Sales negotiation support system and sales negotiation support method

Abstract

This allows us to accurately consider the customer's intentions and other factors during business negotiations and propose appropriate negotiation strategies. [Solution] The sales negotiation support system 1 is configured to include an analysis database 130 that stores past sales negotiation data, an emotion estimation unit 122 that estimates the customer's emotional state based on the customer's biometric information, and a recommendation unit 124 that determines a sales negotiation strategy for the customer based on the customer's emotional state and past sales negotiation data, and outputs information on the sales negotiation strategy.

Description

Technical Field

[0001] The present invention generally relates to the technology of negotiation support systems and negotiation support methods, and specifically relates to a technology that can propose appropriate negotiation content while accurately grasping the customer's intentions and the like in a negotiation.

Background Art

[0002] Opportunities for sales representatives to conduct negotiations with customers exist widely regardless of industry or business type. In such opportunities, sales representatives explore the true feelings and intentions of customers and proceed with negotiations while weaving various techniques such as price discounts and option additions. However, the skills and know-how required for such negotiations are highly personal and difficult to easily share among sales representatives.

[0003] Therefore, support technologies for reading customers' intentions and providing topics suitable for negotiations have been proposed. For example, as a prior art related to the above problems, what is shown in Patent Document 1 has been proposed. In this Patent Document 1, a technology is disclosed that can provide a speaker with a topic suitable for the listener's reaction.

[0004] The above technology is a communication support device for supporting communication between a speaker and a listener, having a generation means for generating content that is a candidate for what the speaker will say, a detection means for detecting that the speaker has used the content generated by the generation means, a reaction analysis means for analyzing the listener's reaction at the timing before and after the detection means detects, and a profile registration means for registering the result analyzed by the reaction analysis means as the listener's profile information, and the generation means updates the content that is a candidate for what the speaker will say based on the profile information registered by the profile registration means. It relates to a communication support device characterized by this.

Prior Art Documents

Patent Documents

[0005] [Patent Document 1] Japanese Patent Publication No. 2016-177483 [Overview of the project] [Problems that the invention aims to solve]

[0006] Considering customer psychology, the appropriateness of compromises, such as price reductions or the addition of options, is a crucial factor in closing a deal during actual negotiations. However, opportunities to actually acquire such negotiation skills are limited, and it is difficult for inexperienced sales representatives to learn and utilize them in a short period of time. These challenges, along with the difficulty of accurately eliciting the customer's true feelings and intentions, can significantly impact the closing rate of deals.

[0007] Therefore, the present invention has been made in view of the above problems, and aims to provide a technology that enables the proposal of appropriate negotiation content while accurately taking into account the intentions of the customer in business negotiations. [Means for solving the problem]

[0008] The present invention includes several means for solving the above problems, but an example is as follows. To solve the above problems, a business negotiation support system according to one aspect of the present invention is characterized by comprising: a storage unit that stores past business negotiation results; an emotion estimation unit that estimates the emotional state of a customer based on the customer's biometric information in the business negotiation; and a recommendation unit that determines a business negotiation policy for the customer based on the customer's emotional state, the customer's current business negotiation status, and the past business negotiation results, and outputs information on the business negotiation policy.

[0009] Furthermore, in order to solve the above problems, a business negotiation support method according to one aspect of the present invention is characterized in that an information processing device performs the following: storing past business negotiation results and estimating the emotional state of the customer based on the customer's biometric information; and determining a business negotiation policy for the customer based on the customer's emotional state and the past business negotiation results, and outputting information on the business negotiation policy. [Effects of the Invention]

[0010] According to the present invention, it becomes possible to propose appropriate negotiation content while accurately taking into account the customer's intentions and other factors during business negotiations. [Brief explanation of the drawing]

[0011] [Figure 1] This is a diagram illustrating the configuration of the sales negotiation support system in this embodiment. [Figure 2] This figure shows an example of the configuration of the customer information table in this embodiment. [Figure 3] This figure shows an example of the configuration of the discount history information table in this embodiment. [Figure 4] This figure shows an example of the configuration of the action history information table in this embodiment. [Figure 5] This figure shows an example of the hardware configuration of the analysis server in this embodiment. [Figure 6] This diagram shows an example of a workflow for the sales negotiation support method in this embodiment. [Figure 7A] This figure shows an example of customer biometric information in this embodiment. [Figure 7B] This figure shows an example of the sentiment analysis results in this embodiment. [Figure 8] This diagram shows an example of a workflow for the sales negotiation support method in this embodiment. [Figure 9A] This figure shows an example of a business negotiation situation in this embodiment. [Figure 9B] This figure shows an example of the sentiment analysis results in this embodiment. [Figure 9C] This figure shows an example of an action candidate in this embodiment. [Figure 9D] This figure shows an example of a similar past business deal in this embodiment. [Figure 10] This figure shows an example of the screen display in this embodiment. [Figure 11] This diagram shows an example of a workflow for the sales negotiation support method in this embodiment. [Figure 12A]This is a diagram showing an example of a selected action that is an action candidate selected by a salesperson in this embodiment. [Figure 12B] This is a diagram showing an example of information generated by a salesperson in this embodiment by executing a selected action. [Figure 12C] This is a diagram showing an example of information generated by a salesperson in this embodiment by executing a selected action.

Mode for Carrying Out the Invention

[0012] In the following description, "CPU" is an arithmetic unit and may be one or more processor devices. At least one processor device may typically be a microprocessor device such as a CPU (Central Processing Unit), but may also be another type of processor device such as a GPU (Graphics Processing Unit). At least one processor device may be single-core or multi-core. At least one processor device may be a processor core. At least one processor device may also be a hardware circuit (e.g., FPGA (Field-Programmable Gate Array), CPLD (Complex Programmable Logic Device), or ASIC (Application Specific Integrated Circuit)) that performs part or all of the processing, which is a processor device in a broad sense.

[0013] Also, in the following description, "storage device" may be one or more persistent storage devices, which is an example of one or more storage devices. Persistent storage devices may typically be non-volatile storage devices, and specifically may be, for example, HDD (Hard Disk Drive), SSD (Solid State Drive), or NVMe (Non-Volatile Memory Express) drive.

[0014] Furthermore, in the following explanation, "memory" refers to one or more memory devices, which are an example of one or more storage devices. At least one memory device in memory may be a volatile memory device or a non-volatile memory device.

[0015] Furthermore, in the following explanation, "communication device" may refer to one or more communication interface devices. One or more communication interface devices may be one or more identical communication interface devices (for example, one or more NICs (Network Interface Cards)) or two or more different communication interface devices (for example, a NIC and an HBA (Host Bus Adapter)).

[0016] Furthermore, in the following explanation, we may use expressions such as "xxx table" or "xxx database" to describe information from which an output is obtained for a given input. This information can be data of any structure (for example, structured data or unstructured data), or it can be a neural network that generates an output for a given input, or a learning model such as a genetic algorithm or random forest. Therefore, "xxx table" or "xxx database" can be referred to as "xxx information." Also, in the following explanation, the configuration of each database or table is just an example, and one database or table may be divided into two or more databases or tables, or all or part of two or more databases or tables may be a single database or table.

[0017] Furthermore, in the following explanation, the process may be described using "program" as the subject. However, since a program is executed by the CPU and performs defined processes using memory devices and / or interface devices as appropriate, the subject of the process may also be the CPU (or a device such as a controller having that processor). A program may be installed from a program source into a device such as a computer. The program source may be, for example, a program distribution server or a computer-readable (e.g., non-temporary) recording medium. Also, in the following explanation, two or more programs may be implemented as a single program, or one program may be implemented as two or more programs.

[0018] Furthermore, in the following explanation, when describing similar elements without distinction, the common part of the reference code may be used, and when describing similar elements with distinction, the reference code or element identifier may be used.

[0019] <Overall configuration of the sales negotiation support system> Figure 1 shows an example configuration of the sales negotiation support system 1 in this embodiment. The sales negotiation support system 1 in this embodiment is a system that can propose appropriate negotiation content while accurately taking into account the customer's intentions in a sales negotiation. This sales negotiation support system 1 is connected via an appropriate network N, with a biometric information reading unit 100, a screen display unit 110, an analysis server 120 (storage unit), and an analysis database 130, which can be linked as needed. However, the analysis server 120 is the main entity that executes the sales negotiation support method. Therefore, the minimum configuration of the sales negotiation support system 1 is, for example, this analysis server 120, but of course, it is not limited to this.

[0020] Of the above configuration, the biometric information reading unit 100 is installed at the location where the customer and sales representative conduct business negotiations, and is implemented by a reading unit 1001 consisting of a camera, microphone, and sensors that read the customer's facial expressions, body movements, body temperature, and voice. This reading unit 1001 has a communication means compatible with the network N protocol and distributes the customer's reactions, etc., acquired in real time during the negotiation, i.e., biometric information obtained from the customer (hereinafter also referred to as "customer biometric information") 133 to the analysis server 120.

[0021] Furthermore, the screen display unit 110 displays information on the next action candidates 136 that are suitable for negotiations in a business deal, as indicated by the analysis results from the analysis server 120. This screen display unit 110 is implemented, for example, as a display. The information on the above action candidates 136 includes actions that occur during negotiations at a car dealership, such as discounting the vehicle price, adding services to the vehicle, and adding accessories. The display format of this screen display unit 110 will be described later.

[0022] The analysis server 120 also includes an analysis unit 121 and a learning unit 126. The analysis unit 121 has an emotion estimation unit 122 and a recommendation unit 124. The emotion estimation unit 122 analyzes the customer's biometric information 133 read by the biometric information reading unit 100 using an emotion estimation model 123 to analyze the customer's emotions in real time. The recommendation unit 124 generates action candidates 136 to present to the sales representative from the output results of the emotion estimation unit 122 and past sales negotiation results (each piece of information held in the analysis database 130).

[0023] The learning unit 126 stores the customer's biometric information 133 read by the biometric information reading unit 100 and the results of sales negotiations conducted for that customer in the past sales negotiation database 132. The sales negotiation result information is distributed from devices responsible for inputting and outputting the history and results of sales negotiations, such as a sales management system or sales representative's terminal, which is linked to the analysis server 120. This distribution is performed each time a sales opportunity arises, or at the end of a certain period of time or at a predetermined time.

[0024] The learning unit 126 also generates the knowledge database 131. The data in the knowledge database 131 is numerical data in which various information related to a business negotiation is vectorized, with each negotiation being treated as one chunk. The data for one negotiation refers to information such as customer information, discount history information, and action history, with each record being based on the customer number and the number of times the app was launched.

[0025] Knowledge DB131 has the following tables for storing such records: customer information table 1311, discount history information table 1312, and action history information table 1313 (Figures 5-7).

[0026] Figure 2 shows an example of the configuration of the customer information table 1311. In this embodiment, the customer information table 1311 is a collection of records that use customer No. as the key and include values ​​such as customer name, date of birth, business negotiation status, number of visits, and hobbies.

[0027] Furthermore, Figure 3 shows an example of the configuration of the discount history information table 1312. In this embodiment, the discount history information table 1312 is a collection of records that use the customer number as the key and include values ​​such as the number of times the app was launched, the number of discounts, the discount amount, the cumulative discount amount, and whether the deal was successful or not.

[0028] Furthermore, an example of the configuration of the action history information table 1313 is shown in Figure 4. In this embodiment, the action history information table 1313 is a collection of records that include values ​​such as the number of times the app was launched, action candidates (for example, four patterns of candidates from candidate 1 to candidate 4), selected action, discount amount, cumulative discount amount, and deal success / failure flag, with customer No. as the key.

[0029] Furthermore, the analysis database 130 stores past sales negotiation results in the past sales negotiation DB 132. This past sales negotiation DB 132 stores information such as customer biometric information 133, sales negotiation status 134, sentiment analysis results 135, and action candidates 136. This various information in the past sales negotiation DB 132 will be used for subsequent analysis and recommendations.

[0030] Of the components of the above-described sales negotiation support system 1, the analysis server 120 is an information processing device that is the main entity executing the sales negotiation support method of this embodiment. This analysis server 120 is operated by, for example, a vehicle dealer or an SIer that provides business support to said dealer (of course, this is merely one example of an implementation).

[0031] <Hardware configuration of the analysis server> Next, the hardware configuration of the analysis server 120, which mainly constitutes the above-mentioned business negotiation support system 1, will be described. Figure 5 is a diagram showing an example of the hardware configuration of the analysis server 120 in this embodiment. In this embodiment, the analysis server 120 consists of an auxiliary storage device 101, a CPU 102, a main memory device 103, and a communication device 104.

[0032] Of these, the auxiliary storage device 101 is a storage means composed of non-volatile storage devices such as a hard disk drive or an embedded multimedia card. The data held by the auxiliary storage device 101 includes a program 1011 containing the OS (Operating System), as well as a deep learning engine 1012, an emotion estimation model 123, and an action recommendation model 125.

[0033] Of these, the deep learning engine 1012 is an engine that learns using a large amount of training data, and continuously generates and tunes learning models such as the emotion estimation model 123 and the action recommendation model 125 as appropriate. In this embodiment, the emotion estimation model 123 and the action recommendation model 125 are learned based on various data on customers, the history of their business negotiations, and the results collected from the business systems of various sales offices and the terminals of sales representatives who handle many business negotiation opportunities on a daily basis.

[0034] Furthermore, the CPU 102 is a processor that calls and executes the program 1011 held in the auxiliary storage device 101 in the main memory device 103, performs overall control of the device itself, and performs various judgment, calculation, and control processing. In other words, the functional unit corresponding to the business negotiation support method implemented in the analysis server 120 (see Figure 1; the emotion estimation unit 122 and recommendation unit 124 of the analysis unit 121, and the learning unit 126) is implemented by the CPU 102 executing the program 1011. Note that some of the processing performed by the CPU 102 when executing the program 1011 may be performed by other computing devices (for example, hardware such as ASICs and FPGAs). Further details of the above functional unit (the emotion estimation unit 122 and recommendation unit 124 of the analysis unit 121, and the learning unit 126) will be described later.

[0035] The program 1011 executed by the CPU 102 may be provided to the analysis server 120 of the business negotiation support system 1 via removable media (such as a CD-ROM or flash memory) or network N, and stored in a non-volatile auxiliary storage device 101, which is a non-temporary storage medium.

[0036] Furthermore, the main memory 103 is a storage means composed of a volatile storage device such as RAM (Random Access Memory). The main memory 103 may also be a non-volatile storage element called ROM (Read Only Memory). ROM stores immutable programs (for example, BIOS).

[0037] Furthermore, the communication device 104 is a device that connects to the network N and communicates with the biometric information reading unit 100, the screen display unit 110, and the analysis database 130.

[0038] The sales support system 1 is a computer system that is configured on a single physical computer, or on multiple logically or physically configured computers, and may operate on a virtual computer built on multiple physical computing resources. The sales support system 1 may be configured on the cloud, or it may be on-premise configured on a specific computer (hardware).

[0039] Furthermore, the network N connecting the business negotiation support system 1, the biometric information reading unit 100, the screen display unit 110, and the analysis database 130 may be the internet, a LAN (Local Area Network), a WAN (Wide Area Network), or a mobile phone network, but is not limited to these. As an example of a mobile phone network, a general public network, whether wired or wireless, such as the fifth-generation mobile communication system, or so-called 5G (5th Generation), which enables "massive simultaneous connections" and "ultra-low latency," may be used. Of course, by taking advantage of the features of newer mobile phone systems beyond 5G, secondary effects such as faster processing and higher resolution rendering of output information in the business negotiation support method according to the present invention can also be expected.

[0040] Furthermore, data exchange between the business negotiation support system 1, the biometric information reading unit 100, the screen display unit 110, and the analysis database 130 may be carried out, for example, according to an API (Application Programming Interface) protocol. In that case, it is assumed that each device has already implemented the functions and configurations necessary to perform API request and response processing.

[0041] <About each functional part> Next, we will describe the analysis unit 121 and the learning unit 126 of the analysis server 120. The analysis unit 121 includes an emotion estimation unit 122 and a recommendation unit 124. The emotion estimation unit 122 can utilize the emotion estimation model 123. The recommendation unit 124 can utilize the action recommendation model 125.

[0042] Of the above, the emotion estimation unit 122 acquires at least one of the customer's biometric information 133, which includes the customer's facial expression, body movements, body temperature, and voice, from the biometric information reading unit 100 at regular intervals or in real time, and estimates the customer's emotional state based on this information. More specifically, the emotion estimation unit 122 inputs the customer's biometric information 133 obtained from the biometric information reading unit 100 into the emotion estimation model 123 and obtains the emotional state, which is the response, as the estimation result.

[0043] In this case, the emotion estimation model 123 is a model obtained by training a deep learning engine 1012 (or an external deep learning engine provided on the network N) using a set of data consisting of biometric information 133 for each customer with whom there have been past business negotiation opportunities and the emotional state of that customer during the negotiation as training data.

[0044] The information on the emotional state of customers during business negotiations, which constitutes the above-mentioned learning data, could be extracted from, for example, the results of post-negotiation or post-sale surveys or interviews with those customers (of course, this is just one example). Furthermore, this emotional state information could include the proportions of positive, negative, and neutral responses.

[0045] Therefore, the emotion estimation result obtained by the emotion estimation unit 122 inputting the customer's biometric information 133 into the emotion estimation model 123 may show the proportions of positive, negative, and neutral emotions, respectively.

[0046] Furthermore, the recommendation unit 124 is a functional unit that determines a suitable negotiation strategy for a customer by providing the action recommendation model 125 with the current emotional state (or its estimated result) and the current negotiation status 134 of the customer obtained from the emotion estimation unit 122, as well as past negotiation results from the past negotiation DB 132. The negotiation strategy obtained through this determination may include various things that the sales representative can consider and implement with the customer during the negotiation, such as the amount of discount to offer the customer and whether or not there is one, the content and whether or not additional options are proposed, the content, frequency, manner of speaking, and gestures of topics for negotiation.

[0047] The action recommendation model 125 used by this recommendation unit 124 identifies past sales negotiation results that are similar to the customer's emotional state and current sales negotiation status 134, based on the similarity between a vector 141 corresponding to the customer's emotional state during a sales negotiation (obtained from the emotion estimation unit 122) and the customer's current sales negotiation status 134 (for example, input by the sales representative during the negotiation using a tablet or smartphone), and vectors corresponding to each past sales negotiation result in the past sales negotiation DB 132. It then determines the sales negotiation strategy from the identified past sales negotiation results.

[0048] Therefore, the action recommendation model 125 is a model obtained by training a deep learning engine 1012 (or an external service deep learning engine provided on network N) using a set of data as training data, which includes the emotional state of each customer during negotiations (e.g., the proportion of positive, negative, and neutral) and the negotiation status 134 at the time (e.g., the number of visits, negotiation status, customer desired products, discount amount requested by the customer or offered by the sales representative, etc.), as well as the details of the deal concluded (which was a deal) and the negotiation strategy (specific details of the negotiation strategy adopted at the time).

[0049] The learning data described above includes information such as the details of the deals concluded and the negotiation strategy, which can be extracted from past negotiation history managed by the sales office's business management system or the sales representative's tablet or smartphone (this is, of course, just one example).

[0050] The recommendation unit 124 outputs the information on the sales negotiation policy determined as described above to the screen display unit 110. The screen display unit 110 is, for example, a terminal at a sales negotiation store where the sales negotiation support service by the sales negotiation support system 1 is provided. This terminal may include a tablet terminal or personal computer installed at the sales negotiation store for sales negotiation support, as well as a sales representative's smartphone.

[0051] Furthermore, the recommendation unit 124 can dynamically update the sales strategy based on the real-time changes in the customer's emotional state estimated by the emotion estimation unit 122. For this reason, the recommendation unit 124 provides the action recommendation model 125 with a prompt requesting a re-estimation of the sales strategy, which includes information on the latest emotional state or the change from the previous emotional state, and obtains a sales strategy that matches the latest emotional state.

[0052] Furthermore, if the action recommendation model 125 is a generative AI or has the functionality of a language model, the recommendation unit 124 may more preferably generate a recommendation statement in natural language by providing the action recommendation model 125 with a prompt requesting it to output a sales strategy for the customer in a natural conversational format. Of course, if the action recommendation model 125 is not a generative AI or does not have such functionality, the recommendation unit 124 or the action recommendation model 125 may send a prompt for generating a recommendation statement, including the sales strategy determination result, to an external generative AI service provided on the network N, and obtain the recommendation statement.

[0053] Furthermore, the learning unit 126 is a functional unit that stores the customer's emotional state and the results of the business negotiations related to that customer in the analysis database 130 (storage unit). The learning unit 126 is also a functional unit that uses the deep learning engine 1012 to train the action recommendation model 125 and the emotion estimation model 123. For example, the learning unit 126 uses a set of data—the customer's emotional state, the customer's business negotiation status 134, and the results of the business negotiations—as training data to perform machine learning on the action recommendation model 125. Alternatively, it uses a set of data—the customer's biometric information 133 and the customer's emotional state—as training data to perform machine learning on the emotion estimation model 123.

[0054] <Sales Negotiation Support Method: Emotion Estimation Flow> Next, the processing flow in the sales negotiation support method of this embodiment will be described. Figure 6 is a diagram showing an example of the flow of the sales negotiation support method of this embodiment, and more specifically, it is a diagram showing an example of the processing flow in the emotion estimation unit 122. In this case, the emotion estimation unit 122 acquires biometric information 133 of the customer during the sales negotiation from the biometric information reading unit 100 (S10). As shown in Figure 7A, this customer biometric information 133 includes information such as the customer's facial expression, body movements, body temperature, and voice.

[0055] Next, the emotion estimation unit 122 inputs the customer's biometric information 133 obtained in S10 into the emotion estimation model 123 and obtains the emotion analysis result 135, which is the estimation result (S11). As shown in Figure 7B, the emotion analysis result 135 shows the proportion of positive, negative, and neutral emotions.

[0056] Furthermore, the emotion estimation unit 122 outputs the emotion analysis result 135 obtained in S11 to the recommendation unit 124 (S12), and this flow ends.

[0057] <Sales Negotiation Support Method: Recommendation Flow> Next, the processing flow in the recommendation unit 124 will be explained based on Figure 8. Figure 8 is a flowchart showing the processing of the recommendation unit 124 in this embodiment. Here, it is assumed that a sales representative in the middle of a business negotiation accesses the analysis server 120 by operating a tablet terminal or the like, and performs a function call operation of the recommendation unit 124 via an appropriate interface. In other words, this sales representative wants to obtain suggestions on the negotiation strategy for the customer they are currently negotiating with.

[0058] Meanwhile, the recommendation unit 124 receives the above function call operation (S20) and calls the action recommendation model 125 (S21). As already mentioned, the action recommendation model 125 is a model that responds with an appropriate sales strategy, i.e., a sales action, to the customer in question by inputting the sentiment analysis result 135 (emotional state) and the current sales negotiation status 134 (S22).

[0059] As shown in Figure 9A, specific examples of the above-mentioned negotiation status 134 include information such as the number of times the customer has visited the store, the negotiation status, the product they are interested in, and the discount amount. Furthermore, as shown in Figure 9B, the sentiment analysis results 135 represent information showing the proportion of positive, negative, and neutral emotions of the customer.

[0060] More specifically, the recommendation unit 124 vectorizes the sentiment analysis results 135 and the current negotiation status 134 information into a single chunk (S23) to create a vector 141 representing the current negotiation status, and compares the similarity between this vector and a vector representing past negotiation statuses stored in the knowledge DB 131 (S24). This allows the recommendation unit to extract information on similar past negotiations 137 that have similar customer characteristics and emotional states. These similar past negotiations 137 become the target records in the customer information table 1311, the discount history information table 1312, and the action history information table 1313, as shown in Figure 9D.

[0061] Furthermore, the recommendation unit 124 identifies action candidates 136 from the past sales negotiation history (and successful deals) with a high degree of similarity obtained from the above comparison (S25). These action candidates 136 include information such as whether or not a discount was offered, the amount of the discount, and actions other than discounts, as shown in Figure 9C.

[0062] For example, if the action candidate 136 identified here is "discount," the recommendation unit 124 calculates the discount amount by applying the discount rate indicated by the action candidate to the price of the product or service currently under negotiation (for example, the value indicated by the negotiation status 134).

[0063] Next, the recommendation unit 124 requests a predetermined generation AI to create a recommendation text for the sales representative based on the information of the action candidates 136 obtained in S25, and obtains the recommendation text (S26). The recommendation unit 124 also displays the recommendation text obtained in S26 on the screen display unit 110 of a tablet terminal or the like that the sales representative will view (S27). An example of such a screen display unit 110 is shown in Figure 10. The screen display unit 110 shown in Figure 10 has a screen configuration that includes at least a display field G11 for the sentiment analysis results 135 related to the target customer and a display field G11 for the action candidates 136 on screen G10.

[0064] As shown in Figure 10, the action candidates 136 may be displayed in multiples rather than just one. Furthermore, when multiple candidates are displayed, the action candidates 136 may be sorted in descending order of similarity to the vectors mentioned above.

[0065] Meanwhile, the sales representative views screen G10 on the display unit 110 and decides which action to take for the customer they are currently negotiating with. When the sales representative taps the "Select" button for the action candidate 136 they have decided to adopt, the learning unit 126 obtains the results of the negotiation strategy adopted by the sales representative for that negotiation and can use this to train the action recommendation model 125. The operation flow of this learning unit 126 will be explained next.

[0066] <Methods for supporting business negotiations: Learning flow> The learning unit 126 can use the information of the action candidates 136 selected by the sales representative as learning data and store it, for example, in the knowledge database 1023. The operation flow of this learning unit 126 will be explained based on Figure 11.

[0067] In this case, the learning unit 126 receives the selection operation of the action candidate 136 on the screen display unit 110 of the sales representative's tablet terminal, etc. (S30). The action candidate 136, or selected action 138, that is the target of this selection operation is the action selected by the sales representative on screen G10 in Figure 10, as shown in Figure 12A.

[0068] At this time, the learning unit 126 also acquires information on the change in the target customer's emotions 139 that occurred as a result of the sales representative performing the selection action 138, and the final negotiation result 140 of the negotiation, and registers this information on the selection action 138, the change in the customer's emotions 139, and the negotiation result 140 in the analysis database 130 (S31).

[0069] Of the information registered here, the customer's emotional change 139 includes the customer's biometric information 133 before and after the execution of the selection action 138, as shown in Figure 12B. Therefore, the learning unit 126 acquires the target customer's biometric information 133 before and after the execution of the selection action 138 from the biometric information reading unit 100. In addition, the negotiation result 140 is information indicating one of the following statuses: deal concluded, deal not concluded, or under consideration, as shown in Figure 12C. Therefore, the learning unit 126 acquires status information regarding the target negotiation, for example, entered by the sales representative using the sales representative's tablet terminal or smartphone, and obtains information on the success or failure of the negotiation as the negotiation result 140.

[0070] Furthermore, the learning unit 126 performs a nearest neighbor search using the action recommendation model 125. It vectorizes the information obtained in S30 (S32), stores the result in the knowledge database 131 (S33), and terminates this flow.

[0071] As described above, the business negotiation support system 1 in this embodiment makes it possible to propose appropriate negotiation content while accurately taking into account the customer's intentions and other factors during business negotiations.

[0072] It should be noted that the present invention is not limited to the embodiments described above, but includes various modifications and equivalent configurations within the spirit of the attached claims. For example, the embodiments described above are described in detail for the purpose of clearly illustrating the present invention, and the present invention is not necessarily limited to having all the described configurations. Furthermore, some of the configurations of one embodiment may be replaced with those of another embodiment. Furthermore, configurations of other embodiments may be added to the configuration of one embodiment. Furthermore, some of the configurations of each embodiment may be added, deleted, or replaced with those of other embodiments.

[0073] Furthermore, each of the aforementioned configurations, functions, processing units, and processing means may be implemented in hardware, for example, by designing them as integrated circuits, or they may be implemented in software by having a processor interpret and execute programs that realize each function.

[0074] Information such as programs, tables, and files that implement each function can be stored in memory, hard disks, SSDs (Solid State Drives), or other storage devices, or in recording media such as IC cards, SD cards, or DVDs. Furthermore, some or all of the above configurations, functions, processing units, and processing means may be implemented in hardware, for example, by designing them as integrated circuits. Alternatively, the above configurations and functions may be implemented in software by a processor interpreting and executing programs that implement each function. Information such as programs, tables, and files that implement each function can be stored in memory, hard disks, SSDs (Solid State Drives), or other storage devices, or in recording media such as IC cards, SD cards, or DVDs.

[0075] Furthermore, the control lines and information lines shown are those deemed necessary for explanation purposes and do not necessarily represent all control lines and information lines required for implementation. In reality, it can be assumed that almost all components are interconnected.

[0076] Furthermore, this embodiment can be applied to various business negotiations other than vehicle sales, and does not limit its application to products, services, industries, business types, or business content from various perspectives.

[0077] Furthermore, the above explanations can be summarized as follows. The following summary may include supplementary explanations and explanations of variations of the above explanations. In the sales support system 1 of this embodiment, the recommendation unit may determine the discount amount to be offered to the customer as a sales strategy for the customer, based on the customer's emotional state, the customer's current sales negotiation status 134, and the past sales negotiation results, and output information on the discount amount.

[0078] According to this system, sales representatives will be able to recognize and appropriately utilize information on highly accurate discount amounts estimated based on past sales performance as the basis for proposing discounts to target customers during business negotiations. Ultimately, this will enable them to propose more appropriate negotiation terms while accurately taking into account the customer's intentions and other factors during business negotiations.

[0079] Furthermore, in the sales negotiation support system 1 of this embodiment, the recommendation unit may dynamically update the sales negotiation policy based on the real-time changes in the customer's emotional state estimated by the emotion estimation unit.

[0080] This approach allows sales representatives to receive timely negotiation strategies that take into account the changing customer psychology based on the history and progress of the negotiations, providing them with support for conducting effective negotiations. Ultimately, it enables the proposal of more appropriate negotiation content while accurately considering the customer's intentions during the negotiations.

[0081] Furthermore, in the sales negotiation support system 1 of this embodiment, the recommendation unit may identify past sales negotiation results that contain content similar to the customer's emotional state and the customer's current sales negotiation status 134, based on the similarity between the vector 141 corresponding to the customer's emotional state and the customer's current sales negotiation status 134 and the vector corresponding to past sales negotiation results, and determine the sales negotiation policy from the identified past sales negotiation results.

[0082] This allows for the extraction and selection of past negotiation results that accurately match the target customer and the status and history of negotiations related to that customer, which serve as the basis for determining negotiation strategies. Ultimately, this enables the proposal of more appropriate negotiation content while accurately taking into account the customer's intentions during negotiations.

[0083] Furthermore, the business negotiation support system 1 of this embodiment may further include a learning unit 126 that stores the customer's emotional state and the results of the business negotiation concerning the customer in the storage unit.

[0084] According to this, each time the negotiation support method of the present invention is executed, training data for the algorithm for determining the negotiation strategy (specifically, the determination model obtained by deep learning) is accumulated, making it possible to continuously improve the accuracy of the algorithm thereafter. In turn, it becomes possible to propose more appropriate negotiation content while accurately taking into account the customer's intentions and other factors in the negotiation.

[0085] Furthermore, in the sales negotiation support system 1 of this embodiment, the learning unit 126 may use the set of the customer's emotional state, the customer's sales negotiation status 134, and the result of the customer's sales negotiation as learning data to perform machine learning on the sales negotiation policy determination model in the recommendation unit.

[0086] This makes it possible to continuously improve the accuracy of negotiation strategy decisions efficiently. Ultimately, it becomes possible to propose more appropriate negotiation content while accurately taking into account the customer's intentions and other factors during negotiations.

[0087] Furthermore, in the business negotiation support system 1 of this embodiment, the emotion estimation unit may estimate the proportion of positive, negative, and neutral states as the emotional state of the customer based on the customer's biometric information 133.

[0088] This allows for a more accurate estimation of the customer's emotional state. Consequently, it becomes possible to propose more appropriate negotiation strategies while accurately taking into account the customer's intentions and other factors during business negotiations.

[0089] Furthermore, in the business negotiation support system 1 of this embodiment, the emotion estimation unit may estimate the emotional state of the customer based on at least one of the customer's biometric information 133, which includes the customer's facial expression, body movements, body temperature, and voice.

[0090] This approach allows for the adoption of appropriate information as a basis for estimating the customer's emotional state, thereby improving the accuracy of the emotional state estimation. Ultimately, this enables the proposal of more appropriate negotiation strategies while accurately considering the customer's intentions and other factors during business negotiations.

[0091] Furthermore, in the sales negotiation support system 1 of this embodiment, the recommendation unit may provide the generating AI with a prompt containing the sales negotiation policy information, thereby causing the generating AI to generate a recommendation statement, and outputting the recommendation statement.

[0092] This allows sales representatives to receive information on negotiation strategies in a conversational format that is easy for them to understand. Ultimately, this enables them to propose more appropriate negotiation strategies while accurately considering the customer's intentions and other factors during negotiations. [Explanation of Symbols]

[0093] N Network 1. Sales negotiation support system 100 Biometric Information Reading Unit 1001 Reading Unit 110 Screen display section 120 Analysis Servers 121 Analysis Department 122 Emotion estimation part 123 Emotion Estimation Models 124 Recommendation Department 125 Action Recommended Models 126 Learning Department 130 Databases for Analysis 131 Knowledge DB 1311 Customer Information Table 1312 Discount History Information Table 1313 Action History Information Table 132 Past business negotiations DB 133 Customer biometric information 134 Business Negotiation Status 135 Sentiment analysis results 136 Action Options 137 Past Similar Deals 138 Select Actions 139 Changes in customer emotions 140 Negotiation results 141 Current negotiation status + vector representing customer emotions 101 Auxiliary storage 1011 Program 1012 Deep Learning Engine 102 CPU (Processor) 103 Main storage 104 Communication equipment

Claims

1. A memory unit that stores past business negotiation results, An emotion estimation unit that estimates the customer's emotional state based on the customer's biometric information during a business negotiation, A recommendation unit that determines a sales strategy for the customer based on the customer's emotional state, the customer's current sales negotiation status, and the results of past sales negotiations, and outputs information on the sales strategy; A business negotiation support system equipped with these features.

2. The recommendation unit is, Based on the customer's emotional state, the customer's current negotiation status, and the past negotiation results, the system determines the discount amount to offer the customer as a negotiation strategy and outputs information on that discount amount. The business negotiation support system according to claim 1.

3. The recommendation unit is, Based on the real-time changes in the customer's emotional state estimated by the emotion estimation unit, the sales negotiation strategy is dynamically updated. The business negotiation support system according to claim 1.

4. The recommendation unit is, Based on the similarity between the vector corresponding to the customer's emotional state and the customer's current negotiation status and the vector corresponding to past negotiation results, the system identifies past negotiation results that contain content similar to the customer's emotional state and the customer's current negotiation status, and determines the negotiation strategy from the identified past negotiation results. The business negotiation support system according to claim 1.

5. The system further includes a learning unit that stores the customer's emotional state and the results of business negotiations with the customer in the memory unit. The business negotiation support system according to claim 1.

6. The aforementioned learning unit, The set of the customer's emotional state, the customer's negotiation status, and the outcome of the negotiation is used as training data to perform machine learning on the model for determining the negotiation strategy in the recommendation unit. The business negotiation support system according to claim 5.

7. The emotion estimation unit, Based on the customer's biometric information, the proportion of each state—positive, negative, and neutral—is estimated as the customer's emotional state. The business negotiation support system according to claim 1.

8. The emotion estimation unit, Based on at least one of the customer's biometric information, such as facial expressions, body movements, body temperature, and voice, the emotional state of the customer is estimated. The business negotiation support system according to claim 1.

9. The recommendation unit is, By providing the generating AI with a prompt containing the aforementioned negotiation policy information, the generating AI generates a recommendation statement and outputs the recommendation statement. The business negotiation support system according to claim 1.

10. Information processing device, By retaining past negotiation results, A process for estimating the emotional state of a customer based on their biometric information, A process that determines a sales strategy for the customer based on the customer's emotional state and past sales negotiation results, and outputs information about the sales strategy. A sales negotiation support method that implements this.

Images