Information processing device

Abstract

To improve the training efficiency of sales representatives. [Solution] The information processing device includes an acquisition unit that acquires information on business conversations to encourage customers to purchase products, a storage unit that stores information on unit conversations to be included in the business conversations, and a control unit that outputs information for presenting an evaluation to the user based on the information on the business conversations, according to how the unit conversations are included in the business conversations.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus.

Background Art

[0002] In various businesses, the skill of negotiations to encourage customers to purchase products depends on the personal skills of the sales representatives. Therefore, various techniques have been proposed to support the improvement of the negotiation skills of the representatives. For example, Patent Document 1 discloses a negotiation support apparatus that enables a user to accurately grasp negotiation risks in the negotiation preparation stage.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technology of supporting the improvement of the negotiation skills of sales representatives using machine learning, there is room for improving the training efficiency of sales representatives.

[0005] In view of the above, an information processing apparatus and the like that can improve the training efficiency of sales representatives will be disclosed below.

Means for Solving the Problems

[0006] The information processing apparatus in the present disclosure includes an acquisition unit that acquires information on negotiation conversations for promoting customers to purchase products, a storage unit that stores information on unit conversations to be included in the negotiation conversations, and a control unit that outputs information for presenting an evaluation according to the inclusion manner of the unit conversations in the negotiation conversations to a user based on the information on the negotiation conversations.

Effects of the Invention

[0007] The information processing device described in this disclosure makes it possible to improve the training efficiency of sales personnel. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing an example of the configuration of an information processing system. [Figure 2] This is a flowchart illustrating an example of the operation procedure for a server device. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described below.

[0010] Figure 1 shows an example configuration of one embodiment. The information processing system 1 comprises one or more server devices 10 and terminal devices 12 connected to the server devices 10 via a network 11 for information communication. The server devices 10 are, for example, one or a plurality of server computers capable of information communication with each other, and the server computers are appropriately installed, for example, in one or more sales offices of a vehicle sales company, one or more data centers, on the cloud, or a combination thereof. The server devices 10 correspond to the "information processing device" in this embodiment. The terminal devices 12 are, for example, one or a plurality of information processing devices capable of information communication with each other, equipped with communication functions and voice input functions, such as personal computers, portable tablet terminal devices, smartphones, etc. The terminal devices 12 are appropriately installed, for example, in one or a plurality of vehicle sales offices and used by sales staff. The terminal devices 12 are equipped with communication interfaces such as mobile communication and LAN (Local Area Network) and are connected to the network 11 for information communication. The terminal devices 12 also have a microphone to acquire the voice of conversations between sales staff and customers and a processor to process the voice information. Network 11 may be, for example, a LAN within a branch office, the Internet, an ad-hoc network, a MAN (Metropolitan Area Network), a mobile communication network, or another network, or any combination thereof.

[0011] The information processing system 1 in this embodiment supports sales representatives of vehicles in negotiations with customers. During negotiations with customers, sales representatives engage in various conversations, such as listening to the customer's preferences or needs, providing information on products that match those preferences or needs, and encouraging the customer to purchase the product once the customer has gained an understanding of and is satisfied with it.

[0012] In the information processing system 1, terminal device 12 sends information about sales conversations (hereinafter referred to as "conversation information") intended to encourage customers to purchase products to server device 10, which is an information processing device. Server device 10 has a communication unit 101, a storage unit 102, and a control unit 103. The communication unit 101 functions as an acquisition unit that acquires conversation information. The storage unit 102 stores information about unit conversations (hereinafter referred to as "essential conversations") that should be included in the sales conversation. Based on the conversation information, the control unit 103 outputs information (hereinafter referred to as "evaluation information") to present to the user an evaluation according to how essential conversations are included in the sales conversation. Here, the inclusion of essential conversations refers to the quantity and accuracy of essential conversations included in the sales conversation. Then, terminal device 12, having received the evaluation information, presents the evaluation information to the user, i.e., the salesperson or their supervisor. In this way, the salesperson or their supervisor can quantitatively evaluate the salesperson's negotiation skills based on the quantity and accuracy of essential conversations and adjust the salesperson's training method, thereby improving the efficiency of salesperson training.

[0013] Next, the communication unit 101, storage unit 102, and control unit 103 of the server device 10 will be described. If the server device 10 is composed of multiple server computers, the communication unit 101, storage unit 102, and control unit 103 may be appropriately distributed and arranged across multiple server computers.

[0014] The communication unit 101 includes one or more communication interfaces. These communication interfaces are, for example, LAN interfaces. The communication unit 101 receives information used in the operation of the server device 10 and transmits information obtained through the operation of the server device 10. The server device 10 is connected to the network 11 via the communication unit 101 and communicates information with the terminal device 12 via the network 11.

[0015] The storage unit 102 includes, for example, one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these, which function as main memory, auxiliary memory, or cache memory. The semiconductor memory is, for example, RAM (Random Access Memory) or ROM (Read Only Memory). The RAM is, for example, SRAM (Static RAM) or DRAM (Dynamic RAM). The ROM is, for example, EEPROM (Electrically Erasable Programmable ROM). The storage unit 102 stores control and processing programs necessary for the operation of the server device 10, various information required by the server device 10 to execute the control and processing programs, and information obtained through the operation of the server device 10.

[0016] The control unit 103 includes one or more processors, one or more dedicated circuits, or a combination thereof. The processors are, for example, general-purpose processors such as CPUs (Central Processing Units) or dedicated processors such as GPUs (Graphics Processing Units) specialized for specific processing. The dedicated circuits are, for example, FPGAs (Field-Programmable Gate Arrays) or ASICs (Application Specific Integrated Circuits). The control unit 103 controls each part of the server device 10 and performs information processing related to the operation of the server device 10.

[0017] In this embodiment, the memory unit 102 stores reference information 104. The reference information 104 is information relating to criteria for evaluating a business conversation, and includes information on essential conversations that should be included in the business conversation. Essential conversations include information such as topic labels attached to each and keywords that should be included in each. Topic labels for essential conversations are, for example, "product knowledge," "service knowledge," "payment method," "insurance," "personal information," "proposal," and "closing." Essential conversations corresponding to "product knowledge" include keywords such as words indicating products and functions, words indicating options, and words indicating the advantages and disadvantages of products, functions, or options. Essential conversations corresponding to "service knowledge" include keywords such as words indicating services from dealers or road service providers, and words indicating maintenance packages. Essential conversations corresponding to "payment method" include keywords such as words indicating payment frequency such as lump sum cash, installments, and two payments, and words indicating explanations of residual value setting. Essential conversations corresponding to "insurance" include keywords such as words indicating insurance products. Essential conversations corresponding to "personal information" include keywords such as vehicle replacement, purpose of use, family structure, hobbies, occupation, and residence. Essential conversations corresponding to "proposals" include keywords indicating a proposal, provided they are close to the keywords corresponding to "personal information." Essential conversations corresponding to "closing" include keywords such as contract completion, next booking, and lost deal.

[0018] Furthermore, the memory unit 102 stores a Large Language Model (LLM) 105. If the server device 10 consists of multiple server computers, the LLM 105 may be stored in any server computer, for example, a server computer that provides cloud services. The LLM 105 is a model that has been machine-learned using a large amount of text data to perform natural language processing, and is a language model that can perform natural language processing such as information extraction, text summarization, and question and answer in a general-purpose manner.

[0019] Figure 2 is a flowchart illustrating an example of the operation of the server device 10.

[0020] The procedure example in FIG. 2(A) is a procedure example executed by the control unit 103 of the server device 10 when a salesperson conducts a business negotiation by activating the business negotiation support function of the server device 10 using the terminal device 12. When the salesperson operates the terminal device 12 to request the business negotiation support function, the terminal device 12 sends a startup request for the support function to the server device 10.

[0021] When the control unit 103 of the server device 10 acquires the startup request for the support function, it activates the business negotiation support function in response to the startup request (S20). Next, the control unit 103 acquires conversation information (S21). When the salesperson conducts a business negotiation with the customer and voice of the business negotiation conversation is acquired by the terminal device 12, conversation information including the voice data of the business negotiation conversation is sent from the terminal device 12 to the server device 10. Next, the control unit 103 generates a conversation text of the business negotiation conversation (S22). For example, the control unit 103 performs voice recognition processing on the voice data included in the conversation information triggered by receiving information indicating that the business negotiation conversation from the terminal device 12 has ended, for example, information on a silent period of a certain time or longer, to generate the conversation text of the business negotiation conversation. At this time, the control unit 103 may perform speaker analysis to distinguish the utterances of the salesperson and the customer and identify the utterance text of the salesperson. Next, the control unit 103 generates evaluation information based on the presence or absence of essential conversations in the business negotiation conversation (S23). The detailed procedure for generating the evaluation information is shown in FIG. 2(B).

[0022] As shown in FIG. 2(B), the control unit 103 extracts unit conversations from the conversation text of the business negotiation conversation (S201). The control unit 103 inputs the conversation text to the LLM 105 to cause the LLM 105 to extract unit conversations from the business negotiation conversation. The LLM 105 divides the conversation text into unit conversations, for example, based on the timing of topic changes in the conversation text, and identifies a topic, that is, a topic label, and keywords for each unit conversation.

[0023] Next, the control unit 103 sequentially collates one or more unit conversations (hereinafter referred to as extracted conversations) extracted from the conversation text with one or more essential conversations included in the reference information 104 (S202), and determines whether the extracted conversation matches the essential conversation (S203). For example, the control unit 103 determines that the extracted conversation matches the essential conversation when a part or more of the topic labels of the extracted conversation and the essential conversation match, and a part or more of the keywords match. The matching ratio of the topic label or keyword for determining the match is arbitrarily set, for example, 50% or more. Then, when the extracted conversation matches the essential conversation (Yes in S203), the control unit 103 determines whether the information of the extracted conversation is accurate (S205). For example, the control unit 103 determines that the information of the extracted conversation is accurate when a part or more of the keywords of the extracted conversation and the essential conversation, for example, 80% or more, match. The keywords for determining accuracy include words indicating numerical values, prices, etc. The control unit 103 can use the LLM 105 to determine the match between the extracted conversation and the essential conversation or the accuracy of the information of the extracted conversation. Then, when the information of the extracted conversation is accurate (Yes in S205), the control unit 103 adds points to the evaluation score (S206). The evaluation score is a score assigned to each extracted conversation, and is a discrete value having an arbitrary level indicating that the extracted conversation matches the unit conversation and the information is accurate. The evaluation score has a value corresponding to, for example, the matching rate of the topic label or keyword of the extracted conversation and the unit conversation.

[0024] If the information in the extracted conversation is inaccurate (No in S205), the control unit 103 determines whether the conversation text contains exceptional expressions (S209). Exceptional expressions are utterances that indicate the salesperson has simplified the explanation or deliberately used an analogy for the sake of facilitating the business negotiation, such as words or phrases like "simply put" or "to give an example." Information on exceptional expressions is stored in the memory unit 102 in advance. If the control unit 103 contains exceptional expressions (Yes in S209), it is presumed that the purpose is to facilitate the business negotiation even if the information in the extracted conversation is inaccurate, so it adds points to the evaluation score (S206). On the other hand, if the control unit 103 does not contain exceptional expressions (No in S209), it does not add points to the evaluation score (S206). Not adding points to the evaluation score may also include deducting points from the evaluation score within an arbitrary range.

[0025] After the steps of adding or not adding points to the evaluation score (S205, S206), or if the extracted conversation does not match the required conversation (No in S203), the control unit 103 determines whether all extracted conversations have been matched with the required conversation (S208). If all extracted conversations have been matched (Yes in S207), the control unit 103 sums up the evaluation scores (S208) and terminates the procedure in Figure 2(B). On the other hand, if not all extracted conversations have been matched (No in S207), the control unit 103 performs steps S202 to S207 for the next extracted conversation. The evaluation score derived in this way is included in the evaluation information.

[0026] Returning to Figure 2(a), the control unit 103 outputs evaluation information to the terminal device 12 (S24). Upon receiving the evaluation information, the terminal device 12 outputs, for example, displays, the evaluation information to the sales representative or their supervisor.

[0027] By checking the evaluation score of the evaluation information displayed by the terminal device 12, the salesperson or their supervisor can quantitatively determine to what extent the salesperson's negotiation included essential topics and whether they accurately conveyed information to the customer. Furthermore, when generating the evaluation information, the control unit 103 may generate a list of labels and keywords of essential conversation topics that matched the extracted conversation and include them in the evaluation information, or conversely, it may generate a list of labels and keywords of essential conversation topics that did not match the extracted conversation and include them in the evaluation information. In this way, the salesperson or their supervisor who checks the displayed evaluation information can confirm the essential conversations that the salesperson was able to include in the negotiation conversation, or essential conversations that should have been included but were not. Thus, according to this embodiment, it is possible to quantitatively evaluate the salesperson's negotiation skills based on the amount and accuracy of essential conversations and adjust the salesperson's training method, thereby improving the efficiency of salesperson training.

[0028] In the procedure shown in Figure 2(A), the control unit 103 of the server device 10 may generate the conversation text at the terminal device 12 and obtain the conversation text as conversation information from the terminal device 12. In that case, step S22 is omitted.

[0029] As described above, embodiments have been explained based on various drawings and examples, but it should be noted that those skilled in the art will find it easy to make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions, etc., included in each means, each step, etc., can be rearranged in a logically consistent manner, and multiple means, steps, etc., can be combined into one or divided. [Explanation of Symbols]

[0030] 10: Server equipment, 11: Network, 12: Terminal equipment, 101: Communications department 102: Memory unit, 103: Control unit, 104: Evaluation criteria information, 105: Large-scale language models

Claims

1. An acquisition unit that obtains information from sales conversations to encourage customers to purchase products, A memory unit for storing information on unit conversations to be included in the aforementioned business negotiation conversation, A control unit that outputs information to present to the user an evaluation based on the information of the business negotiation conversation, according to how the unit conversation is included in the business negotiation conversation. An information processing device having

2. In claim 1, The information from the aforementioned business negotiation conversation includes audio data or text. Information processing device.

3. In claim 1, The control unit improves the evaluation according to the amount of the unit conversation included in the business negotiation conversation. Information processing device.

4. In claim 3, When the control unit detects utterances from the business negotiation conversation that suggest intentional omission or modification of information in the first unit conversation, it maintains the evaluation that the first unit conversation is included in the business negotiation conversation. Information processing device.

Images