Information processing device

Abstract

To reduce the occurrence of disputes with customers during business negotiations. [Solution] The information processing device 20 includes a control unit 21. The control unit 21 uses one or more sensors to acquire negotiation information during negotiations with customers, and uses machine learning to analyze the negotiation information and determine whether there are signs of trouble in the negotiation. If it determines that there are signs, it notifies a specific terminal 30 of an alert.

Description

【Technical Field】 【0001】 This disclosure relates to an information processing apparatus. 【Background Art】 【0002】 Patent Document 1 discloses a technique for selecting a document that may contain an answer to a user's question input to a search model and outputting an answer to the user's question. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2023-076413 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 There is a need for a mechanism to reduce the occurrence of troubles with customers during negotiations and to smoothly progress the negotiations. 【0005】 An object of this disclosure is to reduce the occurrence of troubles with customers during negotiations. 【0006】 An information processing apparatus according to an embodiment of this disclosure includes a control unit, The control unit, uses one or more sensors to acquire negotiation information during negotiations with a customer, uses machine learning to determine the presence or absence of signs of trouble in the negotiation based on the result of analyzing the negotiation information, when it is determined that there are such signs, an alert is notified to a specific terminal. 【Advantages of the Invention】 【0007】 According to this disclosure, the occurrence of troubles with customers during negotiations can be reduced. 【Brief Description of the Drawings】 【0008】 [Figure 1] This is a block diagram showing the configuration of a system according to an embodiment of this disclosure. [Figure 2] This is a flowchart showing the operation of the information processing device according to the embodiment of this disclosure. [Modes for carrying out the invention] 【0009】 The embodiments of this disclosure will be described below with reference to the figures. 【0010】 In each figure, identical or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate. 【0011】 Referring to Figure 1, the configuration of the system 10 according to this embodiment will be described. 【0012】 System 10 comprises at least one information processing device 20 and at least one terminal 30. 【0013】 The information processing device 20 can communicate with the terminal 30 via the network 40. 【0014】 The information processing device 20 is a terminal device installed at a vehicle sales agency or similar location. In other words, some or all of the functions of the information processing device 20 are incorporated into the terminal device. Salespeople at the agency use this terminal device to conduct business negotiations with customers. The information processing device 20 is, for example, a mobile phone, smartphone, tablet, or PC. "PC" is an abbreviation for personal computer. 【0015】 Terminal 30 is held by the manager of a dealership that sells vehicles. Terminal 30 is, for example, a mobile phone, smartphone, tablet, or PC. The details of the sales negotiation conducted by the vehicle salesperson are transmitted to Terminal 30 from the information processing device 20. 【0016】 Network 40 includes the Internet, at least one WAN, at least one MAN, or any combination thereof. "WAN" is an abbreviation for wide area network. "MAN" is an abbreviation for metropolitan area network. 【0017】 The outline of this embodiment will be described with reference to Figure 1. 【0018】 For example, dialogue systems using information retrieval technologies such as RAG are being utilized in business negotiations. "RAG" is an abbreviation for Retrieval-Augmented Generation. Using such a dialogue system, it is possible to generate answers to customer questions during business negotiations, for example. 【0019】 Troubles can arise between employees and customers during business negotiations. In particular, customer harassment during business negotiations has become a problem in recent years. Customer harassment refers to significant disruptive behavior towards employees, such as verbal abuse, threats, and unreasonable demands from customers. Taking appropriate measures to deal with troubles such as customer harassment is essential to protecting the mental and physical health of employees. One possible response to troubles such as customer harassment is for the store manager of the agency to be aware of the situation of the employee's business negotiations and to go to the scene (store) to resolve the issue if a problem occurs. It is also desirable to address troubles early and resolve them before they escalate. However, when business negotiations with multiple customers are being conducted in parallel, it is difficult for the store manager to hear about each negotiation in real time, making it difficult to detect when troubles occur. 【0020】 In this embodiment, the information processing apparatus 20 uses one or more sensors to acquire negotiation information D1 during a negotiation with a customer. For example, the negotiation information D1 includes linguistic information such as the speech content, volume, and tone of voice of the customer and employee during the negotiation, as well as non-linguistic information such as facial expressions and gestures. The negotiation information D1 may include the biometric information of the employee. The information processing apparatus 20 analyzes the negotiation information D1 using machine learning and determines the presence or absence of signs of trouble in the negotiation based on the analysis result. When the information processing apparatus 20 determines that there are signs of trouble, it notifies the terminal 30 of an alert. 【0021】 According to this embodiment, an alert is raised when a situation with a high possibility of trouble, such as customer harassment during a negotiation, occurs. The alert is notified to the store manager of the sales store. Therefore, even if the store manager cannot listen to the negotiation in real time, the store manager can detect the occurrence of trouble, so the store manager can go to the site to contain the trouble. For this reason, the probability of quickly and appropriately executing trouble response is increased. As a result, the occurrence of trouble with the customer during the negotiation can be reduced. 【0022】 Referring to FIG. 1, the configuration of the information processing apparatus 20 according to this embodiment will be described. 【0023】 The information processing apparatus 20 includes a control unit 21, a storage unit 22, and a communication unit 23. The control unit 21 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof, and executes predetermined processing. 【0024】 The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. In this embodiment, the storage unit 22 may store a database DB in which, for a plurality of vehicles, the vehicle type of each vehicle and one or more attributes related to the vehicle type are registered in combination. The database DB will be described later. 【0025】 The communication unit 23 includes at least one communication interface. In this embodiment, the communication unit 23 communicates with the terminal 30. 【0026】 The functions of the information processing device 20 are realized by executing the program according to this embodiment on the processor, which acts as the control unit 21. In other words, the functions of the information processing device 20 are realized by software. 【0027】 Referring to Figure 2, the operation of the information processing device 20 according to this embodiment will be described. This operation corresponds to the information processing method according to this embodiment. That is, the information processing method according to this embodiment includes steps S1 to S3 shown in Figure 2. Hereinafter, each step in the flowchart will be identified by S and a number. 【0028】 In S1, the control unit 21 of the information processing device 20 acquires negotiation information D1. The negotiation information D1 may be acquired by any procedure, but for example, the information processing device 20 is provided with an input unit, and one or more sensors such as a microphone and a camera, which constitute part of the input unit, are used to monitor in real time the voice, speech, and facial expressions of the customer during the negotiation with the customer who has come to the store, and the control unit 21 acquires this data as negotiation information D1. Alternatively, one or more sensors such as a microphone and a camera may be provided outside the information processing device 20, and the control unit 21 may acquire the negotiation information D1 by receiving the information acquired by one or more sensors such as a microphone and a camera via the communication unit 23. 【0029】 In S2, the control unit 21 of the information processing device 20 determines whether there are signs of trouble in the business negotiation based on the business negotiation information D1 acquired in S1. Specifically, the control unit 21 uses machine learning to analyze the business negotiation information D1 acquired in S1 and detect signs of trouble. For example, the control unit 21 analyzes the customer's utterances, volume, tone, and facial expressions included in the business negotiation information D1 using machine learning such as natural language processing or keyword detection, and determines that there are signs of trouble if predetermined conditions are met. For example, the control unit 21 detects negative keywords such as "dissatisfaction," "problem," and "disappointment" from the customer's utterances included in the business negotiation information D1 as signs of trouble. Any machine learning method can be used, but any natural language processing technology selected from large-scale language models, NLP, intent recognition models, NER, and semantic search can be used alone or in combination. "NLP" is an abbreviation for Natural Language Processing. "NER" is an abbreviation for Named Entity Recognition. The control unit 21 may infer the customer's emotions based on the volume, tone, and facial expressions of the customer's speech as indicated in the negotiation information D1, and determine that there are signs of trouble if negative emotions such as anger or dissatisfaction are strong. Alternatively, the control unit 21 may analyze nonverbal signs such as the customer's gestures as indicated in the negotiation information D1 and determine whether there are signs of trouble. Furthermore, if the employee's voice tone becomes higher or their speaking speed increases during the negotiation, the control unit 21 may determine that this is a sign of tension and / or stress, and determine that there are signs of trouble. 【0030】 As a modification of this embodiment, the sales negotiation information D1 may include the biometric information of the employee during the sales negotiation. The control unit 21 of the information processing device 20 may determine that there is a sign of trouble if the employee's biometric information meets predetermined conditions. This is because it is assumed that various changes will be observed in the biometric information of an employee who is experiencing customer harassment from a customer. Major changes in biometric information may include an increase in heart rate and blood pressure, changes in respiration, muscle tension, and sweating. Therefore, in this modification, in S1, the control unit 21 of the information processing device 20 acquires data such as the employee's heart rate, blood pressure, and respiration as sales negotiation information D1, as biometric information of the employee during the sales negotiation. This data can be monitored, for example, by a wearable device such as a smartwatch worn by the employee. Then, in S2, the control unit 21 determines that there is a possibility that the employee is experiencing customer harassment as a sign of trouble if the biometric information included in the sales negotiation information D1 acquired in S1 meets predetermined conditions. The control unit 21 monitors, for example, changes in the employee's heart rate, blood pressure, and breathing pattern in real time, and if predetermined conditions are met, it determines that the employee may be experiencing customer harassment as a sign of trouble. For example, if the employee's heart rate and blood pressure rise sharply, or if their breathing becomes shallow or rapid, the control unit 21 detects these as signs of stress and / or tension and determines that the employee may be experiencing customer harassment. Furthermore, the control unit 21 of the information processing device 20 may determine that trouble has occurred if the employee's biometric information remains in a state where predetermined conditions are met for a certain period of time. For example, the control unit 21 may determine that trouble has occurred if the employee's heart rate remains high for 5 minutes or more. The control unit 21 may also determine a "trouble degree" indicating the severity of the trouble according to the length of time. That is, the longer the duration, the higher the "trouble degree" may be determined. 【0031】 According to this modified version, by monitoring employees' biometric information in real time, signs of employee stress and tension can be detected. This allows for the determination of whether an employee is experiencing customer harassment and enables prompt action. Therefore, it is possible to prevent problems from occurring and reduce the occurrence of disputes with customers during business negotiations. 【0032】 In vehicle sales negotiations, providing customers with incorrect information regarding vehicle specifications, delivery dates, and prices can lead to problems. For example, giving a customer an incorrect delivery date could result in the vehicle not arriving by the expected date, leading to a loss of customer trust and potentially impacting future business. Furthermore, if the customer suffers damages due to the delivery delay, they may be liable for compensation. Therefore, comparing the information employees provide to customers regarding the specifications, delivery dates, and prices of the vehicle under consideration (the target vehicle) with the latest information on that vehicle, and detecting any discrepancies, is an effective way to reduce the risk of providing incorrect information about the vehicle and prevent problems from occurring. 【0033】 Therefore, in S2, the control unit 21 of the information processing device 20 may further refer to a database DB in which the vehicle type and one or more attributes associated with the vehicle type are registered for multiple vehicles, and analyze the sales negotiation information D1 by comparing it with the database DB using machine learning. In this case, the sales negotiation information D1 is assumed to include vehicle data indicating the vehicle type of the target vehicle and the value of its attribute. As a specific example, suppose the vehicle type being considered in the sales negotiation is X, and the employee in the negotiation tells the customer, "The delivery time for X is 3 months." Note that this "specific example" is not intended to limit the present disclosure, but is an example to help understand this embodiment. In this specific example, in the sales negotiation information D1, the vehicle type of the target vehicle is "X", its attribute is "delivery time", and the value of the attribute is "3 months". The control unit 21 of the information processing device 20 compares the spoken attribute value, which is the value of an attribute indicated in the vehicle data and spoken during a business negotiation, with the registered attribute value, which is the value of an attribute registered in the database DB for a vehicle model that is the same as the vehicle model indicated in the vehicle data. In the specific example described above, the vehicle model indicated in the vehicle data is "X", and the spoken attribute value is "delivery time 3 months". On the other hand, the database DB is registered with the value "5 months" as the "delivery time" for vehicle model "X". The control unit 21 searches the database DB and extracts the value "5 months" registered in the database DB as the registered attribute value for vehicle model "X". Since the spoken attribute value indicated in the vehicle data ("3 months") and the registered attribute value registered in the database DB ("5 months") are different, the control unit 21 determines that there is a sign of trouble. With this configuration, the risk of conveying incorrect information to the customer regarding the specifications, delivery time, price, etc. of the target vehicle is reduced. Therefore, the occurrence of troubles with customers during business negotiations can be reduced. 【0034】 If it is determined in S2 that there are signs of trouble, the process in S3 is performed. If it is determined in S2 that there are no signs of trouble, the process returns to S1, and the control unit 21 continues to acquire the business opportunity information D1. 【0035】 In S3, the control unit 21 of the information processing device 20 notifies a specific terminal of an alert W. Specifically, the control unit 21 notifies the store manager's terminal 30 of an alert W. Any alert W can be used as alert W, as long as it can notify the store manager of the occurrence of a problem. For example, an audio alert, a visual alert, or a vibration alert can be used as alert W. An audio alert will issue a warning to the terminal 30 with an audible sound such as a buzzer. A visual alert will display a pop-up message, a warning icon, etc., on the screen of the terminal 30. A vibration alert will draw attention by vibrating the terminal 30. Vibration alerts are particularly effective when audio alerts, visual alerts, etc., may be overlooked. Alternatively, the control unit 21 may send a message to the terminal 30 as alert W. For example, the control unit 21 may send the message to the terminal 30 as alert W, "Signs of trouble have been detected during negotiations with customer Y. Please check the details." These alerts W can be used individually or in combination. 【0036】 In S3, the control unit 21 of the information processing device 20 may notify the terminal 30 of at least a portion of the sales negotiation information D1 along with an alert W. Here, the sales negotiation information D1 is assumed to include voice data V from the sales negotiation. When the control unit 21 determines in S2 that there are signs of trouble, it generates a summary of the sales negotiation from the voice data V, for example, using natural language processing technology. The control unit 21 then notifies the terminal 30 of the generated summary as at least a portion of the sales negotiation information D1 along with the alert W. The content of the summary can be, for example, "The customer has expressed concerns about the vehicle delivery date," "The customer has doubts about the quality," or "The customer feels the price is high compared to competitors' products," objectively reporting an overview of the customer's concerns or dissatisfaction. Alternatively, the summary may be an excerpt of important statements made by the customer. The summary may be in text data or voice data. In this way, by notifying the summary along with the alert W, the store manager who receives the notification can know the cause of the trouble in advance. Therefore, it becomes possible to respond to trouble more quickly. 【0037】 As described above, according to this embodiment, when a problem is detected during a business negotiation, an alert W is sent to a specific terminal. This increases the likelihood that the problem can be addressed quickly and appropriately. Therefore, the occurrence of problems with customers during business negotiations can be reduced. 【0038】 In this embodiment, it has been explained that some or all of the functions of the information processing device 20 are installed in the terminal device. However, the information processing device 20 may be installed outside the terminal device, and the information processing device 20 and multiple terminal devices installed at the agency may perform processing while sending and receiving various data via the network 40. In this case, the information processing device 20 may be a computer such as a server belonging to a cloud computing system or other computing system installed in a data center. 【0039】 This disclosure is not limited to the embodiments described above. For example, multiple blocks described in the block diagram may be combined, or a single block may be divided. Instead of executing multiple steps described in the flowchart in chronological order as described, they may be executed in parallel or in a different order, depending on the processing capacity of the device performing each step, or as necessary. Other modifications are possible without departing from the spirit of this disclosure. [Explanation of Symbols] 【0040】 10 Systems 20 Information Processing Devices 21 Control Unit 22 Memory section 23 Communications Department 30 devices 40 Networks

Claims

[Claim 1] The information processing device includes a control unit, The control unit, Using one or more sensors, acquire negotiation information during a negotiation with a customer. Using machine learning, based on the results of analyzing the aforementioned business negotiation information, it is determined whether or not there are signs of trouble in the aforementioned business negotiation. An information processing device that, upon detecting the aforementioned symptoms, notifies a specific terminal of an alert. [Claim 2] The control unit, For multiple vehicles, the system further refers to a database in which the vehicle type of each vehicle and one or more attributes related to that vehicle type are registered in combination. The information processing apparatus according to claim 1, which analyzes the business negotiation information by comparing the business negotiation information with the database using machine learning. [Claim 3] The aforementioned business negotiation information includes vehicle data showing the vehicle type and attribute values ​​of the vehicle being considered in the negotiation. The control unit compares an utterance attribute value, which is the value of an attribute indicated in the vehicle data, uttered during the business negotiation, with a registered attribute value, which is the value of an attribute registered for a vehicle type in the database that is the same as the vehicle type indicated in the vehicle data, and determines that there is an indication of the trouble if the utterance attribute value and the registered attribute value are different, as described in claim 2. [Claim 4] The aforementioned negotiation information includes audio data from the negotiation, The information processing apparatus according to claim 1 or 2, wherein when the control unit determines that the indication exists, it generates a summary of the business negotiation from the voice data using natural language processing technology, and notifies the alert along with the generated summary as at least part of the business negotiation information. [Claim 5] The aforementioned business negotiation information includes biometric information of the employee during the business negotiation. The information processing apparatus according to claim 1, which determines that there are signs of the trouble when the aforementioned biological information meets predetermined conditions.

Images