Sales support system, sales support device, sales support method, and program

Abstract

This system provides a structured and objective visualization of user behavior during business negotiations between users and their customers, effectively supporting the improvement of users' negotiation skills. [Solution] The system includes a storage unit 120 that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales negotiation script showing the content of a sales negotiation conducted between a first user and a second user, an appeal topic indicating the selling points of the product that is the subject of the sales negotiation corresponding to the needs, and coupling information indicating the coupling relationship between the needs topic and the appeal topic; an acquisition unit 131 that acquires the sales negotiation script to be analyzed; an analysis unit 132 that analyzes the sales negotiation script to be analyzed using a large-scale language model and generates comparison results that determine whether there is a match or a difference for each needs topic and appeal topic of the master needs information; and a display control unit 133 that reflects the comparison results in the master needs information and displays it to the user.

Description

Technical Field

[0001] The present disclosure relates to a business support system, a business support device, a business support method, and a program.

Background Art

[0002] As technologies for supporting business activities, CRM (Customer Relationship Management) systems and SFA (Sales Force Automation) systems that manage customer information, business negotiation histories, etc. are widely used. These systems contribute to the efficiency of business operations by accumulating and managing data related to business activities. In recent years, with the development of artificial intelligence (AI), particularly large language models (LLMs), technologies for analyzing conversations in business activities have emerged. For example, technologies such as automatically transcribing the voices of business negotiations and creating meeting minutes, and analyzing the frequency of appearance of specific keywords in conversations are known.

[0003] For example, Patent Document 1 describes a system comprising means for collecting the plan and service information of one's own company and other companies, and the conversation contents of excellent employees of one's own company and storing them in a database, means for preprocessing the stored data and training it using a generated AI model, and means for analyzing inquiries from users and generating optimal answers using the generated AI model.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the conventional technologies described above only provide the optimal answer to an inquiry, and have the drawback that they do not allow the person in charge to understand why that answer is optimal or to develop the logical thinking necessary to obtain the optimal answer.

[0006] Furthermore, with conventional sales support tools, feedback to sales representatives tended to be limited to comparing quantitative indicators such as the number of calls made, or pointing out the quality of individual sales pitches. As a result, it was difficult to identify the fundamental factors that led to the high closing rates of top sales representatives—namely, structural differences such as the strategic flow of the entire sales negotiation and the skill in deeply exploring customer needs. Consequently, guidance for sales representatives became abstract and did not easily translate into concrete improvement actions.

[0007] Therefore, this disclosure aims to provide a sales support system, sales support device, sales support method, and program that can structurally and objectively visualize the user's behavior in business negotiations between the user and the user's customers, and effectively support the improvement of the user's negotiation skills. [Means for solving the problem]

[0008] The sales support system relating to this disclosure includes: a storage unit that stores master needs information, which includes: a needs topic that indicates the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic that indicates the selling points of the product that is the subject of the sales negotiation corresponding to the needs; and coupling information that indicates the coupling relationship between the needs topic and the appeal topic; an acquisition unit that acquires a sales script to be analyzed; an analysis unit that analyzes the sales script to be analyzed using a large-scale language model and generates comparison results that determine whether there is a match or a difference for each of the needs topic and the appeal topic of the master needs information; and a display control unit that reflects the comparison results in the master needs information and displays it on a user terminal.

[0009] The sales support device relating to this disclosure includes: a storage unit that stores master needs information, which includes: a needs topic that indicates the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic that indicates the selling points of the product that is the subject of the sales negotiation corresponding to the needs; and coupling information that indicates the coupling relationship between the needs topic and the appeal topic; an acquisition unit that acquires a sales script to be analyzed; an analysis unit that analyzes the sales script to be analyzed using a large-scale language model and generates comparison results that determine whether there is a match or a difference for each of the needs topic and the appeal topic of the master needs information; and a display control unit that reflects the comparison results in the master needs information and displays it on a user terminal.

[0010] Furthermore, the sales support method performed by the computer relating to this disclosure includes a computer having a storage unit that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic indicating the selling points of the product that is the subject of the sales negotiation corresponding to the needs; and coupling information indicating the coupling relationship between the needs topic and the appeal topic. The computer then performs the steps of: acquiring a sales script to be analyzed; analyzing the sales script to be analyzed using a large-scale language model to generate comparison results determining whether there is a match or a difference for each needs topic and appeal topic in the master needs information; and reflecting the comparison results in the master needs information and displaying it on a user terminal.

[0011] The program relating to this disclosure causes a computer equipped with a storage unit that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic indicating the selling points of the product that is the subject of the sales negotiation corresponding to the needs; and coupling information indicating the coupling relationship between the needs topic and the appeal topic. The computer then performs the steps of: acquiring a sales script to be analyzed; analyzing the sales script to be analyzed using a large-scale language model to generate comparison results determining whether there is a match or a difference for each of the needs topic and the appeal topic in the master needs information; and displaying the comparison results reflected in the master needs information on a user terminal. [Effects of the Invention]

[0012] According to the present disclosure, which has the configuration described above, it is possible to provide a sales support system, sales support device, sales support method, and program that can structurally and objectively visualize the user's actions in business negotiations between the user and the user's customers, and effectively support the improvement of the user's negotiation skills. [Brief explanation of the drawing]

[0013] [Figure 1] This is a schematic diagram showing a sales support system according to an embodiment of this disclosure. [Figure 2] This is a functional block diagram of a sales support server according to an embodiment of this disclosure. [Figure 3] This figure shows an example of information contained in the storage unit of a sales support server according to the embodiment of this disclosure. [Figure 4] This is a functional block diagram of a user terminal according to an embodiment of this disclosure. [Figure 5] This is a flowchart showing the analysis process performed by the sales support system according to the embodiment of this disclosure. [Figure 6]This is a flowchart showing the master data generation process by the sales support system according to the embodiment of this disclosure. [Figure 7] This is a flowchart showing the master data update process by the sales support system according to the embodiment of this disclosure. [Figure 8] This figure shows a specific example of a screen displayed on a user terminal according to the embodiment of this disclosure. [Figure 9] This is a diagram showing the basic configuration of a computer. [Modes for carrying out the invention]

[0014] Hereinafter, the sales support system 1 according to an embodiment of this disclosure will be described with reference to the drawings. In all the drawings illustrating the embodiments, common components are denoted by the same reference numerals, and repeated explanations are omitted.

[0015] <System Configuration> Figure 1 is a schematic diagram showing a sales support system 1 according to an embodiment of this disclosure. The sales support system 1 is a system that analyzes a business negotiation conducted between a first user and a second user who is a customer of the first user, and provides feedback on the negotiation to the first user. In this embodiment, the first user will be described below as the sales representative (hereinafter sometimes simply referred to as the representative) of the product handled in the negotiation. Sales representatives include those who acquire new customers, those who secure additional orders from existing customers, those who deliver and provide services like consultants, those who schedule appointments for business meetings via telephone like inside sales representatives, and those who communicate the value of services and conduct conversations regarding their operation. Furthermore, "customers" refers to those who are considering introducing a product or service, as well as those who have already introduced and are involved in its operation. For example, customers generally include all company representatives who are using the service, as well as prospective customers who are considering using it, and consultants from other companies who advise prospective customers on service introduction. In addition, business negotiations include interviews regarding order-taking and delivery / service provision operations after an order is received, in addition to interviews for making decisions to contract or purchase so-called services and products. Order-taking and delivery / service provision operations refer to activities of hearing problems and needs through interviews with customers after a contract is concluded and presenting solutions as appeals, including activities for enabling customers to make good use of services and activities where a consultant provides services. Interviews include face-to-face, telephone, online interviews, etc., and are activities in which exchanges of statements are continuously conducted within a predetermined time period.

[0016] The sales support system 1 includes a sales support server (sales support device) 100 and a user terminal 200. In the system configuration example shown in FIG. 1, only one sales support server 100 and one user terminal 200 are shown, but a plurality of each may be provided. The sales support server 100 and the user terminal 200 are connected to a network NW and can communicate with each other via the network NW. The network NW includes the Internet. The network NW may include a LAN (Local Area Network) and / or a WAN (Wide Area Network).

[0017] The sales support server 100 and the user terminal 200 are each composed of one or a plurality of computers 900. The basic configuration of the computer 900 will be described later.

[0018] FIG. 2 is a functional block diagram of the sales support server 100 according to an embodiment of the present disclosure. The sales support server 100 is an information processing device that provides the sales support function according to this embodiment. The sales support server 100 may be, for example, a physically single server computer, or may be a server group in which a plurality of server computers cooperate to function. Further, the sales support server 100 may be a virtual server constructed in a cloud computing environment. The sales support server 100 provides a sales support service (sales support function) to the user terminal 200, for example, in the form of software as a service (SaaS: Software as a Service).

[0019] The sales support server 100 comprises a communication unit 110, a storage unit 120, and a processing unit 130.

[0020] The communication unit 110 is a network interface and communicates with the user terminal 200 via the network NW. The communication unit 110 passes data received from the user terminal 200 to the processing unit 130 and also transmits data generated by the processing unit 130 to the user terminal 200.

[0021] The storage unit 120 is configured using a storage device such as a magnetic hard disk or a semiconductor storage device. The storage unit 120 stores various information necessary for the sales support server 100 to function. For example, the storage unit 120 stores application programs 121, a database 122 that manages user account information and information related to sales support services, a learning model 123, etc. The storage unit 120 may be provided externally to the sales support server 100 so as to be able to communicate with it.

[0022] Figure 3 shows an example of information stored in the database 122 of the storage unit 120. Figure 3 shows the structure of the five main databases used in the sales support system 1. In the following description and figures, "database" may be abbreviated as "DB". Database 122 includes the Value Map DB, Script DB, Analysis DB, Product DB, and Personnel DB. These databases are managed by a relational database management system (RDBMS), etc.

[0023] The script database is a database that stores the scripts of business negotiations and related information that are the target of analysis and learning. The scripts include video scripts and audio scripts. Video scripts are text-based descriptions of the video's content, and include not only the dialogue and narration within the video, but also the video's constituent elements (scene transitions, the movements of the characters (gestures, screen sharing), text displayed on the screen or shared documents, instructions for background music and sound effects, etc.). Audio scripts are text-based descriptions of the audio data's content, and mainly refer to text transcribed from the audio data using speech recognition technology. In both cases, the scripts include not only the content of the statements but also the names of the speakers associated with those statements. Specifically, the script database is a database that stores sales scripts, which are scripts extracted from sales video and / or audio recordings of sales negotiations conducted between a sales representative (first user) and a customer (second user), as well as related information. The script ID stores a unique identifier that uniquely identifies each script. The type stores information indicating whether the script is for "analysis," "master generation," "master update," or "training (including additional training)." The basic negotiation information stores basic details such as the date and time of the negotiation, the contact person's ID, the product ID, attendees, and the customer. The format stores information indicating whether the script was in the format of "video, audio, text, etc." The success or failure of a business negotiation is recorded by documenting whether the negotiation resulted in a deal being closed (success / failure).

[0024] The Value Map DB is a database that stores and manages master needs information, which structures the ideal sales negotiation flow from customer needs (problems) to selling points. Each piece of master needs information is extracted and stored through the master generation process and master update process described later. In this embodiment, master needs information is generated for each product. Master needs information includes template ID, target product, needs topic, selling topic, combination information, example information, and closing information. Master needs information is used to generate the value map described later. Customer needs are the problems or issues that customers want to solve, expressed in the form of desires such as "I want to do ~". In other words, needs are the inverse of the problems or issues that need to be solved, and refer to the desire to seek their solution. For example, the problem "We are not able to convey the appeal of our business / operations" corresponds to the need "I want to convey the appeal of our business / operations". The template ID stores a unique identifier that uniquely identifies each piece of master needs information. The target product stores information (product ID) that indicates which product the master needs information pertains to. Needs topics are information that represents customer needs extracted from sales scripts. Each needs topic is managed with the following information for each customer need: "Needs ID," "Content (text data)," and "Process and hierarchy (one of the following: expressed needs process, intermediate needs process, or essential needs process, and the depth of the hierarchy)." A selling topic is information that indicates the selling points of the product or service being offered in a deal, in response to the customer's needs. The selling points of a product or service are also the selling points of that product or service. Selling topics manage the selling points for each need using the following information: "selling point ID," "content (text data)," and "process and hierarchy (either an intermediate selling point process or a final selling point process, and the depth of the hierarchy)." Joint information is information that shows the relationship between two needs topics and / or appeal topics (hereinafter sometimes simply referred to as topics). Specifically, it is, for example, the relationship between one needs topic and another needs topic, the relationship between one appeal topic and another appeal topic, or the relationship between one needs topic and another appeal topic. Joint information stores the combination of the "needs ID" and / or "appeal point ID" of the two topics. In addition, as supplementary information to the joint relationship, the joint information includes a correlation coefficient that shows the correlation with the closing of a sale. The correlation coefficient is calculated, for example, by analyzing a large number of past closing cases and based on the closing rate when a specific appeal point is presented after a specific need is presented. The correlation coefficient may also be determined, for example, based on the behavioral data of top sales representatives (identification of needs and presentation of appeal points) included in the sales scripts of top sales representatives. The correlation coefficient is information that can identify joint relationships that are points where the closing rate improves. The example information stores specific examples of selling points, such as example or training materials like "partial sales negotiation script" files, advice information, or references to these, linked to the selling topic (selling point ID). Closing information is information about the closing of a sales opportunity, extracted from the sales script. Closing information includes a closing ID and a content section. The closing ID is a unique identifier that uniquely identifies each closing information. The content section stores the specific details of the closing as text data.

[0025] The analysis database is a database that stores the analysis results obtained when sales negotiation scripts are compared with master needs information (value map). The analysis ID stores a unique identifier that uniquely identifies the analysis result. The system analyzes the scripts and stores the script IDs of the scripts being analyzed. The application map stores the template ID of the master needs information (value map) used for the analysis. The comparison results store the results of comparing each item in the master needs information (value map) with the details of the business negotiation.

[0026] The product database is a database that manages information about the products and / or services that are the subject of a sales opportunity. The product ID stores a unique identifier that uniquely identifies the product. The product name remembers the name of the product.

[0027] The Sales Representative Database is a database that manages information about sales representatives. The 담당자 ID stores a unique identifier that uniquely identifies the person in charge. Remember the name of the person in charge.

[0028] Returning to Figure 2, let's continue the explanation of the memory unit 120. The learning model 123 is a learning model that takes a sales negotiation script as input to generate master needs information, and extracts and generates "needs topics," "appeal topics," "combination information," and "correlation coefficients." The learning model 123 particularly includes a Large Language Model (LLM). A Large Language Model is a neural network model pre-trained using a vast amount of text data and has advanced natural language processing capabilities such as text generation, summarization, classification, and semantic analysis. As the learning model 123, for example, GPT (Generative Pre-trained Transformer) type models and BERT (Bidirectional Encoder Representations from Transformers) type models can be used. Alternatively, these general-purpose models may be fine-tuned using sales negotiation data from a specific industry or company to create a dedicated model. Furthermore, the learning model 123 may include other types of machine learning models, such as classification models for predicting the success or failure of a sales negotiation, or regression models for evaluating the performance of sales representatives.

[0029] The processing unit 130 comprises, as functional units, an acquisition unit 131, an analysis unit 132, a display control unit 133, an improvement suggestion unit 134, a master generation unit 135, and a learning unit 136. The processing unit 130 realizes each of these functional units by executing the application program 121 stored in the storage unit 120, and performs analysis processing, master generation processing, and master update processing. The analysis processing, master generation processing, and master update processing perform a series of processes including the steps described later. Details of the analysis processing, master generation processing, and master update processing will be described later.

[0030] The acquisition unit 131 has the function of acquiring various types of information from other devices and the storage unit 120.

[0031] The acquisition unit 131 acquires the sales negotiation script from the user terminal 200 and stores it in the storage unit 120. The user uploads the sales negotiation script to be analyzed from the user terminal 200 to the sales support server 100 in order to execute the analysis process. The sales negotiation script to be analyzed is data used to analyze the performance of sales negotiations conducted by individual sales representatives. The user uploads the sales negotiation script for master generation from the user terminal 200 to the sales support server 100 in order to execute the master generation process. The sales negotiation script for master generation is data used to generate new master needs information that serves as the basis for analysis. The user uploads the sales negotiation script for master update to the sales support server 100 in order to execute the master update process. The additional sales negotiation script for master generation is data used to update and refine existing master needs information. The user uploads the sales negotiation script for training in order to generate a learning model. The acquisition unit 131 acquires the sales negotiation script uploaded by the user and stores it in the script DB of the storage unit 120.

[0032] The analysis unit 132 analyzes the linguistic content of the sales negotiation script to be analyzed using a large-scale language model (LLM), segments it into semantically coherent partial sales negotiation scripts, and generates comparison results that determine whether there is a match or a difference for each needs topic and appeal topic of the master needs information. The determination of a match is not based on simple keyword matching, but on the contextual understanding ability and semantic similarity calculation ability of the large-scale language model (LLM). For example, if the needs topic is "decreased work efficiency," then if the sales negotiation script contains expressions such as "the work takes a long time" or "there is a lot of unnecessary manual work," it will be determined to be semantically matched. Furthermore, if there are achievement conditions set for the needs topic, the analysis unit 132 will determine the match for the partial sales negotiation script, including whether or not the achievement conditions have been met. An achievement condition is, for example, customer agreement. Customer agreement, for example, in the case of a needs topic, is when the sales representative paraphrases the customer's statement into an expressed need (or equivalent content as described later), and the customer responds with agreement such as "Yes, that's right" or nods on the screen. Furthermore, in the case of a selling topic, this could be a positive response from the customer after the sales representative mentions the selling topic of the final selling point, as described later. On the other hand, the analysis unit 132 determines that there is a discrepancy if the partial sales negotiation script does not semantically match the needs topic or selling topic, or if it does not meet the achievement conditions.

[0033] Furthermore, the analysis unit 132 may have a function to acquire audio data, etc., in real time during a business negotiation and perform analysis on the spot. In this case, the analysis unit 132 transcribes the video data or audio data of the business negotiation transmitted in streaming format from the user terminal 200 into text in real time and performs sequential analysis. When an utterance matching a specific needs topic is detected in the business negotiation script, that information is immediately passed to the improvement suggestion unit 134.

[0034] The display control unit 133 reflects the comparison results in the master needs information and displays them on the user terminal 200.

[0035] The display control unit 133 may display the master needs information on the user terminal 200 in the form of a tree-like value map as shown in Figure 8. The display layout can be arbitrarily set to a vertical tree, a horizontal tree, or a format that radiates outwards from the center.

[0036] The display control unit 133 displays the needs topic, appeal topic, and combined information of the master needs information on the user terminal 200, and visually displays the match or difference in the comparison results for the needs topic and appeal topic, respectively. The display control unit 133 may also highlight the combined information if there is a combined relationship between a needs topic and an appeal topic that has been determined to be a match. The highlighting can take any form. For example, topics determined to be a "match" may be highlighted in a specific color (e.g., yellow), or topics determined to be a "difference" may be displayed in a different specific color (e.g., gray).

[0037] The display control unit 133 may highlight the needs topics and appeal topics that have been determined to be a match. This highlighting may be achieved, for example, by changing the background color of the topic to a specific color (e.g., yellow) (highlighting).

[0038] The display control unit 133 may highlight the needs topics and appeal topics that have been determined to be different. This highlighting may be achieved, for example, by displaying the topics in gray (graying them out) or by highlighting them in another specific color.

[0039] Highlighting of needs topics and / or appeal topics can be achieved through various means, such as a change in background color from the default white to yellow, changes in border color, thickness, line type, etc. from the default settings, or changes in font size, color, font, etc. from the default settings. Furthermore, highlighting of linked information involves changes in the display of multiple topics and the lines connecting them, similar to the display of the topics themselves. One specific example of highlighting is shown in Figure 8, which will be discussed later.

[0040] The display control unit 133 may highlight the needs topic, appeal topic, and lines indicating a coupling relationship between a needs topic and an appeal topic, if such a coupling relationship exists, in the same color. The display control unit 133 may display an icon indicating "points that could have been explored further" as feedback to the sales representative if the customer has made relevant statements that could potentially become agreements regarding the needs topics and appeal topics that have been determined to be different by the analysis of the analysis unit 132.

[0041] The display control unit 133 controls the display content in response to user operations on the user terminal 200. The display control unit 133 may display or play at least a portion of the sales negotiation script for analysis specified by the user on the user terminal 200 based on user operations on the user terminal 200. For example, it may control the display of a user-specified portion of the sales negotiation script for analysis, or play the original video or audio.

[0042] The display control unit 133 may, in response to user operations on the master value map displayed on the user terminal 200, display or play at least a portion of the partial sales negotiation script associated with the appeal topic on the user terminal 200.

[0043] The improvement suggestion unit 134 has the function of generating and presenting information that contributes to improving the performance of sales representatives based on the analysis results.

[0044] The improvement suggestion unit 134 calculates the overall agreement rate of the needs topics and / or appeal topics for the sales negotiation script under analysis, i.e., the coverage rate of the needs topics and appeal topics, based on the master needs information and comparison results, and displays the agreement rate on the user terminal 200.

[0045] The improvement suggestion unit 134 may generate statistical information on the agreement rate based on the agreement rate of multiple past sales negotiation scripts that have been analyzed, and for the sales negotiation script being analyzed in the current analysis, it may identify needs topics and / or appeal topics with a lower agreement rate than the statistical information as "weak points" and display them on the user terminal 200. The statistical information may be, for example, the average value or the score of the top performers.

[0046] The improvement suggestion unit 134 may identify appeal topics with a corresponding relationship based on the correlation coefficient for the needs topics determined to be matching, and display them on the user terminal 200. Furthermore, if the combined information of the master needs information includes a correlation coefficient that shows the correlation with the closing of a sale of a product, the improvement suggestion unit 134 may identify the most suitable appeal topic to present next based on that correlation coefficient and display it as a suggestion.

[0047] The master generation unit 135 generates and maintains master needs information, which forms the basis for analysis.

[0048] The master generation unit 135 uses the learning model 123 to generate new master needs information from the sales opportunity scripts for master generation and stores it in the value map DB. The sales opportunity scripts for master generation are, for example, numerous sales opportunity scripts from top sales representatives. The master generation unit 135 comprehensively analyzes the sales opportunity scripts for master generation using the learning model 123. Through this analysis, the master generation unit 135 automatically extracts and structures customer needs that commonly appear in successful sales opportunities, effective selling points presented to address those needs, and typical connections (relationships) between the two.

[0049] The master generation unit 135 uses the learning model 123 to update master needs information from sales opportunity scripts for master updates and stores it in the value map DB. Updates include, for example, adding new needs or selling points, and changing the coupling relationships. Updates include adding new needs topics and selling points topics, deleting topics that have become ineffective due to changing times, and recalculating the strength of the coupling relationships (correlation coefficient) between needs and selling points. Effective sales opportunity patterns may also change due to changes in the market environment, the introduction of new products, or the implementation of new sales strategies. Through regular or necessary updates, master needs information is always kept active and relevant to the actual situation without becoming obsolete.

[0050] The learning unit 136 manages the learning of the learning model 123. The learning procedure for the learning model 123 is mainly as follows:

[0051] <Step 1: Preparing the training data (annotation)> A dataset will be constructed primarily from numerous past sales scripts of successful deals where the "deal success / failure" status was "successful." These sales scripts will then be annotated (tagged). Specifically, individual utterances within the scripts will be analyzed, and predefined topics will be associated with each part of the text, such as "this statement corresponds to the needs topic of 'cost reduction'" or "this part corresponds to the appeal topic of 'presentation of implementation examples'." Simultaneously, "connection information" indicating which appeal points were presented for a particular need will also be recorded. This process will create an "annotated corpus" that will serve as training data for machine learning. At this time, utterances related to appeal topics will be recorded as partial sales scripts. Annotation may be performed using, for example, a Large-Scale Language Model (LLM).

[0052] <Step 2: Training the topic extraction model> Next, a topic extraction model is trained using an annotated corpus to automatically extract needs topics and appeal topics from sales scripts. This process applies named entity recognition (NER) and text classification techniques based on large-scale language models (LLMs) that excel at understanding natural language context. Annotated sales scripts are fed to the model as training data, and fine-tuning is performed. The model learns patterns of which words, phrases, or contextual flows correspond to which needs topics and appeal topics. For example, it learns that expressions such as "tight budget" or "price is a sticking point" are associated with the topic "budget-related needs." Furthermore, by learning the order and co-occurrence relationships of what appeal points are often presented after a particular need is presented, the accuracy of extracting combined information is also improved.

[0053] <Step 3: Statistical calculation of the correlation coefficient> The correlation coefficient is not directly extracted from individual sales scripts, but is a statistically calculated metric obtained by cross-analyzing a large number of sales results. Using the topic extraction model built in Step 2, all sales opportunities (including both successes and failures) stored in the script DB are automatically analyzed, and data on which topics appeared in each sales opportunity is stored in the analysis DB. The correlation between specific linked information (e.g., the pattern of presenting "cost reduction" needs followed by "cost-effectiveness examples") and "sales success or failure" is statistically calculated. Statistical methods such as Pearson's product-moment correlation coefficient are used for this calculation, resulting in a correlation coefficient between +1.0 and -1.0. The calculated correlation coefficient is stored as additional information for each linked piece of information in the value map DB. This completes the learning process to quantitatively evaluate which linked pieces of information are strongly linked to closing deals, and it functions as part of the model.

[0054] Figure 4 is a functional block diagram of a user terminal 200 according to an embodiment of this disclosure. The user terminal 200 is an information processing device used by users such as sales representatives and their managers. The user terminal 200 is any terminal device such as a personal computer (PC), notebook PC, tablet terminal, smartphone, or wearable device. The user terminal 200 utilizes various functions provided by the sales support server 100 via a web browser or dedicated application software. The user uses the user terminal 200 to upload recorded data of business negotiations (video, audio, etc.) to the sales support server 100 and to view the analysis results from the sales support server 100.

[0055] The user terminal 200 comprises a communication unit 210, a storage unit 220, a control unit 230, a display unit 240, and an operation unit 250. The communication unit 210, storage unit 220, control unit 230, display unit 240, and operation unit 250 are electrically connected to each other via a communication bus 260.

[0056] The display unit 240 is a display device that displays analysis results (e.g., value maps) and other information received from the sales support server 100. The operation unit 250 is an input device for the user to input various operations. The user uses the operation unit 250 to perform operations such as instructing the upload of sales opportunity data and selecting topics on the displayed value map.

[0057] <System Operation> Next, the operation of the sales support system 1, which has the configuration and functions described above, will be explained using a flowchart.

[0058] Figure 5 is a flowchart showing the analysis process performed by the sales support system 1 according to the embodiment of this disclosure.

[0059] In step S101, the user uploads a sales negotiation script for analysis and various information related to the sales negotiation script (various information to be stored in the script DB) from the user terminal 200 to the sales support server 100. The acquisition unit 131 of the sales support server 100 acquires the sales negotiation script for analysis and various information related to the sales negotiation script from the user terminal 200 and stores it in the script DB of the storage unit 120.

[0060] In step S102, the analysis unit 132 of the sales support server 100 identifies the master needs information to be used for analysis based on the product ID acquired in step S101. The analysis unit 132 analyzes the sales negotiation script for analysis, determines whether each needs topic and each appeal topic of the identified master needs information matches or differs, and stores the determination result for each topic as a comparison result in the analysis DB of the storage unit 120.

[0061] In step S103, the display control unit 133 of the sales support server 100 displays a value map on the user terminal 200, which visualizes the needs topic, appeal topic, and the combined information of these topics in a tree diagram. In the value map, for example, the needs topic and appeal topic are displayed as text boxes with a white background, and the combined information, i.e., if there is a connection between topics, is displayed as a black line (connection line) connecting the two text boxes. An example of the value map screen will be described later.

[0062] In step S104, the display control unit 133 of the sales support server 100 displays each topic of the value map in a manner that allows identification of matches or differences based on the comparison results generated in step S102. For example, the background color of the text box for topics determined to be matches (matching topics) is highlighted in yellow. Note that this step may be executed simultaneously with S103.

[0063] In step S105, the display control unit 133 of the sales support server 100 determines, based on the comparison results, whether or not there are two adjacent matching topics that can be joined. If the determination result is true (YES), that is, if there are two adjacent matching topics that can be joined, the process proceeds to step S106. On the other hand, if the determination result is false (NO), that is, if there are no two adjacent matching topics that can be joined, the flow is terminated.

[0064] In step S106, or in step S105, if it is determined that there are two adjacent matching topics that should be joined, the display control unit 133 of the sales support server 100 highlights the joining line between the adjacent matching topics and terminates the flow. For example, the joining line is highlighted in the same yellow color as the matching topics and is a thick line.

[0065] Figure 6 is a flowchart showing the master generation process by the sales support system 1 according to the embodiment of this disclosure.

[0066] In step S201, the user uploads a sales opportunity script for master generation and various information related to the sales opportunity script (various information to be stored in the script DB) from the user terminal 200 to the sales support server 100. The sales opportunity script for master generation pertains to one product specified by the user and preferably includes multiple, preferably dozens, sales opportunity scripts. The acquisition unit 131 of the sales support server 100 acquires the sales opportunity script for master generation and various information related to the sales opportunity script from the user terminal 200 and stores them in the script DB of the storage unit 120.

[0067] In step S202, the master generation unit 135 of the sales support server 100 inputs the sales negotiation script acquired in step S201 into the learning model 123 to generate master needs information for the product specified by the user, and stores it in the value map DB of the storage unit 120.

[0068] In step S203, the master generation unit 135 of the sales support server 100 causes the learning model 123 to generate partial sales negotiation scripts, links them to relevant appeal topics, and stores them in the value map DB of the storage unit 120 as part of the master needs information.

[0069] In step S204, the display control unit 133 of the sales support server 100 displays the master needs information generated in steps S202 and S203 on the user terminal 200 in the form of a tree diagram, and then terminates the flow.

[0070] Figure 7 is a flowchart showing the master update process by the sales support system 1 according to the embodiment of this disclosure.

[0071] In step S301, the user uploads a sales opportunity script for master updates and various information related to the sales opportunity script (various information to be stored in the script DB) from the user terminal 200 to the sales support server 100. The acquisition unit 131 of the sales support server 100 acquires the sales opportunity script for master updates and various information related to the sales opportunity script from the user terminal 200 and stores it in the script DB of the storage unit 120.

[0072] In step S302, the master generation unit 135 of the sales support server 100 inputs the sales negotiation script acquired in step S301 into the learning model 123 to generate updated master needs information for the product specified by the user, and stores it in the value map DB of the storage unit 120.

[0073] In step S303, the master generation unit 135 of the sales support server 100 causes the learning model 123 to generate partial sales negotiation scripts, links them to relevant appeal topics among the appeal topics included in the update information, and stores them in the value map DB of the storage unit 120 as part of the update information of the master needs information.

[0074] In step S304, the display control unit 133 of the sales support server 100 displays the master needs information, which is an integrated version of the update information generated in steps S302 and S303, on the user terminal 200 in the form of a tree diagram, and then terminates the flow.

[0075] <Screen example> Next, we will explain the value map that the sales support server 100 displays on the user terminal 200.

[0076] Figure 8 shows a specific example of a screen including a value map 400 displayed on a user terminal 200 according to an embodiment of this disclosure.

[0077] Figure 8 shows an example of the configuration of the value map 400 used in this embodiment. The value map 400 visualizes the ideal thought process of a business negotiation, from the customer's needs to the final selling point, in the form of a tree diagram. In Figure 8, multiple objects representing the same function or hierarchy are assigned a single representative code. For example, in Figure 8, "Needs" has "Needs 1" and "Needs 2," but only "Needs 1" is assigned the code 422. Also, the value map 400 shown in Figure 8 is only a part of the upper section of the entire value map, and the parts not shown can be displayed by scrolling.

[0078] The Value Map 400 is divided into five main processes, from left to right. Expressed Needs 411 is a process that includes a needs topic that represents the superficial needs that the customer first mentions. These needs are further classified hierarchically into more specific categories such as "Major Needs 421," "Medium Needs 422," and "Minor Needs 423." Intermediate needs 412 is a process that includes intermediate needs topics 431, 432, and 433, which show the intermediate needs (factors included in the expressed needs) that give rise to the expressed needs. Intermediate needs 412 represents a detailed causal analysis process that goes from the expressed needs 411 presented by the customer to the essential needs 413, which are at the core of the problem. Intermediate needs 412 is not a single step, but includes multiple layers for progressively deepening the needs. In the example shown in Figure 8, there are three layers: intermediate needs topic 431 at the first layer, intermediate needs topic 432 at the second layer, and intermediate needs topic 433 at the third layer, but the depth of the layers is not limited to these. Essential needs 413 is a process that includes essential needs topic 441, which indicates the root cause of the expressed needs. Intermediate appeal points 414 are a hierarchy that includes appeal topics 451 and 452, which indicate intermediate steps or measures to resolve the underlying issues. Similar to intermediate needs 412, it can include multiple levels. The final selling point 415 is a process that includes a selling topic 461 that describes the functions and features of the product or service that ultimately solve the customer's needs. Furthermore, hierarchy defines the parent-child relationships or differences in abstraction between needs or selling points. For example, under the broad need of "cost reduction," there are smaller needs such as "labor cost reduction" and "operating cost reduction."

[0079] Multiple topics at each level, such as "needs" and "selling points," are connected by connecting lines (e.g., 471, 472), creating a tree diagram that illustrates the logical connections from needs to the final selling point and the ideal conversation flow for a business negotiation.

[0080] Topics highlighted with a thick border are examples of items that the sales representative in a given deal mentioned and achieved when the deal script was analyzed. Similarly, connecting lines between two adjacent topics highlighted with thick borders are also highlighted with thick lines. In this way, the comparison results of the deal scripts being analyzed are reflected on the value map using highlighting. For example, the path (421→422→423→431→441→461) in value map 400 in Figure 8 visually shows the path the sales representative took to successfully follow an ideal conversation flow in accordance with the master needs information (value map). On the other hand, appeal topic 461a, highlighted with a thick border, indicates that although the sales representative mentioned it in the deal, there was no path connecting it to other topics via a thick connecting line, meaning it was unrelated to expressed need minor 2, and the customer did not mention expressed need minor 1.

[0081] Furthermore, a closing window 480 is provided at the bottom of the value map 400, presenting one or more topics 481 that should be discussed in the final stage of the negotiation after the needs resolution process. Figure 8 shows that the sales representative mentioned topic 2.

[0082] <Basic Computer Configuration> Figure 9 is a block diagram showing the basic hardware configuration of computer 900. Computer 900 includes a control unit 901, a storage unit 902, a communication unit 903, an input unit 904, and an output unit 905. The control unit 901, storage unit 902, communication unit 903, input unit 904, and output unit 905 are electrically connected to each other via a communication bus 910.

[0083] The control unit 901 includes a CPU (Central Processing Unit, also called a processor) and controls various parts of the computer 900, as well as reading and executing various programs stored in the storage unit 902.

[0084] The memory unit 902 includes a main memory such as DRAM (Dynamic Random Access Memory) and an auxiliary memory such as a hard disk, and is a device that stores various programs for running the operating system and various applications of the computer 900, as well as data used by these programs. The processes shown in the flowcharts described above are realized by the control units 901 of each computer constituting the sales support server 100 and the user terminal 200 executing the programs stored in their respective memory units 902.

[0085] The communication unit 903 is a device for communicating with external devices and sends and receives data according to instructions from the control unit 901. Each computer that makes up the sales support server 100 and user terminals 200 uses this communication unit 903 to communicate with other devices, including the network NW shown in Figure 1.

[0086] The input unit 904 is a device that receives input from an external source and supplies it to the control unit 901, and includes, for example, a keyboard, mouse, touch panel, and camera. The output unit 905 is a device that outputs the processing results of the control unit 901 to the outside, and includes, for example, a display and speaker.

[0087] <Program> Here, we will describe the programs for realizing each functional unit of the sales support server 100 according to this embodiment.

[0088] The sales support server 100 is implemented on the computer 900. The operation of each component of the sales support server 100 is stored in the auxiliary storage device of the storage unit 902 in the form of a program. The control unit 901 reads the program from the auxiliary storage device of the storage unit 902, loads it into the main memory of the storage unit 902, and executes the above processing according to the program. The control unit 901 also reserves a storage area in the main memory of the storage unit 902 corresponding to the storage unit 120 described above, according to the program.

[0089] Specifically, the program is a program to be executed on a computer 900 which is equipped with a processor and a storage unit, and the program is a program which is equipped with a storage unit that stores master needs information which includes a needs topic that indicates the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic that indicates the appeal points of the product that is the subject of the sales negotiation corresponding to the needs; and coupling information that indicates the coupling relationship between the needs topic and the appeal topic, and the program includes the steps of obtaining a sales script to be analyzed on a computer equipped with a storage unit that stores master needs information which includes a needs topic that indicates the needs of the second user extracted from a sales script which is a script extracted from a sales negotiation video and / or sales negotiation audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic that indicates the appeal points of the product that is the subject of the sales negotiation corresponding to the needs; and coupling information that indicates the coupling relationship between the needs topic and the appeal topic, and the steps of analyzing the sales script to be analyzed on a large-scale language model and generating comparison results that determine whether there is a match or a difference for each of the needs topic and the appeal topic of the master needs information, and displaying the comparison results reflected in the master needs information on a user terminal.

[0090] The auxiliary storage device of the memory unit 902 is an example of a tangible medium that is not temporary. Other examples of tangible mediums that are not temporary include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, and semiconductor memory connected via the input unit 904. Furthermore, if this program is distributed to the computer 900 via the network NW, the computer 900 that receives the program may load it into the main memory of the memory unit 902 and execute the above processing.

[0091] Furthermore, the program may be intended to implement some of the functions described above. In addition, the program may be a so-called differential file (differential program) that implements the functions described above in combination with other programs already stored in the auxiliary storage device of the memory unit 902.

[0092] According to the sales support system 1 of this embodiment described above, by comparing the sales representative's actions with a value map that models the structural "winning pattern" of how top sales representatives strategically build the entire sales negotiation and lead to the resolution of customer needs (problems), the weaknesses and strengths of the sales representative can be visualized in a structural and objective manner. Specifically, based on the sales scripts of your company's top salespeople with high closing rates, you can structurally map your company's customers' needs (challenges), your company's solutions (selling points), and how top salespeople elicit customer needs, creating a truly original "sales negotiation map (value map)." Then, by placing the sales scripts of (regular) salespeople on this "sales negotiation map," you can clearly identify what those salespeople are "not doing well (weaknesses)" and suggest what they "should do." Furthermore, by easily accessing examples and case studies (partial sales scripts) that address these weaknesses, you can efficiently improve your skills. This can contribute to improving the performance of the entire sales organization. In addition, if a salesperson does not fully understand customer needs or if the proposed content is out of sync with customer needs, you can identify the cause and find specific areas for improvement. In other words, it is possible to structurally and objectively visualize the actions of sales representatives during business negotiations and effectively support the improvement of their skills.

[0093] This disclosure is not limited to the embodiments described above, and various modifications can be adopted.

[0094] For example, in this embodiment, the client-server system in which the sales support server 100 and the user terminal 200 are separate has been described, but the present invention is not limited to this. For example, it is also possible to implement all or part of the functions of the sales support server 100 as application software that runs on the user terminal 200. In this case, the user terminal 200 corresponds to the sales support device.

[0095] Furthermore, the sample information of the sales support system 1 according to the above embodiment includes not only scripts and videos of top sales representatives actually speaking, but also other information for effectively conducting business negotiations, such as separately defined materials, and the improvement suggestion unit 134 may present suitable information (e.g., materials and case studies) from these assets to the sales representative.

[0096] Furthermore, the analysis unit 132 of the sales support system 1 according to the above embodiment may extract negotiation information on topics arbitrarily set by the user, including a summary of the conversation content, and display it on the user terminal 200 by the display control unit 133. For example, the analysis unit 132 may extract information from any angle, such as an overall summary, a summary of next actions, or bottlenecks in implementation mentioned by the customer.

[0097] Furthermore, the sales support system 1 according to the above embodiment may also be linked with an online meeting program installed on the user terminal 200, and the acquisition unit 131 may automatically acquire the sales negotiation script from the linked online meeting program and have the analysis unit 132 automatically perform the analysis.

[0098] Furthermore, the sales support system 1 according to the above embodiment may include an agent control unit (not shown) that provides an agent function in which an artificial intelligence (AI) sales agent conducts business negotiations in online meetings on behalf of the customer, based on defined master needs information. For example, the LLM analyzes the negotiation audio in real time, synthesizes the speech according to the master needs information, and conducts interviews and appeals to the customer.

[0099] Furthermore, after performing analysis of the sales negotiation script, the sales support system 1 according to the above embodiment may, instead of or in addition to displaying a tree diagram-style map, create and display or provide to the user text information indicating the content of the feedback based on the comparison results. Master needs information will be used for the analysis.

[0100] Furthermore, in the sales support system 1 according to the above embodiment, master needs information is generated for each product, but it may also be generated for other classifications related to the product. For example, it may be generated for each value and function of the product, or for each business or business organization that handles the product.

[0101] <Other Embodiments> The above-described operation flows can be performed not only independently, but also in combination of two or more operation flows. For example, some steps of one operation flow may be added to another operation flow, or some steps of one operation flow may be replaced with some steps of another operation flow. It is not necessary to execute all steps in each flow; only some steps may be executed. Furthermore, the order of steps in each flow may be changed as appropriate.

[0102] A program may be provided that causes a computer to execute each of the processes according to the above embodiment. The program may be recorded on a computer-readable medium. Using a computer-readable medium, it is possible to install the program on a computer. Here, the computer-readable medium on which the program is recorded may be a non-transient storage medium. The non-transient storage medium is not particularly limited, but may be a storage medium such as a CD-ROM or DVD-ROM. Furthermore, the circuits that execute each of the processes performed by the device according to the above embodiment may be integrated, and at least a part of the device may be configured as a semiconductor integrated circuit (chipset, SoC).

[0103] The functions realized by the apparatus according to the above embodiments may be implemented in a circuit or processing circuitry, including a general-purpose processor, an application-specific processor, an integrated circuit, an ASIC (Application Specific Integrated Circuit), a CPU (a Central Processing Unit), conventional circuits, and / or a combination thereof, programmed to realize the described functions. A processor, including transistors and other circuits, is considered a circuit or processing circuitry. A processor may be a programmed processor that executes a program stored in memory. In this disclosure, circuitry, unit, and means are hardware programmed to realize or perform the described functions. Such hardware may be any hardware disclosed herein, or any hardware known to be programmed to realize or perform the described functions. If such hardware is a processor that is considered a type of circuitry, then such circuitry, means, or unit is a combination of hardware and software used to constitute such hardware and / or processor.

[0104] The terms "based on" and "depending on / in response to" used in this disclosure do not mean "based solely on" or "depending solely on" unless otherwise specified. "Based on" means both "based solely on" and "at least partially on." Similarly, "depending on" means both "at least partially on" and "at least partially on." The terms "include," "comprise," and their variations do not mean to include only the listed items, but may include only the listed items or may include additional items in addition to the listed items. Furthermore, the term "or" used in this disclosure is not intended to mean exclusive OR. Additionally, any reference to elements using designations such as "first," "second," etc., used in this disclosure does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient way to distinguish between two or more elements. Therefore, references to the first and second elements do not imply that only two elements may be adopted therein, or that the first element must precede the second element in any way. In this disclosure, where articles are added by translation, such as a, an, and the in English, these articles shall be plural unless it is clearly indicated by the context that they are not.

[0105] Although the embodiments have been described in detail above with reference to the drawings, the specific configuration is not limited to those described above, and various design changes can be made without departing from the gist of the invention.

[0106] (Note) The features of the above-described embodiment are noted below. (Note 1) A storage unit that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales script, which is a sales script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic indicating the appeal points of the product that is the subject of the sales negotiation corresponding to said needs; and coupling information indicating the coupling relationship between said needs topic and said appeal topic. The acquisition unit obtains the sales negotiation script to be analyzed, An analysis unit analyzes the sales negotiation script to be analyzed using a large-scale language model and generates comparison results that determine whether there is a match or a difference for each of the needs topics and appeal topics in the master needs information. A display control unit that reflects the comparison results in the master needs information and displays them on the user terminal. Equipped with, Sales support system. (Note 2) The display control unit, The needs topic, appeal topic, and combined information of the master needs information are displayed on the user terminal, and the agreement or disagreement in the comparison results for the needs topic and appeal topic are visually displayed, When a matching needs topic and a matching appeal topic are found to be linked, the linked information is highlighted. The sales support system described in Appendix 1. This allows for an intuitive understanding of whether or not there is a connection between needs and selling points. It also makes it easier to compare with the correct answer. (Note 3) The display control unit displays the master needs information on the user terminal in the form of a tree diagram. The sales support system described in Appendix 1 or 2. This allows users to intuitively grasp the overall picture and structure of needs and selling points. Furthermore, users can intuitively understand and grasp the strengths and weaknesses. (Note 4) The display control unit highlights the needs topic, the appeal topic, and the line indicating a coupling relationship between the needs topic and the appeal topic, if such a coupling relationship exists, in the same color. The sales support system described in Appendix 3. This allows users to intuitively understand and grasp the strengths and weaknesses of the first user. (Note 5) The display control unit highlights the needs topic and appeal topic that have been determined to be a match. A sales support system as described in any of the appendices 1 to 4. This allows users to intuitively understand and grasp the strengths of the first user. (Note 6) The display control unit highlights the needs topic and appeal topic that have been determined to be different. A sales support system as described in any of the appendices 1 to 5. This allows users to intuitively understand and grasp the weaknesses of first-time users. (Note 7) The memory unit stores the sales negotiation script to be analyzed, The display control unit displays or plays the sales negotiation script to be analyzed based on user operations on the user terminal. A sales support system as described in any of the appendices 1 through 6. This allows users to review their actions during a business negotiation with a single click. (Note 8) The memory unit stores example information associated with the appeal topic, The display control unit displays or plays the example information based on the user's operation on the appeal topic of the displayed master needs information. A sales support system as described in any of the appendices 1 through 7. This allows users to access examples of how to address weaknesses with a single click. (Note 9) The system further includes an improvement suggestion unit that calculates the overall agreement rate of the needs topic and / or appeal topic for the sales negotiation script to be analyzed, based on the master needs information and the comparison results, and displays the agreement rate on the user terminal. A sales support system as described in any of the appendices 1 through 8. This allows users to quantitatively understand their strengths and weaknesses. (Note 10) The improvement suggestion unit generates statistical information on the matching rate based on the matching rate of multiple past sales negotiation scripts to be analyzed, and for the sales negotiation script to be analyzed this time, identifies the needs topics and / or appeal topics with a lower matching rate than the statistical information and displays them on the user terminal. The sales support system described in Appendix 9. This makes the weaknesses of the first user visible. (Note 11) The combined information includes a correlation coefficient that shows the correlation with the closing of a deal for the product. The improvement suggestion unit identifies the appeal topics that have a corresponding relationship with the needs topics determined to be identical, based on the correlation coefficient, and displays them on the user terminal. The sales support system described in Appendix 9. This allows for the presentation of effective selling points once a need has been identified. (Note 12) The analysis unit analyzes the sales negotiation script to be analyzed in real time, and if it detects a need that matches the needs topic, it proposes appeal points in real time that correspond to the detected need based on the master needs information. A sales support system as described in any of the appendices 1 through 11. This allows for real-time support of business negotiations. (Note 13) The memory unit stores a learning model that has learned the correlation between the needs of a second user included in a learning sales script for which a sales deal was concluded, and the selling points presented in response to those needs. The acquisition unit acquires the opportunity script for master generation, The system further comprises a master generation unit that generates the master needs information from the aforementioned business opportunity script for master generation. A sales support system as described in any of the appendices 1 through 12. This allows you to map customer needs (challenges) and your company's solutions (selling points), creating a truly original "sales negotiation map." Furthermore, it helps you identify where you've gone wrong on that map and how to get back on track. (Note 14) The acquisition unit acquires the opportunity script for master update, The master generation unit updates the master needs information based on the sales opportunity script for master updates. The sales support system described in Appendix 13. (Note 15) A storage unit that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales script, which is a sales script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic indicating the appeal points of the product that is the subject of the sales negotiation corresponding to said needs; and coupling information indicating the coupling relationship between said needs topic and said appeal topic. The acquisition unit obtains the sales negotiation script to be analyzed, An analysis unit analyzes the sales negotiation script to be analyzed using a large-scale language model and generates comparison results that determine whether there is a match or a difference for each of the needs topics and appeal topics in the master needs information. A display control unit that reflects the comparison results in the master needs information and displays them on the user terminal. Equipped with, Sales support device. (Note 16) A computer having a storage unit that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales script, which is a sales script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic indicating the appeal points of the product that is the subject of the sales negotiation corresponding to said needs; and coupling information indicating the coupling relationship between said needs topic and said appeal topic, Steps to obtain the sales opportunity script to be analyzed, The steps include: analyzing the sales negotiation script to be analyzed using a large-scale language model to generate comparison results that determine whether there are matches or differences for each of the needs topics and appeal topics in the master needs information; The steps include: displaying the comparison results reflected in the master needs information on the user terminal; A program that executes the command. (Note 17) A computer having a storage unit that stores master needs information, which includes a needs topic indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; an appeal topic indicating the appeal points of the product that is the subject of the sales negotiation corresponding to said needs; and coupling information indicating the coupling relationship between said needs topic and said appeal topic, Steps to obtain the sales opportunity script to be analyzed, The steps include: analyzing the sales negotiation script to be analyzed using a large-scale language model to generate comparison results that determine whether there are matches or differences for each of the needs topics and appeal topics in the master needs information; The steps include: displaying the comparison results reflected in the master needs information on the user terminal; A sales support method for implementing this. [Explanation of Symbols]

[0107] 1: Sales support system 100: Sales support server 110: Communications Department 120: Storage section 123: Learning Model 130: Processing Unit 131: Acquisition Department 132:Analysis Department 133: Display Control Unit 134: Improvement proposal department 135: Master Generation Unit 136: Learning Department 200: User terminal 400: Value Map NW: Network

Claims

1. A storage unit that stores master needs information, which includes: a plurality of needs topics indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; appeal topics indicating the appeal points of the product that is the subject of the sales negotiation corresponding to those needs; and coupling information indicating the coupling relationships between each of the plurality of needs topics, and between at least some of the plurality of needs topics and the appeal topics; The acquisition unit obtains the sales negotiation script to be analyzed, An analysis unit analyzes the sales negotiation script to be analyzed using a large-scale language model to identify the context and semantic content of the sales negotiation script, and generates comparison results that determine whether there is a match or a difference for each of the needs topic and appeal topic of the master needs information. A display control unit that reflects the comparison results in the master needs information and displays them on the user terminal. Equipped with, The analysis unit analyzes the customer's response in the script being analyzed for each of the multiple needs topics, specifically for the needs topic that includes achievement conditions related to the customer's response, and determines whether there is a match or a difference based on the customer's response. Sales support system.

2. The display control unit, The needs topic, appeal topic, and combined information of the master needs information are displayed on the user terminal, and the agreement or disagreement in the comparison results for each of the multiple needs topics and appeal topics is visually displayed. When there is a coupling relationship between the need topics that are determined to be identical among the aforementioned multiple need topics, the coupling information is highlighted. The sales support system according to claim 1.

3. The display control unit displays the master needs information on the user terminal in the form of a tree diagram. The sales support system according to claim 1 or 2.

4. The display control unit highlights lines indicating a coupling relationship in the same color when there is a coupling relationship between the need topics that have been determined to be a match among the plurality of need topics. The sales support system according to claim 3.

5. The display control unit highlights the needs topic and appeal topic that are determined to be a match among the plurality of needs topics. The sales support system according to claim 1 or 2.

6. The display control unit highlights the needs topics and appeal topics that have been determined to be different from the plurality of needs topics. The sales support system according to claim 1 or 2.

7. The memory unit stores the sales negotiation script to be analyzed, The display control unit displays or plays the sales negotiation script to be analyzed based on user operations on the user terminal. The sales support system according to claim 1 or 2.

8. The memory unit stores example information associated with the appeal topic, The display control unit displays or plays the example information based on the user's operation on the appeal topic of the displayed master needs information. The sales support system according to claim 1 or 2.

9. The system further includes an improvement suggestion unit that calculates the overall agreement rate of the needs topic and / or appeal topic for the sales negotiation script to be analyzed, based on the master needs information and the comparison results, and displays the agreement rate on the user terminal. The sales support system according to claim 1 or 2.

10. The improvement suggestion unit generates statistical information on the agreement rate based on the agreement rate of multiple past sales negotiation scripts to be analyzed, and for the sales negotiation script to be analyzed this time, identifies the needs topics and / or appeal topics with a lower agreement rate than the statistical information and displays them on the user terminal. The sales support system according to claim 9.

11. The combined information includes a correlation coefficient that shows the correlation with the closing of a deal for the product. The improvement suggestion unit identifies the appeal topics that have a corresponding relationship with the needs topics determined to be identical, based on the correlation coefficient, and displays them on the user terminal. The sales support system according to claim 9.

12. The analysis unit analyzes the sales negotiation script to be analyzed in real time, and if it detects a need that matches the needs topic, it proposes appeal points in real time that correspond to the detected need based on the master needs information. The sales support system according to claim 1 or 2.

13. The memory unit stores a learning model that has learned the correlation between the needs of a second user included in a learning sales script for which a sales deal was concluded, and the appeal points presented in response to those needs. The acquisition unit acquires the opportunity script for master generation, The system further comprises a master generation unit that generates the master needs information from the aforementioned business opportunity script for master generation. The sales support system according to claim 1 or 2.

14. The acquisition unit acquires the opportunity script for master update, The master generation unit updates the master needs information based on the sales opportunity script for master updates. The sales support system according to claim 13.

15. A storage unit that stores master needs information, which includes: a plurality of needs topics indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; appeal topics indicating the appeal points of the product that is the subject of the sales negotiation corresponding to those needs; and coupling information indicating the coupling relationships between each of the plurality of needs topics, and between at least some of the plurality of needs topics and the appeal topics; The acquisition unit obtains the sales negotiation script to be analyzed, An analysis unit analyzes the sales negotiation script to be analyzed using a large-scale language model to identify the context and semantic content of the sales negotiation script, and generates comparison results that determine whether there is a match or a difference for each of the needs topic and appeal topic of the master needs information. A display control unit that reflects the comparison results in the master needs information and displays them on the user terminal. Equipped with, The analysis unit analyzes the customer's response in the script being analyzed for each of the multiple needs topics, specifically for the needs topic that includes achievement conditions related to the customer's response, and determines whether there is a match or a difference based on the customer's response. Sales support device.

16. A computer having a storage unit that stores master needs information, which includes: a plurality of needs topics indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; appeal topics indicating the appeal points of the product that is the subject of the sales negotiation corresponding to those needs; and coupling information indicating the coupling relationships between each of the plurality of needs topics, and between at least some of the plurality of needs topics and the appeal topics; Steps to obtain the sales opportunity script to be analyzed, The steps include: analyzing the sales negotiation script to be analyzed using a large-scale language model to identify the context and semantic content of the sales negotiation script, and generating comparison results that determine the match or difference for each needs topic and appeal topic of the master needs information; The steps include: displaying the comparison results reflected in the master needs information on the user terminal; Make it run, The step of generating the comparison results involves analyzing the customer's response in the script to be analyzed for each of the multiple needs topics that includes achievement conditions related to customer responses, and determining whether there is a match or a difference based on the customer's response. program.

17. A computer having a storage unit that stores master needs information, which includes: a plurality of needs topics indicating the needs of the second user extracted from a sales script, which is a script extracted from a sales video and / or sales audio recording of a sales negotiation conducted between a first user and a second user who is a customer of the first user; appeal topics indicating the appeal points of the product that is the subject of the sales negotiation corresponding to those needs; and coupling information indicating the coupling relationships between each of the plurality of needs topics, and between at least some of the plurality of needs topics and the appeal topics, Steps to obtain the sales opportunity script to be analyzed, The steps include: analyzing the sales negotiation script to be analyzed using a large-scale language model to identify the context and semantic content of the sales negotiation script, and generating comparison results that determine the match or difference for each needs topic and appeal topic of the master needs information; The steps include: displaying the comparison results reflected in the master needs information on the user terminal; Execute, The step of generating the comparison results involves analyzing the customer's response in the script to be analyzed for each of the multiple needs topics that includes achievement conditions related to customer responses, and determining whether there is a match or a difference based on the customer's response. Sales support methods.

Images