INFORMATION PROCESSING DEVICE

Abstract

An information processing device includes a control unit. The control unit is configured to: during a business negotiation with a customer, it uses one or more sensors to collect negotiation information; based on the results of analyzing the negotiation information using machine learning, it determines whether there is an indication of a problem in the business negotiation, and if it determines that there is an indication of a problem, it sends an alert to a specific terminal device.

Description

BACKGROUND OF THE INVENTION 1. Field of the invention

[0001] The present disclosure relates to information processing devices. 2. Description of the related prior art

[0002] JP 2023 - 076 413 A discloses a method for selecting documents that may contain information relevant to answering a query entered by a user into a search model, and for outputting the answer. SUMMARY OF THE INVENTION

[0003] There is a need for systems that reduce the occurrence of problems with customers during business negotiations and ensure the smooth running of business negotiations.

[0004] One purpose of the present disclosure is to reduce the occurrence of problems with customers during business negotiations.

[0005] An information processing device according to an embodiment of the present disclosure comprises a control unit. The control unit is configured to acquire negotiation information during a business negotiation with a customer using one or more sensors, to determine, based on the result of an analysis of the negotiation information using machine learning, whether there is an indication of a problem in the business negotiation, and, if such an indication is found, to send an alarm to a specific terminal device.

[0006] The present disclosure may reduce the occurrence of problems with customers during business negotiations. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Features, advantages and technical and industrial significance of exemplary embodiments of the invention are described below with reference to the accompanying drawings, in which the same symbols denote the same elements, and wherein: Fig. 1 is a block diagram showing the configuration of a system according to an embodiment of the present disclosure; and Fig. 2 is a flowchart illustrating the operation of an information processing device according to the embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EXECUTION FORMS

[0008] An embodiment of the present disclosure is described below with reference to the drawings.

[0009] Identical or corresponding parts are marked with the same symbols in the drawings. In the following description of the embodiment, the description of identical or corresponding parts is omitted or simplified where necessary.

[0010] The construction of a system 10 according to the present embodiment is described with reference to Fig. 1 described.

[0011] The system 10 comprises at least one information processing device 20 and at least one terminal device 30.

[0012] The information processing device 20 is able to communicate with the terminal device 30 via a network 40.

[0013] The information processing device 20 is an end device, such as one installed in a car dealership that sells vehicles. This means that some or all of the functions of the information processing device 20 are implemented on the end device. A car salesperson at the dealership uses the end device to conduct negotiations with customers. The information processing device 20 could be, for example, a mobile phone, a smartphone, a tablet, or a PC. "PC" stands for personal computer.

[0014] The terminal device 30, for example, is owned by a manager of a car dealership that sells vehicles. Terminal device 30 could be, for example, a mobile phone, a smartphone, a tablet, or a PC. Information about the content of a business transaction conducted by a car salesperson is transmitted from the information processing device 20 to terminal device 30.

[0015] Network 40 encompasses the Internet, at least one WAN, at least one MAN, or any combination thereof. "WAN" stands for Wide Area Network. "MAN" stands for Metropolitan Area Network.

[0016] The overall configuration of the present embodiment is described with reference to Fig. 1 described.

[0017] In business negotiations, for example, dialogue systems are used that employ information retrieval technologies such as RAG. "RAG" stands for Retrieval-Augmented Generation. With the help of such a dialogue system, it is possible, for example, to generate an answer to a customer's question during a business negotiation.

[0018] Problems can arise between a customer and a salesperson during a business negotiation. In particular, customer harassment during negotiations has become a growing problem in recent years. Customer harassment refers to excessive and inappropriate behavior by customers towards employees, including insults, threats, and unreasonable demands. To protect the mental and physical well-being of employees, it is important to take appropriate countermeasures against problems such as customer harassment. One possible countermeasure is for a dealership manager or similar person to monitor the status of negotiations conducted by employees and intervene on-site (on the sales floor) to resolve any problems that arise. It is desirable that such problems be addressed and resolved at an early stage before they escalate.However, if business negotiations with several customers are being conducted in parallel, it is difficult for the car dealership manager to listen to each negotiation in real time, making it difficult to detect the occurrence of a problem.

[0019] In the present embodiment, the information processing device 20 acquires negotiation information D1 during a business negotiation with a customer using one or more sensors. The negotiation information D1 can include, for example, verbal information such as the content, volume, and tone of speech of the customer and the employee during the negotiation, as well as nonverbal information such as facial expressions and gestures of the customer and the employee. The negotiation information D1 can also include biometric information of the employee. The information processing device 20 analyzes the negotiation information D1 using machine learning and, based on the analysis results, determines whether there is an indication of a problem in the business negotiation.When the information processing device 20 detects that there is an indication of a problem, it sends an alarm to the terminal device 30.

[0020] In the present embodiment, an alarm is triggered when a situation with a high probability of causing a problem, such as customer harassment during a business negotiation, is detected. The alarm is sent to the dealership manager. Even if the manager is unable to monitor the negotiation in real time, they can recognize the emergence of a problem and go to the location to intervene and resolve the situation. This increases the likelihood that the problem can be addressed promptly and appropriately. As a result, the occurrence of problems with customers during business negotiations can be reduced.

[0021] The structure of the information processing device 20 according to the present embodiment is described with reference to Fig. 1 described.

[0022] The information processing device 20 comprises a control unit 21, a storage unit 22 and a communication unit 23. The control unit 21 comprises at least one processor, at least one programmable circuit, at least one dedicated circuit or any combination thereof and performs a predetermined processing action.

[0023] The storage unit 22 comprises at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these memories. In the present embodiment, the storage unit 22 can store a database DB in which a model is registered for each of a plurality of vehicles, in conjunction with one or more features associated with the model. The database DB is described later.

[0024] The communication unit 23 comprises at least one communication interface. In the present embodiment, the communication unit 23 communicates with the terminal device 30.

[0025] The functions of the information processing device 20 are implemented by causing a processor, acting as a control unit 21, to execute a program according to the present embodiment. That is, the functions of the information processing device 20 are realized by software.

[0026] The functioning of the information processing device 20 according to the present embodiment is described with reference to Fig. 2 described. This operation corresponds to an information processing method according to the present embodiment. That is, the information processing method according to the present embodiment comprises the Fig. The two steps S1 to S3 are shown. In the following, each step in the flowchart is labelled with "S", followed by a number.

[0027] In S1, the control unit 21 of the information processing device 20 acquires negotiation information D1. The negotiation information D1 can be acquired by any method. For example, an input unit can be provided in the information processing device 20, and one or more sensors, such as a microphone and a camera, which are part of the input unit, can be used to monitor in real time the voice during a business negotiation with a visiting customer, the customer's utterances, facial expressions, etc. The control unit 21 can then acquire this data as negotiation information D1. Alternatively, one or more sensors, such as...a microphone and a camera are provided outside the information processing device 20, and the control unit 21 can capture the negotiation information D1 by receiving the information obtained from the one or more sensors via the communication unit 23.

[0028] In S2, the control unit 21 of the information processing device 20 determines, based on the negotiation information D1 captured in S1, whether there is an indication of a problem in the business negotiation. Specifically, the control unit 21 analyzes the negotiation information D1 captured in S1 using machine learning and detects an indication of a problem. For example, the control unit 21 analyzes the content, volume, tone of voice, facial expressions, etc., contained in the negotiation information D1 using machine learning such as natural language processing or keyword recognition, and determines, if a predetermined condition is met, that an indication of a problem exists.For example, control unit 21 can recognize a negative keyword or phrase such as "not happy," "problem," or "disappointed" in the customer's utterances contained in negotiation information D1 as an indication of a problem. Any type of machine learning can be used. For example, any natural language processing techniques selected from major language models, NLP, intent recognition models, NER, and semantic search can be used, either alone or in combination. "NLP" stands for Natural Language Processing. "NER" stands for Named Entity Recognition.Control Unit 21 can assess the customer's emotional state based on the volume and tone of the customer's speech, facial expressions, and similar information provided in Negotiation Information D1. It can determine that a strong negative emotion, such as anger or dissatisfaction, indicates a potential problem. Alternatively, Control Unit 21 can analyze nonverbal cues, such as the customer's gestures indicated in Negotiation Information D1, to determine if a problem is present. Furthermore, if an employee's tone of voice increases or they begin speaking faster during the business negotiation, Control Unit 21 can determine that such a change is a sign of tension and / or stress, and can further determine that a problem is present.

[0029] As a modification of the present embodiment, the negotiation information D1 can contain biometric information of the employee obtained during the business negotiation. The control unit 21 of the information processing device 20 can detect that there is an indication of a problem if the employee's biometric information meets a predetermined condition. This is based on the assumption that various changes can be observed in the biometric information of an employee who is being harassed by customers. The most significant changes in the biometric information may include an increase in heart rate and blood pressure, changes in respiration, muscle tension, and perspiration.Accordingly, in this modification, in S1, the control unit 21 of the information processing device 20 records biometric information of the employee during the business negotiation as negotiation information D1, such as data on the employee's heart rate, blood pressure, and respiration. This data can be monitored, for example, with a wearable device such as a smartwatch worn by the employee. If, in S2, the biometric information contained in the negotiation information D1 recorded in S1 then meets the predetermined condition, the control unit 21 can determine that there is an indication of a problem and that the employee may be experiencing customer harassment.For example, the control unit 21 can monitor changes in the employee's heart rate, blood pressure, or breathing pattern in real time and, if these changes meet a predetermined condition, determine that they indicate a problem and that the employee may be experiencing customer harassment. For instance, the control unit 21 can detect a sudden increase in the employee's heart rate or blood pressure, or shallower or faster breathing, as signs of stress and / or tension and determine that the employee may be experiencing customer harassment. Furthermore, the control unit 21 can determine that a problem has occurred with the information processing device 20 if the state in which the employee's biometric information meets the predetermined condition persists for a certain period of time.For example, control unit 21 can determine that a problem has occurred if the employee's elevated heart rate persists for five minutes or longer. Control unit 21 can also determine a "problem level," which indicates the severity of the problem depending on the duration of the condition. That is, the longer the condition lasts, the higher the problem level can be assigned.

[0030] According to this modification, real-time monitoring of employee biometric information allows for the detection of signs of stress or tension. This makes it possible to identify potential customer harassment and take immediate action. As a result, potential problems can be addressed at an early stage, reducing the likelihood of issues arising with customers during business transactions.

[0031] Problems can arise during business negotiations for the sale of a vehicle if the customer is given incorrect information regarding the vehicle's technical specifications, delivery date, or price. For example, if the customer is given an incorrect delivery date, the vehicle may not arrive on the expected date, leading to a loss of customer trust and posing a risk to future business. Furthermore, if the customer incurs damages due to a delivery delay, they may be entitled to compensation. Therefore, it is crucial to verify the information provided by the employee to the customer, such as...Comparing the specifications, delivery time and price of the vehicle under consideration in the business negotiation (the target vehicle) with the latest information about the target vehicle and detecting any discrepancies between these pieces of information is an effective means of reducing the risk of providing incorrect information about the target vehicle and addressing potential problems early on.

[0032] Accordingly, in S2, the control unit 21 of the information processing device 20 can further refer to a database DB in which a model is registered for each of a multitude of vehicles, along with one or more attributes associated with that model. The control unit 21 can analyze the negotiation information D1 by comparing it with the database DB using machine learning. In this case, it is assumed that the negotiation information D1 contains vehicle data specifying the model of the target vehicle and the values ​​of the attributes associated with that model. As a concrete example, it is assumed that the model of the vehicle under consideration in the business negotiation is model X, and that the employee informs the customer during the negotiation: “The delivery time for model X is three months.”It should be noted that the “specific example” is not intended to limit the present disclosure, but rather serves to better illustrate the present embodiment. In this specific example, the negotiation information D1 contains the target vehicle model as “X”, with “delivery time” as the model feature and “three months” as the feature value. The control unit 21 of the information processing device 20 compares a speech feature value with a stored feature value. The speech feature value is a feature value spoken during the business negotiation and specified in the vehicle data. The stored feature value is a feature value registered in the database DB for the same model as the target vehicle model specified in the vehicle data.In the specific example described above, the target vehicle model specified in the vehicle data is "X," and the language attribute value is "Delivery time: three months." It is assumed that the database DB contains the value "five months" as the "Delivery time" for model "X." Control unit 21 searches the database DB and extracts the value "five months" as the stored attribute value, which is entered as the "Delivery time" for model "X" in the database DB. Since the language attribute value specified in the vehicle data ("three months") differs from the stored attribute value ("five months") in the database DB, control unit 21 detects an indication of a problem. This configuration reduces the risk of providing the customer with incorrect information about the specifications, delivery time, or price of the target vehicle.This can reduce the likelihood of problems occurring with customers during business negotiations.

[0033] If S2 detects an indication of a problem, the process proceeds to S3. If S2 detects no indication of a problem, the process returns to S1, and control unit 21 continues to collect the negotiation information D1.

[0034] In S3, the control unit 21 of the information processing device 20 sends an alarm W to a specific terminal. Specifically, the control unit 21 sends an alarm W to the manager's terminal 30. Any type of alarm can be used as alarm W, as long as it is capable of notifying the manager of a problem. For example, alarm W can be an audible alarm, a visual alarm, or a vibration alarm. The audible alarm emits a warning sound, such as a buzzer, from terminal 30. The visual alarm displays a pop-up message, a warning symbol, or something similar on the screen of terminal 30. The vibration alarm attracts attention by causing terminal 30 to vibrate. The vibration alarm is particularly effective in situations where an audible alarm, a visual alarm, or something similar might be overlooked.Alternatively, the control unit 21 can send a message or similar information to the terminal 30 as an alarm W. For example, the control unit 21 can send a message to the terminal 30 as an alarm W stating: "An indication of a problem was detected during the business negotiation with customer Y. Please check the details." These alarms W can be used either alone or in combination.

[0035] In S3, the control unit 21 of the information processing device 20 can send at least part of the negotiation information D1, along with the alarm W, to the terminal device 30. It is assumed here that the negotiation information D1 contains speech data V received during the business negotiation. If, in S2, an indication of a problem is detected, the control unit 21 can generate a summary of the business negotiation from the speech data V, for example, by using a natural language processing technique. The control unit 21 then sends the generated summary, along with the alarm W, to the terminal device 30 as part of the negotiation information D1. The summary can objectively reflect the customer's concerns or dissatisfaction, such as..."The customer has expressed concerns regarding the vehicle's delivery time," "The customer has questions about the quality," or "The customer feels the price is high compared to competing products." Alternatively, the summary can be an excerpt of the customer's key statements. The summary can be in the form of text or audio data. Transmitting the summary along with the alert in this way allows the manager receiving the message to be informed in advance about the cause of the problem, etc. This enables a faster response to the issue.

[0036] As described above, according to the present embodiment, an alarm W is sent to a specific terminal device when a problem is detected during a business negotiation. This increases the likelihood that the problem will be addressed promptly and appropriately. Consequently, the occurrence of problems for customers during business negotiations can be reduced.

[0037] In the present embodiment, it has been described that some or all of the functions of the information processing device 20 are implemented in an end device. However, the information processing device 20 can also be installed outside of an end device, and the information processing device 20 and a plurality of end devices installed in the car dealership can perform processing while sending and receiving various types of data over the network 40. In this case, the information processing device 20 can be a computer, such as a server, belonging to a cloud computing system or another computing system installed in a data center.

[0038] The present disclosure is not limited to the embodiment described above. For example, a plurality of the blocks shown in the block diagram can be integrated, or a single block can be split. Instead of executing the steps of the flowchart in chronological order as described above, the steps can be executed in parallel or in a different order, depending on the processing capability of the device executing the steps, or as required. Other modifications can be made without affecting the spirit and scope of the present disclosure. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] JP 2023 - 076 413 A

[0002]

Claims

Information processing device with a control unit, wherein the control unit is configured to collect negotiation information during a business negotiation with a customer using one or more sensors, determines, based on the result of an analysis of the negotiation information using machine learning, whether there is an indication of a problem in the business negotiation, and, if it determines that there is an indication of a problem, sends an alarm to a specific terminal device. Information processing device according to claim 1, wherein the control unit is further configured to refer to a database in which a model is registered for each of a plurality of vehicles in conjunction with one or more features relating to the model, and to analyze negotiation information by comparing the negotiation information with the database using machine learning. Information processing device according to claim 2, wherein: the negotiation information includes vehicle data specifying a model of a vehicle considered in the business negotiation and a value of a feature relating to the model; and the control unit is further configured to compare a language feature value with a stored feature value and, if the language feature value differs from the stored feature value, determines that there is an indication of a problem, wherein the language feature value is the value of the feature that is discussed during the business negotiation and that is specified in the vehicle data, and wherein the stored feature value is a value of the feature that is registered in the database for the same model as the model specified in the vehicle data. Information processing device according to claim 1 or 2, wherein: the negotiation information comprises speech data obtained during the business negotiation; and the control unit is further configured to generate a summary of the business negotiation from the speech data using natural language processing when it determines that there is an indication of a problem, and to send the generated summary at least as part of the negotiation information together with the alarm. Information processing device according to claim 1, wherein: the negotiation information comprises biometric information of an employee obtained during the business negotiation; and the control unit is further configured to detect that there is an indication of a problem when the biometric information meets a predetermined condition.

Images