Information processing apparatus

Abstract

An information processing device includes a control unit. The control unit uses one or more sensors to acquire negotiation information during discussions with customers; based on the results obtained by analyzing the negotiation information using machine learning, it determines whether there are signs of a dispute in the negotiation; when it determines that there are signs, it notifies a specific terminal of an alarm.

Description

Technical Field

[0001] This disclosure relates to information processing devices. Background Technology

[0002] Japanese Patent Application Publication No. 2023-076413 discloses a technique for selecting documents that can contain answer content for a user question input into a retrieval model and outputting an answer to the user question. Summary of the Invention

[0003] The goal is to develop a structure that reduces disputes with customers during negotiations and facilitates smoother negotiations.

[0004] The purpose of this disclosure is to reduce disputes with customers during negotiations.

[0005] An information processing apparatus according to one embodiment of the present disclosure includes a control unit, wherein...

[0006] The control unit:

[0007] Using one or more sensors, information is obtained during discussions with customers.

[0008] Based on the results obtained by analyzing the negotiation information using machine learning, it is determined whether there are any signs of a dispute in the negotiation.

[0009] When the aforementioned signs are detected, an alert is sent to the specific terminal.

[0010] According to this disclosure, disputes with customers during negotiations can be reduced. Attached Figure Description

[0011] The features, advantages, and technical and industrial significance of exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which the same reference numerals denote the same elements, and are attached as follows:

[0012] Figure 1 This is a block diagram illustrating the structure of a system according to an embodiment of the present disclosure;

[0013] Figure 2 This is a flowchart illustrating the operation of an information processing apparatus according to an embodiment of the present disclosure. Detailed Implementation

[0014] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings.

[0015] In all figures, the same or equivalent parts are labeled with the same reference numerals. In the description of this embodiment, the description of the same or equivalent parts is appropriately omitted or simplified.

[0016] Reference Figure 1This section describes the structure of system 10 in this embodiment.

[0017] System 10 includes at least one information processing device 20 and at least one terminal 30.

[0018] The information processing device 20 is able to communicate with the terminal 30 via the network 40.

[0019] The information processing device 20 is a terminal device installed in a vehicle sales agency or similar establishment. That is, some or all of the functions of the information processing device 20 are integrated into the terminal device. Salespeople selling vehicles at the agency use this terminal device to negotiate with customers. The information processing device 20 can be, for example, a mobile phone, smartphone, tablet computer, or PC. "PC" is an abbreviation for personal computer.

[0020] Terminal 30 is maintained by the manager of the dealership where the vehicle is sold. Terminal 30 is, for example, a mobile phone, smartphone, tablet, or PC. The content of the negotiation conducted by the vehicle salesperson is sent from the information processing device 20 to the terminal 30.

[0021] 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.

[0022] Reference Figure 1 This section provides an overview of the implementation method.

[0023] For example, dialogue systems utilizing information retrieval technologies such as RAG (Retrieval-Augmented Generation) have been widely used in business negotiations. This type of dialogue system can be used to generate answers to questions from customers during negotiations.

[0024] Disputes sometimes arise between sales representatives and customers during negotiations. In particular, customer harassment during negotiations has become a problem in recent years. Customer harassment refers to significant harassment of salespeople, such as verbal abuse, threats, and inappropriate demands from customers. Taking appropriate measures to address customer harassment and other disputes is essential for maintaining the mental and physical well-being of salespeople. As a way to deal with customer harassment and other disputes, store managers should be aware of the salesperson's negotiations and, in the event of a dispute, be present at the store to de-escalate the situation. Furthermore, it is preferable to address disputes as early as possible to resolve them before they escalate. However, when dealing with multiple customers simultaneously, store managers may find it difficult to hear all the conversations in real time and to detect disputes.

[0025] In this embodiment, the information processing device 20 uses one or more sensors to acquire negotiation information D1 during discussions with customers. For example, the negotiation information D1 includes verbal information such as the content, volume, and tone of voice of the customer and salesperson during the discussion, as well as non-verbal information such as facial expressions and gestures. The negotiation information D1 may also include the salesperson's biometric information. The information processing device 20 uses machine learning to analyze the negotiation information D1 and determines whether there are signs of a dispute during the discussion based on the analysis results. When the information processing device 20 determines that there are signs of a dispute, it sends an alarm to the terminal 30.

[0026] According to this embodiment, an alarm is triggered when there is a high probability of a dispute, such as customer harassment, occurring during a negotiation. This alarm is then sent to the store manager. Therefore, even if the store manager cannot hear the negotiation in real time, they can still detect the occurrence of a dispute and can go to the scene to resolve it. This increases the likelihood of responding to disputes quickly and appropriately. As a result, the occurrence of disputes with customers during negotiations can be reduced.

[0027] Reference Figure 1 The structure of the information processing device 20 in this embodiment will now be described.

[0028] The information processing device 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 performs predetermined processing.

[0029] 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 also store a database DB that combines the vehicle models and one or more attributes associated with each vehicle model for multiple vehicles. The database DB will be described later.

[0030] The communication unit 23 includes at least one communication interface. In this embodiment, the communication unit 23 communicates with the terminal 30.

[0031] The functions of the information processing device 20 are realized by executing the program of this embodiment through a processor that serves as the control unit 21. That is, the functions of the information processing device 20 are realized by software.

[0032] Reference Figure 2 The operation of the information processing device 20 in this embodiment will now be described. This operation corresponds to the information processing method of this embodiment. That is, the information processing method of this embodiment includes... Figure 2 The steps S1 to S3 are shown below. Hereafter, S and numbers are used to define each step in the flowchart.

[0033] In S1, the control unit 21 of the information processing device 20 acquires the negotiation information D1. The negotiation information D1 can be acquired through any process. For example, an input unit can be provided in the information processing device 20, and one or more sensors, such as a microphone or camera, which are part of the input unit, can be used to monitor in real time the sounds, speech, and expressions of customers during their negotiations. The control unit 21 then acquires this data as the negotiation information D1. Alternatively, one or more sensors, such as a microphone or camera, can be installed outside the information processing device 20, and the control unit 21 can receive information acquired by the microphone, camera, or other sensors via the communication unit 23, thereby acquiring the negotiation information D1.

[0034] In S2, the control unit 21 of the information processing device 20 determines whether there are signs of a dispute in the negotiation based on the negotiation information D1 obtained in S1. Specifically, the control unit 21 uses machine learning to analyze the negotiation information D1 obtained in S1 and detect signs of a dispute. For example, the control unit 21 analyzes the customer's speech content, volume, tone, and facial expressions contained in the negotiation information D1 using machine learning such as natural language processing or keyword detection, and determines that there are signs of a dispute if predetermined conditions are met. For example, the control unit 21 detects negative keywords such as "dissatisfaction," "problem," and "disappointment" from the customer's speech contained in the negotiation information D1 as signs of a dispute. Machine learning can be any machine learning method, and any natural language processing technique can be used alone or in combination, such as any natural language processing technique selected from large-scale language models, NLP, intent recognition models, NER, and semantic retrieval. "NLP" is an abbreviation for Natural Language Processing. "NER" is an abbreviation for Named Entity Recognition. Control unit 21 can also infer the customer's emotions based on the volume, tone, and facial expressions of the customer's speech shown in the negotiation information D1. If strong negative emotions such as anger or dissatisfaction are present, it can be determined as a sign of a dispute. Alternatively, control unit 21 can analyze the customer's nonverbal signals, such as gestures, shown in the negotiation information D1 to determine if there are signs of a dispute. Furthermore, if the salesperson's voice tone increases or their speaking speed increases during the negotiation, control unit 21 can determine that there are signs of tension and / or mental stress, and thus, a sign of a dispute.

[0035] As a variation of this embodiment, the negotiation information D1 may also include the biometric information of the salesperson during the negotiation. The control unit 21 of the information processing device 20 can determine that there is a sign of a dispute when the salesperson's biometric information meets predetermined conditions. This is because it is conceivable that various changes will be seen in the biometric information of a salesperson who has been harassed by a customer. Major changes in biometric information may include an increase in heart rate / blood pressure, changes in respiration, muscle tension, sweating, etc. Therefore, in this variation, in S1, the control unit 21 of the information processing device 20 obtains data such as the salesperson's heart rate, blood pressure, and respiration as negotiation information D1, which serves as the biometric information of the salesperson during the negotiation. This data can be monitored by a wearable device such as a smartwatch worn by the salesperson. Then, in S2, if the biometric information included in the negotiation information D1 obtained in S1 meets predetermined conditions, the control unit 21 determines that there is a possibility that the salesperson has been harassed by a customer, which is an indication of a dispute. Control unit 21 monitors changes in the salesperson's heart rate, blood pressure, and breathing pattern in real time, and determines that the salesperson may have been harassed by a customer if predetermined conditions are met. For example, if the salesperson's heart rate / blood pressure rises sharply, or their breathing becomes shallow or rapid, control unit 21 detects signs of mental stress and / or tension and determines that the salesperson may have been harassed by a customer. Furthermore, control unit 21 of information processing device 20 may determine that a dispute has occurred if the salesperson's biometric information meets predetermined conditions for a certain period of time. For example, control unit 21 may determine that a dispute has occurred if the salesperson's high heart rate persists for more than 5 minutes. Additionally, control unit 21 may determine the "dispute level" based on the duration of the dispute; that is, the longer the duration, the higher the "dispute level."

[0036] According to this variation, signs of stress and tension in salespeople can be detected by real-time monitoring of their biometric information. This allows for the assessment of potential customer harassment and enables swift action. Therefore, disputes can be prevented before they arise, reducing the likelihood of conflicts with customers during negotiations.

[0037] In vehicle sales negotiations, disputes can arise if incorrect information is conveyed to the customer regarding vehicle specifications, delivery date, or price. For example, if an incorrect delivery date is given, the customer may not receive the vehicle by the expected date, risking a loss of trust and impacting future transactions. Furthermore, customers may demand compensation for losses incurred due to delivery delays. Therefore, comparing the salesperson's initial information with the latest details regarding the vehicle's specifications, delivery date, and price during negotiations is effective in reducing the risk of misinformation and preventing potential disputes.

[0038] Therefore, in S2, the control unit 21 of the information processing device 20 can further refer to a database DB that records the model of each vehicle and one or more attributes associated with the model for multiple vehicles, and use machine learning to compare the negotiation information D1 with the database DB, thereby analyzing the negotiation information D1. In this case, the negotiation information D1 is assumed to contain vehicle data representing the model of the target vehicle and the value of its attributes. As a specific example, the model of the vehicle being discussed in the negotiation is X, and the salesperson in the negotiation conveys to the customer that "the delivery time for X is 3 months." Furthermore, this "specific example" is not intended to limit this disclosure, but rather an example used to help understand this embodiment. In this specific example, in the negotiation information D1, the model of the target vehicle is "X", its attribute is "delivery time", and its attribute value is "3 months". The control unit 21 of the information processing device 20 compares the value of the attribute represented by vehicle data, which is stated during the negotiation, with the value of the attribute registered in the database DB that is the same as the vehicle model represented by the vehicle data, which is the model of the target vehicle. In the specific example described above, the model of the target vehicle represented by the vehicle data is "X", and the statement attribute value is "delivery period of 3 months". On the other hand, in the database DB, a value of "5 months" is registered as the "delivery period" for model "X". The control unit 21 searches the database DB and extracts the value "5 months" registered as the "delivery period" for model "X" as the registration attribute value. Since the statement attribute value ("3 months") represented by the vehicle data differs from the registration attribute value ("5 months") registered in the database DB, the control unit 21 determines that there is a sign of a dispute. According to this configuration, the risk of conveying incorrect information to the customer regarding the specifications, delivery period, price, etc., of the target vehicle is reduced. Therefore, disputes with customers during negotiations can be reduced.

[0039] In S2, if there are signs of a dispute, proceed to S3. If there are no signs of a dispute in S2, return to S1, and control unit 21 continues to obtain negotiation information D1.

[0040] In S3, the control unit 21 of the information processing device 20 notifies a specific terminal of an alarm W. Specifically, the controller 21 notifies the store manager's terminal 30 of an alarm W. As an alarm W, any alarm can be used as long as it can notify the store manager that a dispute has occurred. For example, an audible alarm, a visual alarm, a vibration alarm, etc., can be used as alarm W. An audible alarm emits a sound to the terminal 30 via a buzzer or similar sound. A visual alarm displays a pop-up message, an alarm icon, etc., on the screen of the terminal 30. A vibration alarm draws attention by causing the terminal 30 to vibrate. Vibration alarms are particularly effective when audible alarms, visual alarms, etc., might be missed. Alternatively, the control unit 21 may also send a message to the terminal 30 as an alarm W. For example, the control unit 21 may send a message to the terminal 30 such as "Signs of a dispute were detected during a discussion with customer Y. Please check the details," as an alarm W. These alarms W can be used individually or in combination.

[0041] In step S3, the control unit 21 of the information processing device 20 can notify the terminal 30 of at least a portion of the negotiation information D1 along with the alarm W. Here, the negotiation information D1 is assumed to include voice data V from the negotiation. When signs of a dispute are detected in step S2, the control unit 21 generates a summary of the negotiation based on the voice data V, for example, using natural language processing technology. Then, the control unit 21 notifies the terminal 30 of the generated summary as at least a portion of the negotiation information D1, along with the alarm W. The summary may include, for example, objectively reporting the customer's concerns or dissatisfaction, such as "The customer has concerns about the vehicle's delivery date," "The customer has questions about the quality," or "Compared to products from other competing companies, the price feels high." Alternatively, the summary may be an excerpt of the customer's important statements. The summary can be text data or voice data. In this way, by notifying the store manager along with the alarm W, the store manager receiving the notification can know the cause of the dispute in advance. Therefore, disputes can be handled more quickly.

[0042] As described above, according to this embodiment, when a dispute is detected during negotiations, an alarm W is notified to a specific terminal. Therefore, the possibility of responding to disputes quickly and appropriately is increased. Consequently, the occurrence of disputes with customers during negotiations can be reduced.

[0043] In this embodiment, it is described that some or all of the functions of the information processing device 20 are installed on the terminal device. However, the information processing device 20 may also be installed outside the terminal device, and the information processing device 20 and multiple terminal devices installed in the agency store may perform processing while sending and receiving various data via the network 40. In this case, the information processing device 20 may also be a computer such as a server located in a data center, belonging to a cloud computing system or other computing system.

[0044] This disclosure is not limited to the embodiments described above. For example, multiple blocks shown in the block diagram may be merged, or a block may be divided. Instead of performing multiple steps shown in the flowchart in chronological order as described, the steps may be performed in parallel or in a different order, depending on the processing capability of the device performing each step or as needed. Furthermore, modifications can be made without departing from the spirit of the invention.

Claims

1. An information processing device comprising a control unit, wherein, The control unit: Using one or more sensors, information is obtained during discussions with customers. Based on the results obtained by analyzing the negotiation information using machine learning, it is determined whether there are any signs of a dispute in the negotiation. When the aforementioned signs are detected, an alert is sent to the specific terminal.

2. The information processing apparatus according to claim 1, wherein, The control unit: For multiple vehicles, further reference is made to a database that registers each vehicle's model and one or more attributes associated with that model. Machine learning is used to analyze the negotiation information by comparing it with the database.

3. The information processing apparatus according to claim 2, wherein, The negotiation information includes vehicle data representing the vehicle model and attribute values ​​of the vehicle being discussed in the negotiation. The control unit compares the value of the attribute represented by the vehicle data spoken during the negotiation, i.e., the speaking attribute value, with the value of the attribute registered for the same vehicle model as the one represented by the vehicle data, which is registered in the database. If the speaking attribute value and the registered attribute value are different, it determines that there is an indication that the dispute exists.

4. The information processing apparatus according to claim 1 or 2, wherein, The negotiation information includes audio data from the negotiation. When the presence of the aforementioned signs is detected, the controller uses natural language processing technology to generate a summary of the negotiation based on the sound data, and sends the generated summary along with the alarm as at least part of the negotiation information.

5. The information processing apparatus according to claim 1, wherein, The negotiation information includes the biometric information of the salesperson involved in the negotiation. If the biological information meets predetermined conditions, the control unit determines that there are signs of the dispute.

Images