, nodding a head to a question posed by the robot 200. The customer's response includes, for example, asking a question to a question posed by the robot 200. The customer's response may include any other response to a question posed by the robot 200.

[0063] The emotion value determination unit 112 may determine the emotion value of the customer based on the response information of the customer acquired by the information acquisition unit 122. For example, when the response of the customer indicated by the response information of the customer is a correct answer to a question by the robot 200, a nod to a question by the robot 200, or the like, the emotion value determination unit 112 determines that the emotion value of the customer is a positive value. Also, for example, when the response of the customer indicated by the response information of the customer is an irrelevant answer to a question by the robot 200, a tilt of the head to a question by the robot 200, or the like, the emotion value determination unit 112 determines that the emotion value of the customer is a negative value. Also, for example, when the response of the customer indicated by the response information of the customer is a parroting of a question by the robot 200, a question to a question by the robot 200, or the like, the emotion value determination unit 112 determines that the emotion value of the customer is a value of 0.

[0064] The emotion value determination section 112 may determine the emotion value of a customer based on the analysis results of analyzing the image data of the customer captured by the camera 214 and the voice data of the customer detected by the microphone 211, and on the customer's response information. In this case, for example, the emotion value determination section 112 may determine that the customer's emotion value is the sum of the value determined based on the analysis results of the image data of the customer and the voice data of the customer and the value determined based on the customer's response information.

[0065] The selection unit 113 selects one talk step from among a plurality of talk steps stored in the storage unit 130. The selection unit 113 selects the one talk step based on, for example, a story of a sales talk indicated by the story information stored in the storage unit 130.

[0066] For example, when the robot 200 selects a first talk step to start talking with a customer, the selection unit 113 selects the first talk step based on the emotional value of the customer before the robot 200 starts talking with the customer, which is determined by the emotional value determination unit 112. The selection unit 113 selects the first talk step so that, for example, customer satisfaction with the sales activity by the robot 200 is higher. The selection unit 113 selects the first talk step so that, for example, the emotional value of the customer is higher. The selection unit 113 selects the first talk step so that, for example, the emotional value of the customer is positive.

[0067] The selection unit 113, for example, selects a talk step next to one talk step from among a plurality of talk steps stored in the storage unit 130. The selection unit 113 selects the next talk step based on a story of a sales talk indicated by the story information stored in the storage unit 130, for example.

[0068] The selection unit 113 selects the next talk step based on, for example, the emotional value of the customer while the robot 200 is talking with the customer based on the one talk step determined by the emotional value determination unit 112. The selection unit 113 selects the next talk step, for example, so that customer satisfaction with the sales activity by the robot 200 is higher. The selection unit 113 selects the next talk step, for example, so that the emotional value of the customer is higher. The selection unit 113 selects the next talk step, for example, so that the emotional value of the customer is always positive.

[0069] For example, when the customer's emotion value indicates that the customer's emotion while the robot 200 is talking to the customer based on the one talk step is positive, the selection unit 113 may select the next talk step so that the customer's emotion is maintained positive. When the customer's emotion value indicates that the customer's emotion while the robot 200 is talking to the customer based on the one talk step is positive, the selection unit 113 may select the next talk step so that the customer's emotion becomes more positive.

[0070] On the other hand, when the emotion value of the customer indicates that the emotion of the customer while the robot 200 is talking with the customer based on the one talk step is negative, the selection unit 113 may select the next talk step so that the customer's negative emotion is reduced. When the emotion value of the customer indicates that the emotion of the customer while the robot 200 is talking with the customer based on the one talk step is negative, the selection unit 113 may select the next talk step so that the customer's emotion transitions from negative emotion to positive emotion.

[0071] When the emotion value of the customer indicates that the emotion of the customer while the robot 200 was talking with the customer based on the one talk step was negative, the selection unit 113 may select the robot 200 to ask the customer a question to clarify the cause of the customer's negative emotion while the robot 200 was talking with the customer based on the one talk step. In this case, the selection unit 113 may interrupt the story of the sales talk indicated by the story information as necessary.

[0072] The selection unit 113 selects a talk step next to the one talk step from among a plurality of talk steps stored in the storage unit 130, for example, thereby selecting a question that the robot 200 will ask the customer. The selection unit 113 selects the next talk step from among a plurality of talk steps whose talk theme is classified as "question and answer". The selection unit 113 may select a question that the robot 200 will ask the customer from a list of questions for clarifying the cause of the customer's negative feelings, which is stored in the storage unit 130 separately from the talk steps.

[0073] The attribute identification unit 114 identifies the attributes of the customer. The attribute identification unit 114 identifies the attributes of the customer based on, for example, customer-related information acquired by the information acquisition unit 122. The attribute identification unit 114 identifies the attributes of the customer by, for example, performing image analysis on image data of the customer included in the customer-related information. The attribute identification unit 114 identifies the attributes of the customer by, for example, performing voice analysis on voice data of the customer included in the customer-related information. The attribute identification unit 114 may identify the attributes of the customer based on response information of the customer acquired by the information acquisition unit 122.

[0074] The storage unit 130 may store attribute data indicating attributes of a customer in association with a plurality of talk steps. The storage unit 130 may store attribute data of a customer in association with story information.

[0075] The customer attributes include, for example, attributes based on the customer's age. The customer attributes include, for example, attributes based on the customer's gender. The customer attributes include, for example, attributes based on the customer's family structure. The customer attributes include, for example, attributes based on the customer's purchasing conditions. The customer attributes include, for example, attributes based on the customer's interests. The customer attributes include, for example, attributes based on the customer's hobbies and tastes. The customer attributes may include attributes based on any other information.

[0076] Customer attributes include, for example, "20s". Customer attributes include, for example, "elderly". Customer attributes include, for example, "female". Customer attributes include, for example, "male". Customer attributes include, for example, "single male". Customer attributes include, for example, "father". Customer attributes include, for example, "camping lover". Customer attributes include, for example, "outdoorsy". Customer attributes may include any other attributes.

[0077] The selection unit 113 selects one talk step from among the multiple talk steps stored in the storage unit 130, for example, based on the attributes of a customer identified by the attribute identification unit 114. The selection unit 113 selects the one talk step, for example, so that the robot 200 sells to the customer a product that better meets the needs of the customer with the attributes identified by the attribute identification unit 114.

[0078] The selection unit 113 selects the one talk step further based on, for example, the research results stored in the storage unit 130. For example, the selection unit 113 identifies the needs of a customer with the attribute identified by the attribute identification unit 114 from the research results, and selects the one talk step so that the robot 200 sells a product that better meets the identified needs to the customer. For example, when the attribute of the customer identified by the attribute identification unit 114 is "male in his 40s" and the research result indicates that "males in their 40s are highly interested in purchasing car Y of company X", the selection unit 113 selects the one talk step so that the robot 200 sells car Y of company X to the customer.

[0079] The selection unit 113 selects the one talk step, for example, further based on the product-related information stored in the storage unit 130. For example, the selection unit 113 identifies the needs of the customer from the attributes of the customer identified by the attribute identification unit 114, and selects the one talk step so that the robot 200 sells to the customer a product that better meets the identified needs. For example, when the attribute of the customer identified by the attribute identification unit 114 is "budget 5 million yen," the selection unit 113 selects the one talk step so that the robot 200 sells to the customer a car that is less than 5 million yen.

[0080] The selection unit 113 selects the one talk step, for example, further based on the target demographic information stored in the storage unit 130. The selection unit 113 selects the one talk step, for example, so that the robot 200 sells a product whose target demographic includes the attribute of the customer specified by the attribute specification unit 114 to the customer. For example, when the attribute of the customer specified by the attribute specification unit 114 is "father," the selection unit 113 selects the one talk step so that the robot 200 sells a family car whose target demographic includes "family" to the customer. Also, for example, when the attribute of the customer specified by the attribute specification unit 114 is "camping lover" and "outdoorsy," the selection unit 113 selects the one talk step so that the robot 200 sells a camper whose target demographic includes "camping lover" and "outdoorsy" to the customer.

[0081] The selection unit 113 selects a talk step next to the one talk step from among the multiple talk steps stored in the storage unit 130, based on, for example, the emotional value of the customer while the robot 200 is talking with the customer based on the one talk step determined by the emotional value determination unit 112 and the attribute of the customer identified by the attribute identification unit 114. The selection unit 113 selects the next talk step so that, for example, the robot 200 sells to the customer a product that better meets the needs of the customer with the attribute identified by the attribute identification unit 114.

[0082] The selection unit 113 selects the next talk step, for example, further based on the research results stored in the storage unit 130. For example, the selection unit 113 identifies the needs of a customer having the attribute identified by the attribute identification unit 114 from the research results, and selects the next talk step such that the robot 200 sells a product that better satisfies the identified needs to the customer.

[0083] The selection unit 113 selects the next talk step, for example, further based on the product-related information stored in the storage unit 130. For example, the selection unit 113 identifies the needs of the customer from the attributes of the customer identified by the attribute identification unit 114, and selects the next talk step such that the robot 200 sells to the customer a product that better satisfies the identified needs.

[0084] The selection unit 113 selects the next talk step, for example, further based on the target demographic information stored in the storage unit 130. The selection unit 113 selects the next talk step, for example, so that the robot 200 sells a product whose target demographic includes the attribute of the customer identified by the attribute identification unit 114 to the customer.

[0085] The storage unit 130 may store learning data. The learning data includes attribute data of a customer, an emotion value of the customer while the robot 200 is talking with the customer based on one talk step, and an emotion value of the customer while the robot 200 is talking with the customer based on the talk step next to the one talk step.

[0086] The attribute of the customer indicated by the attribute data included in the learning data may be identified by the attribute identification unit 114. The emotion value determination unit 112 may determine the emotion value of the customer while the robot 200 is talking with the customer based on the one talk step included in the learning data, and the emotion value of the customer while the robot 200 is talking with the customer based on the next talk step.

[0087] The model generation unit 115 generates a selection model for selecting a talk step following one talk step by machine learning. For example, the model generation unit 115 uses a plurality of learning data stored in the storage unit 130 as teacher data to generate a selection model for selecting the next talk step from the attributes of the customer indicated by the customer attribute data and the emotional value of the customer while the robot 200 is talking with the customer based on the one talk step by machine learning, so as to increase the emotional value of the customer. The model generation unit 115 stores the generated selection model in the storage unit 130.

[0088] The selection unit 113 may select a talk step next to one talk step by using a selection model stored in the storage unit 130. For example, the selection unit 113 uses the selection model to select the next talk step from the attribute of the customer identified by the attribute identification unit 114 and the emotion value of the customer while the robot 200 is talking with the customer based on the one talk step, which emotion value is determined by the emotion value determination unit 112.

[0089] The server 100 shown in FIG. 2 uses a plurality of learning data including emotion values ​​of customers during past sales activities by the robot 200 to the customers as teacher data to generate a selection model for selecting a talk step following one talk step by machine learning. By using the plurality of learning data as teacher data, the server 100 can learn by machine learning, for example, when the emotion of the customer is negative while the robot 200 is talking to the customer based on one talk step, what talk step should be selected as the next talk step after the one talk step to cause the emotion of the customer to transition from negative to positive. In addition, the server 100 can learn by machine learning, for example, when the emotion of the customer is positive while the robot 200 is talking to the customer based on one talk step, what talk step should be selected as the next talk step after the one talk step to cause the emotion of the customer to transition from positive to negative. Therefore, by using the selection model generated by machine learning to select the next talk step after one talk step, the server 100 can select the next talk step so as to transition the customer's emotion from negative to more positive when the customer's emotion is negative, and so as to maintain the customer's emotion as more positive when the customer's emotion is positive. Furthermore, by continuously accumulating learning data to increase the number of learning data, and by generating a selection model using more learning data as teacher data, the sales talk to customers by the robot 200 can be perpetually evolved.

[0090] The update unit 116 updates the target demographic information stored in the storage unit 130. For example, when a customer purchases a product whose target demographic does not include the customer's attributes identified by the attribute identification unit 114 as a result of sales activities to the customer by the robot 200, the update unit 116 updates the target demographic information so that the customer's attributes are included in the target demographic of the product purchased by the customer. For example, when the attributes of a customer identified by the attribute identification unit 114 are "single male" and "camping lover" and the customer purchases a car whose target demographic does not include "single male" and "camping lover" but includes "family", the update unit 116 updates the target demographic information so that "single male" and "camping lover" are added to the target demographic of the car. In the updated target demographic information, the target demographic of the car includes "family", "single male", and "camping lover". When the update unit 116 updates the target demographic information, the update unit 116 may transmit the updated target demographic information to the manufacturer of the car.

[0091] The functions of the server 100 described above may be implemented by one or more computers. At least some of the functions of the server 100 may be implemented by a virtual machine. At least some of the functions of the server 100 may be implemented in the cloud. In the above embodiment, the robot 200 has been mainly given as an example of an electronic device, but this is not limited to this. Examples of electronic devices include smartphones, tablet terminals, PCs (Personal Computers), smart speakers, stuffed toys, vehicles such as automobiles and motorcycles, home appliances, etc. Note that these are merely examples, and electronic devices are not limited to these.

[0092] 3 is a schematic diagram showing an example of a hardware configuration of a computer 1200 functioning as the server 100 or the robot 200. The computer 1200 may function as the server 100, for example. A program installed on the computer 1200 may cause the computer 1200 to function as one or more "parts" of an apparatus according to the present embodiment, or cause the computer 1200 to execute operations or one or more "parts" associated with the apparatus according to the present embodiment, and / or cause the computer 1200 to execute a process or steps of the process according to the present embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0093] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, and a graphics controller 1216, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive, a DVD-RAM drive, or the like. The storage device 1224 may be a hard disk drive, a solid state drive, or the like. The computer 1200 also includes a legacy input / output unit such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0094] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 acquires image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into itself, and causes the image data to be displayed on the display device 1218.

[0095] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from a DVD-ROM 1227 or the like and provides the programs or data to the storage device 1224. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0096] The ROM 1230 stores therein a boot program or the like that is executed by the computer 1200 upon activation, and / or a program that depends on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a USB port, a parallel port, a serial port, a keyboard port, a mouse port, and the like.

[0097] The programs are provided by a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The programs are read from the computer-readable storage medium, installed in the storage device 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable storage media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by implementing operations or processing of information according to the use of the computer 1200.

[0098] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in the RAM 1214, the storage device 1224, the DVD-ROM 1227, or a recording medium such as an IC card, and transmits the read transmission data to a network, or writes reception data received from the network to a reception buffer area or the like provided on the recording medium.

[0099] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as the storage device 1224, the DVD drive 1226 (DVD-ROM 1227), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 may then write back the processed data to the external recording medium.

[0100] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry whose attribute value of the first attribute matches a specified condition from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0101] The above-described programs or software modules may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the programs to the computer 1200 via the network.

[0102] The blocks in the flowcharts and block diagrams in the present embodiment may represent stages of a process in which an operation is performed or "parts" of an apparatus responsible for performing the operation. Particular stages and "parts" may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable storage medium, and / or a processor provided with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuitry may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuitry may include reconfigurable hardware circuits, such as, for example, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like, including AND, OR, XOR, NAND, NOR, and other logical operations, flip-flops, registers, and memory elements.

[0103] A computer-readable storage medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer-readable storage medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like. More specific examples of computer-readable storage media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, and the like.

[0104] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0105] Computer readable instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, either locally or over a local area network (LAN), a wide area network (WAN), such as the Internet, etc., to cause the processor of the general purpose computer, special purpose computer, or other programmable data processing apparatus, or to a programmable circuit, to execute the computer readable instructions to generate means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0106] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the claims that such modifications and improvements can also be included in the technical scope of the present invention.

[0107] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before" or "prior to," and that the process may be performed in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, it does not mean that the process must be performed in this order. [Explanation of symbols]

[0108] 10 system, 20 user, 50 communication network, 100 server, 110 information processing unit, 111 control unit, 112 emotion value determination unit, 113 selection unit, 114 attribute identification unit, 115 model generation unit, 116 update unit, 120 communication unit, 122 information acquisition unit, 130 memory unit, 200 robot, 210 sensor unit, 211 microphone, 212 gyro sensor, 213 motor sensor, 214 camera, 215 infrared sensor, 216 battery remaining sensor, 220 information processing unit, 230 control target, 240 communication unit, 1200 computer, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphic controller, 1218 display device, 1220 input / output controller, 1222 communication interface, 1224 storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 I / O chip

Claims

1. A storage unit stores talk steps including a plurality of talk scripts that define talk contents of a sales talk to a customer by an electronic device; an emotion value determination unit that determines an emotion value indicating an emotion of the customer while the electronic device is talking with the customer based on one of the plurality of talk steps stored in the storage unit; a selection unit that selects a talk step subsequent to the one talk step from among the plurality of talk steps stored in the storage unit based on the emotional value of the customer determined by the emotional value determination unit so as to increase customer satisfaction in the sales activity using the electronic device; An information processing system comprising:

2. The information processing system of claim 1, wherein the selection unit selects the next talk step so that the customer's emotion transitions from a negative emotion to a positive emotion when the emotion value indicates that the customer's emotion while the electronic device is talking to the customer based on the one talk step is a negative emotion.

3. The information processing system of claim 2, wherein the selection unit selects that the electronic device should ask the customer a question to clarify the factor that caused the customer to have negative emotions while the electronic device was talking to the customer based on the one talk step.

4. an information acquisition unit for acquiring customer-related information related to the customer; an attribute specification unit that specifies attributes of the customer based on the customer-related information acquired by the information acquisition unit; Further equipped with The selection unit selects the next talk step further based on the attributes of the customer identified by the attribute identification unit. The information processing system according to claim 1 .

5. the storage unit further stores a research result of marketing research related to a product sold by the electronic device to the customer; The selection unit selects the next talk step further based on the research results stored in the storage unit.

5. The information processing system according to claim 4.

6. The storage unit further stores learning data including attribute data indicating attributes of a customer, an emotional value of the customer while the electronic device is talking to the customer based on a talk step, and an emotional value of the customer while the electronic device is talking to the customer based on a talk step next to the talk step, The information processing system includes: a model generation unit that uses the plurality of learning data stored in the storage unit as teacher data to generate, by machine learning, a selection model that selects a talk step following one talk step so as to increase the emotional value of the customer from the customer's attributes indicated by the customer's attribute data and the emotional value of the customer while the electronic device is talking to the customer based on the one talk step. Further equipped with The selection unit selects the next talk step based on the attribute of the customer identified by the attribute identification unit and the emotion value of the customer determined by the emotion value determination unit, using the selection model generated by the model generation unit.

5. The information processing system according to claim 4.

7. The storage unit further stores target demographic information indicating a target demographic of each product sold by the electronic device to the customer; The selection unit selects the next talk step based on the target demographic information stored in the storage unit so that the electronic device sells to the customer a product whose target demographic includes the attribute of the customer identified by the attribute identification unit; The information processing system includes an update unit that updates the target demographic information stored in the storage unit so that the target demographic of the product purchased by the customer includes the attributes of the customer when the customer purchases a product whose target demographic does not include the attributes of the customer as a result of sales activities to the customer by the electronic device. The information processing system according to claim 4 , further comprising:

8. an information acquisition unit that acquires response information indicating a response of the customer to a question posed to the customer by the electronic device while the electronic device is talking to the customer based on the one talk step; Further equipped with the emotion value determination unit determines the emotion value of the customer based on the response information of the customer acquired by the information acquisition unit; The information processing system according to claim 1 .

9. The information processing system according to claim 1 , further comprising the electronic device.

10. A program for causing a computer to function as the information processing system according to any one of claims 1 to 3.