Information processing systems, information processing methods, and programs

Abstract

To enable analysis that takes into account past business negotiations. Furthermore, to identify actions agreed upon in past negotiations that have not yet been implemented. [Solution] The information processing system comprises: an audio acquisition unit that acquires audio data of a business negotiation; a business negotiation content acquisition unit that acquires the content of the current business negotiation from the audio data; a business negotiation content storage unit that stores the acquired content of the current business negotiation; a past business negotiation content acquisition unit that acquires past business negotiation content from the business negotiation content storage unit; an implementation status management unit that determines the implementation status of next actions included in past business negotiation content based on the content of the current business negotiation; and a report generation unit that generates a business negotiation report based on both past and current business negotiation content. The report generation unit includes next actions that have been determined not to have been implemented in the business negotiation report.

Description

Technical Field

[0004] ,

[0006] , , , ,

[0005] , , , ,

[0001] The present invention relates to an information processing system, an information processing method, and a program.

Background Art

[0002] There has been proposed a technique for performing analysis based on data related to a meeting generated during a meeting and generating a report including a label indicating a point of the meeting and data of content corresponding to the label (see Patent Document 1).

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0007] Further issues and solutions disclosed in this application will be made clear in the section on embodiments of the invention and in the drawings. [Effects of the Invention]

[0008] According to the present invention, it is possible to perform analysis that takes into account the content of past business negotiations. Furthermore, according to the present invention, it is possible to identify actions that were agreed upon in past business negotiations but have not yet been implemented. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the overall configuration of an information processing system. [Figure 2] This figure shows an example of the hardware configuration of management server 2. [Figure 3] This figure shows an example of the software configuration for management server 2. [Figure 4] This is a diagram illustrating the processing flow in an information processing system. [Modes for carrying out the invention]

[0010] <System Overview> The following describes an information processing system according to one embodiment of the present invention. The information processing system of this embodiment acquires audio data of a business negotiation and extracts the content of the current negotiation from the audio data. The information processing system stores the extracted content of the current negotiation and acquires the content of past negotiations, and generates a negotiation report based on both the content of past negotiations and the content of the current negotiation. This makes it possible to generate a negotiation report that takes into account the history of past negotiations, which could not be achieved by generating a report based only on a single negotiation record. In addition, the information processing system can also generate an evaluation and feedback of the negotiation based on both the content of past negotiations and the content of the current negotiation. This makes it possible to provide appropriate advice that takes into account actions taken in the past, and can effectively support the enablement of solution sales and account sales. Furthermore, the information processing system can automatically link negotiation records on a customer or deal basis by linking with CRM (Customer Relationship Management) / SFA (Sales Force Automation).

[0011] Figure 1 shows an example of the overall configuration of an information processing system. The information processing system in this embodiment includes a management server 2. The management server 2 is connected to the user terminal 1 via a communication network. The communication network is, for example, the internet and is constructed using public telephone networks, mobile phone networks, wireless communication channels, Ethernet (registered trademark), etc.

[0012] User terminal 1 is a computer operated by the user. User terminal 1 can be, for example, a smartphone, a tablet computer, or a personal computer.

[0013] The management server 2 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0014] <Management Server 2> Figure 2 shows an example of the hardware configuration of the management server 2. Note that the illustrated configuration is just one example, and other configurations are also possible. The management server 2 includes a CPU 201, memory 202, storage device 203, communication interface 204, input device 205, and output device 206. The storage device 203 stores various data and programs, such as a hard disk drive, solid-state drive, or flash memory. The communication interface 204 is an interface for connecting to a communication network, such as an adapter for connecting to Ethernet®, a modem for connecting to a public telephone network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector or RS232C connector for serial communication. The input device 205 is for inputting data, such as a keyboard, mouse, touch panel, button, or microphone. The output device 206 is for outputting data, such as a display, printer, or speaker. Furthermore, each functional unit of the management server 2, as described later, is realized by the CPU 201 reading programs stored in the storage device 203 into memory 202 and executing them, and each storage unit of the management server 2 is realized as part of the storage area provided by memory 202 and storage device 203. <Step 1: Explanation of Software Configuration>

[0015] Figure 3 shows an example of the software configuration of the management server 2. The management server 2 includes a voice acquisition unit 211, a sales negotiation content acquisition unit 212, a past sales negotiation content acquisition unit 213, a report generation unit 214, an evaluation unit 215, a feedback generation unit 216, a CRM / SFA linkage unit 217, a linking unit 218, an implementation status management unit 219, a knowledge acquisition unit 220, a sales negotiation content storage unit 231, a customer information storage unit 232, a sales activity definition storage unit 233, a knowledge storage unit 234, and a feedback history storage unit 235. <Step 2: Explanation of Functional Parts> <Management Server 2> The following describes the functional components of the management server 2.

[0016] The negotiation content storage unit 231 is a storage device that stores negotiation content. The negotiation content storage unit 231 stores negotiation content for each negotiation. The negotiation content storage unit 231 stores, as negotiation content, the purpose, summary, decisions, next actions, customer issues, customer requirements, etc. The negotiation content storage unit 231 stores the negotiation content after assigning a negotiation identifier thereto. The negotiation content storage unit 231 stores the negotiation content after assigning a customer identifier and a project identifier thereto. Thereby, the negotiation content storage unit 231 can manage negotiation content in units of customers and projects. Further, the negotiation content storage unit 231 can store the next action included in the negotiation content in association with its implementation status. The implementation status will be described later.

[0017] The customer information storage unit 232 is a storage device that stores information related to customers. The customer information storage unit 232 stores a customer identifier, customer name, customer industry, customer scale, customer contact information, etc. The customer information storage unit 232 stores a project identifier, project name, project progress status, project amount, etc. The customer information storage unit 232 can store information obtained from a CRM / SFA system.

[0018] The sales activity definition storage unit 233 is a storage device that stores definitions of sales activities. The sales activity definition storage unit 233 stores desirable actions, items to be confirmed, goals to be achieved, etc. at each stage of the sales process. The sales activity definition storage unit 233 stores viewpoints for evaluation. The viewpoints for evaluation are, for example, the degree of understanding of customer issues, the appropriateness of proposed content, the clarity of next actions, the progress of relationship building with customers, etc. The sales activity definition storage unit 233 stores, as the sales activity definition, information related to the company's sales policy and sales methods.

[0019] The voice acquisition unit 211 acquires the voice data of the negotiation. The voice acquisition unit 211 can receive the voice data from the user terminal 1. The voice acquisition unit 211 may acquire the voice data in real time during the negotiation, or may acquire the voice data recorded after the negotiation ends. The voice acquisition unit 211 assigns a negotiation identifier to the acquired voice data. The voice acquisition unit 211 can acquire metadata such as the date and time of the negotiation, participants, customer identifier, project identifier, etc. together with the voice data.

[0020] The negotiation content acquisition unit 212 acquires the content of the current negotiation from the voice data. The negotiation content acquisition unit 212 converts the voice data into text data using voice recognition technology. The negotiation content acquisition unit 212 extracts the negotiation content from the converted text data. The negotiation content acquisition unit 212 analyzes the text data using natural language processing technology and extracts at least one of the purpose, summary, decisions, next actions, customer issues, and customer requirements as the content of the current negotiation. In addition, the negotiation content acquisition unit 212 can extract the next action as the content of the current negotiation. The next action refers to the action to be executed in the future, explicitly stated by the parties (salesperson or customer) during the negotiation. The negotiation content acquisition unit 212 extracts the next action as a fact from the voice data (or text data). Examples of the next action include actions to be executed in the negotiation such as "submit a quotation by the next time", "send a product sample", "submit a request within the company", "send a draft of the contract".

[0021] The sales opportunity content acquisition unit 212 can extract sales opportunity content using a Large Language Model (LLM). The sales opportunity content acquisition unit 212 inputs text data and prompts specifying the items to be extracted to the Large Language Model, and retrieves sales opportunity content from the Large Language Model. For example, the sales opportunity content acquisition unit 212 inputs text data to the Large Language Model along with the prompt, "Extract the objective, summary, decisions, next actions, customer challenges, and customer requirements from the following sales opportunity text."

[0022] The negotiation content acquisition unit 212 stores the extracted negotiation content in the negotiation content storage unit 231. The negotiation content acquisition unit 212 stores the negotiation content with an negotiation identifier, customer identifier, case identifier, negotiation date and time, etc. Rather than simply overwriting as in conventional technology, the negotiation content acquisition unit 212 stores the current negotiation content in addition while retaining past negotiation content. As a result, the negotiation content storage unit 231 accumulates the content of multiple negotiations related to the same customer or case.

[0023] The linking unit 218 automatically links multiple sales negotiation records. The linking unit 218 links sales negotiation content on a customer and case basis using customer identifiers and case identifiers obtained from the CRM / SFA system via the CRM / SFA linking unit 217. The linking unit 218 can perform linking using customer identifiers and case identifiers included in the metadata obtained by the voice acquisition unit 211. The linking unit 218 can also search the customer information storage unit 232 using customer names and case names included in the sales negotiation content to identify corresponding customer identifiers and case identifiers. The linking unit 218 assigns the identified customer identifiers and case identifiers to the sales negotiation content and stores it in the sales negotiation content storage unit 231.

[0024] The CRM / SFA integration unit 217 integrates with the CRM / SFA system. The CRM / SFA integration unit 217 retrieves customer information and deal information from the CRM / SFA system and stores it in the customer information storage unit 232. The CRM / SFA integration unit 217 sends the deal report generated by the report generation unit 214 to the CRM / SFA system and can automatically input it into individual fields in the CRM / SFA system. The CRM / SFA integration unit 217 can communicate with the CRM / SFA system using an API (Application Programming Interface).

[0025] The Past Sales Negotiation Content Acquisition Unit 213 acquires past sales negotiation content from the Sales Negotiation Content Storage Unit 231. The Past Sales Negotiation Content Acquisition Unit 213 uses the customer identifier and case identifier assigned to the current sales negotiation to search the Sales Negotiation Content Storage Unit 231 for past sales negotiation content related to the same customer or case. The Past Sales Negotiation Content Acquisition Unit 213 acquires multiple past sales negotiation contents that have been found. The Past Sales Negotiation Content Acquisition Unit 213 can acquire past sales negotiation contents in chronological order of sales negotiation date and time. The Past Sales Negotiation Content Acquisition Unit 213 can limit the number of past sales negotiation contents to acquire. For example, the Past Sales Negotiation Content Acquisition Unit 213 can acquire the contents of the five most recent sales negotiations. Alternatively, the Past Sales Negotiation Content Acquisition Unit 213 may be configured to acquire only the contents of the single most recent sales negotiation.

[0026] The report generation unit 214 generates a sales opportunity report based on both past sales opportunity details and current sales opportunity details. The report generation unit 214 generates a sales opportunity report by integrating past sales opportunity details acquired by the past sales opportunity details acquisition unit 213 and current sales opportunity details acquired by the sales opportunity details acquisition unit 212. The report generation unit 214 can generate a sales opportunity report that organizes the history of multiple sales opportunities in chronological order. The report generation unit 214 can generate a sales opportunity report that shows how matters decided in past sales opportunities have progressed in the current sales opportunity. The report generation unit 214 can check whether the next actions set in past sales opportunities have been implemented and include the results in the sales opportunity report. In particular, the report generation unit 214 can extract next actions that have been determined not to have been implemented by the implementation status management unit 219 (described later) and include them in the sales opportunity report as a list of unaddressed next actions.

[0027] The report generation unit 214 can generate a sales opportunity report using a large-scale language model. The report generation unit 214 inputs prompts to the large-scale language model, including past sales opportunity details and current sales opportunity details, and retrieves a sales opportunity report from the large-scale language model. For example, the report generation unit 214 inputs past sales opportunity details and current sales opportunity details to the large-scale language model with the prompt, "Please create a sales opportunity report that summarizes the history of the sales opportunity based on the following past sales opportunity details and current sales opportunity details." The report generation unit 214 can send the generated sales opportunity report to the CRM / SFA system via the CRM / SFA integration unit 217.

[0028] The report generation unit 214 can generate a sales opportunity report that includes the overall flow of the sales opportunity, the main agenda items for each opportunity, the progress of decisions, changes in customer issues, and changes in the proposed content. The report generation unit 214 can also extract the differences between past sales opportunity content and the current sales opportunity content and generate a sales opportunity report that clearly shows what has changed. This makes it possible to grasp the overall picture of the sales opportunity that could not be grasped with a report based only on a single sales opportunity record. If the report generation unit 214 has acquired the content of multiple past sales opportunities, it can also weight the content of newer sales opportunities so that it is reflected in the report accordingly. For example, when the report generation unit 214 adds the content of multiple past sales opportunities along with the content of the current sales opportunity to the prompt, it can set a weight for each past sales opportunity in the prompt and add instructions to the prompt to reflect it in the report according to this weight.

[0029] The evaluation unit 215 evaluates the deal based on both the content of past deals and the content of the current deal. The evaluation unit 215 evaluates the deal based on the evaluation criteria stored in the sales activity definition memory unit 233. The evaluation unit 215 can evaluate the progress from past deals to the current deal. The evaluation unit 215 can evaluate whether the next actions set in past deals were properly implemented. The evaluation unit 215 can evaluate whether there is a deeper understanding of the customer's challenges. The evaluation unit 215 can evaluate whether the sales process is progressing properly.

[0030] The evaluation unit 215 evaluates the business opportunity using a large-scale language model. The evaluation unit 215 specifies the evaluation criteria in the prompts given to the large-scale language model. For example, the evaluation unit 215 inputs the past and current business opportunity content into the large-scale language model with the prompt, "Based on the following past and current business opportunity content, please evaluate the business opportunity from the perspectives of the degree to which the customer's challenges are understood, the appropriateness of the proposed content, the clarity of the next actions, and the progress of building a relationship with the customer." The evaluation unit 215 can quantify the evaluation results obtained from the large-scale language model as a score. The evaluation unit 215 can include the evaluation results in the business opportunity report. The evaluation unit 215 can evaluate the content and progress of the business opportunity, and the evaluation can include both qualitative and quantitative content.

[0031] The evaluation unit 215 can evaluate business negotiations based on the company's sales activity definitions stored in the sales activity definition storage unit 233. The evaluation unit 215 compares the desired actions at each stage of the sales process defined in the sales activity definition with the actual content of the business negotiation and evaluates whether the negotiation is progressing in accordance with the sales activity definition. If there is a deviation from the sales activity definition, the evaluation unit 215 can include that fact in the evaluation results. This enables objective evaluation of business negotiations based on the company's sales policy.

[0032] The feedback generation unit 216 generates feedback based on both past and current business negotiation content. The feedback generation unit 216 can also generate feedback based on the evaluation results from the evaluation unit 215. The feedback generation unit 216 generates feedback that takes into account actions already taken in past business negotiations. This avoids giving repeated advice on actions already taken in the past and allows for the provision of appropriate advice based on the history up to that point. Furthermore, the feedback generated by the feedback generation unit 216 may include recommended actions. Recommended actions are actions that the information processing system deems desirable and proposes based on past business negotiation content, current business negotiation content, and the knowledge described later, and which were not explicitly stated in the business negotiation. Examples of recommended actions include "requesting the presence of the decision-maker at the next business negotiation," "preparing comparative materials with competing products," "confirming the budget finalization date," and "presenting implementation examples from the same industry," which are the next steps taken based on the business negotiation. Thus, next actions are actions that are explicitly stated in the business negotiation, while recommended actions are actions that are not explicitly stated in the business negotiation, and the two are distinguished in this respect.

[0033] The feedback generation unit 216 generates feedback using a large-scale language model. The feedback generation unit 216 inputs prompts to the large-scale language model, including past negotiation details, current negotiation details, evaluation results, and sales activity definitions, and obtains feedback from the large-scale language model. For example, the feedback generation unit 216 inputs the prompt, "Please generate specific feedback for the sales representative based on the following past negotiation details, current negotiation details, evaluation results, and sales activity definitions. Please exclude actions already taken in the past and suggest actions to be taken in the future," to the large-scale language model. When generating feedback that takes into account actions already taken in past negotiations, for example, a feedback history storage unit can be provided to store feedback content previously proposed in association with past negotiations. The feedback generation unit 216 can then obtain the feedback content corresponding to past negotiations acquired by the past negotiation content acquisition unit 213 from the feedback history storage unit, and further include the acquired past feedback content and an instruction not to propose the same content as past feedback content in the above prompt.

[0034] The feedback generation unit 216 can generate advice as feedback, including items to confirm in the next business meeting, content to propose, actions to take with the customer, and specific actions to advance the sales process. The feedback generation unit 216 can send the generated feedback to the user terminal 1 and present it to the sales representative. The feedback generation unit 216 can also include the generated feedback in the business meeting report. The feedback generation unit 216 can also link the generated feedback to the sales AI agent. This allows the AI ​​agent to provide appropriate advice after understanding the history of each customer's business meeting, resolving the issue of the AI ​​agent not being able to grasp the context.

[0035] Figure 4 is a diagram illustrating the processing flow in an information processing system.

[0036] The voice acquisition unit 211 of the management server 2 acquires voice data of the business negotiation from the user terminal 1 (S401). The business negotiation content acquisition unit 212 converts the voice data into text data (S402) and extracts the content of the current business negotiation from the text data (S403). The linking unit 218 assigns a customer identifier and a case identifier to the content of the current business negotiation (S404). The business negotiation content acquisition unit 212 stores the content of the current business negotiation in the business negotiation content storage unit 231 (S405). The past business negotiation content acquisition unit 213 acquires past business negotiation content from the business negotiation content storage unit 231 based on the customer identifier and case identifier (S406). The report generation unit 214 generates a business negotiation report based on both the past business negotiation content and the current business negotiation content (S407). The evaluation unit 215 evaluates the business negotiation based on both the past business negotiation content and the current business negotiation content (S408). The feedback generation unit 216 generates feedback based on both past and current sales negotiation details (S409). The CRM / SFA linkage unit 217 sends the sales negotiation report to the CRM / SFA system (S410). The management server 2 sends the sales negotiation report and feedback to the user terminal 1 (S411).

[0037] As described above, the information processing system of this embodiment can store the content of the current business negotiation while retaining the content of past business negotiations, and generate a business negotiation report based on both the content of past and current business negotiations. This enables analysis that takes into account the history of past business negotiations, which was not possible with report generation based only on single business negotiation records. Furthermore, the information processing system of this embodiment can automatically link business negotiation records on a customer or project basis through CRM / SFA integration. This eliminates the need to manually link multiple business negotiation records. In addition, the information processing system of this embodiment can generate evaluations and feedback on business negotiations based on both the content of past and current business negotiations. This makes it possible to provide appropriate advice that takes into account actions taken in the past, and avoids giving advice on actions that have already been taken. Furthermore, the information processing system of this embodiment can evaluate business negotiations based on the company's definition of sales activities. This enables objective business negotiation evaluation based on the company's sales policy. Furthermore, the information processing system of this embodiment can link the generated feedback to a sales AI agent. This allows AI agents to understand the history of each customer's sales negotiation and provide appropriate advice, resolving the challenge of AI agents being unable to grasp context. As a result, it can effectively support the enablement of solution sales and account sales.

[0038] Although these embodiments have been described above, they are intended to facilitate understanding of the present invention and are not intended to limit its interpretation. The present invention can be modified and improved without departing from its spirit, and equivalents thereof are also included.

[0039] For example, the processing performed by each functional unit of the management server 2 described above may be executed by any of the functional units. Furthermore, different functional units may be added to perform some of the processing performed by each of the functional units described above. Also, the functional units of the management server 2 may be distributed across multiple computers.

[0040] Furthermore, the information stored in each memory unit of the management server 2 may be stored in any of the memory units. That is, the information stored in the multiple memory units mentioned above may be stored in a single memory unit, or a portion of the information stored in one memory unit may be stored in another memory unit.

[0041] <Example 1> The above-described embodiment shows an example of acquiring negotiation content from audio data, but is not limited to this. The negotiation content acquisition unit 212 may also acquire negotiation content directly from text data. For example, the negotiation content acquisition unit 212 can receive text data of the negotiation minutes from the user terminal 1 and extract negotiation content from the text data. Alternatively, the negotiation content acquisition unit 212 can acquire transcript data of the negotiation from a video conferencing system and extract negotiation content from the transcript data. In this case, the audio acquisition unit 211 functions as a data acquisition unit that acquires text data instead of audio data. This makes it possible to omit speech recognition processing and shorten processing time.

[0042] <Modification 2> The embodiments described above show examples of linking deal records using customer identifiers and deal identifiers, but are not limited to these. The linking unit 218 can also link deal records using deal participant information. For example, the linking unit 218 can use the name and email address of the customer's representative who participated in the deal to search for past deals in which the same representative participated and link the deal records. The linking unit 218 can also link deal records using product names and service names included in the deal content. Furthermore, the linking unit 218 can calculate the similarity of deal content and link deal records where the similarity is above a predetermined threshold. The linking unit 218 can calculate the semantic similarity of deal content using a large-scale language model. This makes it possible to appropriately link deal records even for deals that are not registered in the CRM / SFA system.

[0043] <Variation 3> The above-described embodiment shows an example of generating a sales opportunity report using all past sales opportunity data, but it is not limited to this. The report generation unit 214 can also generate a sales opportunity report by selectively using sales opportunity data of high importance from past sales opportunity data. For example, the report generation unit 214 can prioritize selecting sales opportunity data that includes decisions made or sales opportunity data where customer issues have been clarified. The report generation unit 214 can also prioritize selecting sales opportunity data at important stages of the sales process. The report generation unit 214 can evaluate the importance of each sales opportunity data using a large-scale language model and select sales opportunity data of high importance. This reduces the number of input tokens to the large-scale language model and lowers processing costs. It also enables the generation of sales opportunity reports that focus on important information.

[0044] <Modification 4> In the embodiment described above, an example was shown in which the evaluation unit 215 evaluates a business negotiation. However, the evaluation unit 215 can also evaluate the actions of the sales representative. The evaluation unit 215 can extract the sales representative's statements and actions from past and current business negotiation content and evaluate the sales representative's actions by comparing them with desirable actions stored in the sales activity definition storage unit 233. For example, the evaluation unit 215 can evaluate whether the sales representative is able to properly hear the customer's issues, whether they are able to respond appropriately to the customer's statements, and whether the proposed content addresses the customer's issues. The evaluation unit 215 can input a prompt to the large-scale language model such as, "Extract the sales representative's statements from the following business negotiation content and evaluate them from the perspectives of customer issue hearing ability, proposal ability, and relationship building ability." This makes it possible to provide evaluations that are useful for improving the capabilities of sales representatives.

[0045] <Modification 5> In the embodiment described above, an example was shown in which the feedback generation unit 216 generates feedback for sales representatives. However, the feedback generation unit 216 can also generate feedback for sales managers. The feedback generation unit 216 can analyze the content of sales negotiations from multiple sales representatives and extract trends and challenges in the overall sales activities of the team. For example, the feedback generation unit 216 can extract that many deals are stalled at a particular stage of the sales process, or that there is a lack of proposals to address the challenges of a particular customer. Based on the extracted trends and challenges, the feedback generation unit 216 can propose measures to the sales manager to improve the overall sales activities of the team. This can support the improvement of capabilities not only for individual sales representatives but also for the entire sales organization.

[0046] <Variation 6> The above embodiment shows an example of sending a sales opportunity report to a CRM / SFA system, but the report generation unit 214 can also generate a sales opportunity report in a format that corresponds to the fields of the CRM / SFA system. The report generation unit 214 can obtain the field definitions of the CRM / SFA system via the CRM / SFA linkage unit 217 and extract the content corresponding to each field from the sales opportunity content. For example, if the CRM / SFA system has a field called "customer budget," the report generation unit 214 can extract information about the customer budget from the sales opportunity content and generate it as content to be entered into that field. The report generation unit 214 can input field definitions and sales opportunity content to the large-scale language model with a prompt that says, "Please extract the content to be entered into each field of the CRM / SFA system from the following sales opportunity content." This automates the input work to the CRM / SFA system.

[0047] <Example 7> The above-described embodiment shows an example of extracting deal content and generating deal reports using a large-scale language model, but it is not limited to this. The deal content acquisition unit 212 and the report generation unit 214 can also extract deal content and generate deal reports using rule-based natural language processing technology. For example, the deal content acquisition unit 212 can extract sentences containing keywords such as "by the next meeting" or "action item" as next actions. The deal content acquisition unit 212 can also extract sentences containing keywords such as "the issue is" or "the problem is" as customer issues. The report generation unit 214 can generate a deal report by applying the extracted deal content to a template. This makes it possible to generate a deal report even without using a large-scale language model.

[0048] <Differentiation Example 8> The above-described embodiment shows an example of acquiring negotiation content from audio data of a business negotiation, but the audio acquisition unit 211 can also acquire video data during the negotiation. The negotiation content acquisition unit 212 can analyze the participants' facial expressions and gestures from the video data and include them in the negotiation content. For example, the negotiation content acquisition unit 212 can analyze whether the customer showed a positive or negative facial expression in response to the proposal and record it in the negotiation content as the customer's reaction. The negotiation content acquisition unit 212 can also detect when the salesperson presents materials and record the content of the presented materials in the negotiation content. The evaluation unit 215 can also evaluate the salesperson's nonverbal communication. This makes it possible to include information that cannot be grasped from audio data alone in the negotiation content, enabling more detailed negotiation analysis.

[0049] <Modification 9> In the embodiment described above, an example was shown in which the management server 2 generates the sales opportunity report, but the user terminal 1 may also generate the sales opportunity report. In this case, the user terminal 1 is equipped with the same functional units as the management server 2. The user terminal 1 acquires the audio data of the sales opportunity and extracts the sales opportunity content from the audio data. The user terminal 1 sends the extracted sales opportunity content to the management server 2 and retrieves past sales opportunity content from the management server 2. The user terminal 1 generates a sales opportunity report based on both past sales opportunity content and current sales opportunity content. This makes it possible to generate a sales opportunity report even in an environment with an unstable network connection. In addition, since it is not necessary to send audio data to the management server 2, the amount of communication can be reduced.

[0050] <Variation 10> In the embodiment described above, an example was shown in which the deal content storage unit 231 stores deal content. However, the deal content storage unit 231 can also store summaries of deal content. The deal content acquisition unit 212 can summarize the extracted deal content using a large-scale language model and store the summarized deal content in the deal content storage unit 231. This reduces the storage capacity of the deal content storage unit 231. It also reduces the amount of data on past deal content acquired by the past deal content acquisition unit 213, and reduces the number of tokens that the report generation unit 214 inputs into the large-scale language model. The deal content acquisition unit 212 can adjust the level of detail of the summary. For example, the deal content acquisition unit 212 can generate a detailed summary for recent deal content and a concise summary for older deal content.

[0051] <Management of implementation status and identification of unaddressed next actions> The management server 2 may further include an implementation status management unit 219. The implementation status management unit 219 determines the implementation status of next actions included in past business negotiations based on the content of the current business negotiation, and stores the implementation status associated with the next action. The implementation status is information indicating, for example, not implemented, implemented, or partially implemented. The implementation status management unit 219 identifies next actions from past business negotiation content acquired by the past business negotiation content acquisition unit 213, and compares them with the content of the current business negotiation (content of statements, decisions, reports, etc. in the current business negotiation) to determine whether the next action has been implemented. For example, if the next action recorded in a past business negotiation was "submit a quotation by the next meeting," and the content of the current business negotiation includes the fact that a quotation was presented, the implementation status management unit 219 determines that the next action has been implemented; otherwise, it determines that it has not been implemented. The implementation status management unit 219 can determine the implementation status using a large-scale language model. For example, the implementation status management unit 219 inputs the next action and the current negotiation details into the large-scale language model with the prompt, "For each of the next actions agreed upon in the following past negotiations, refer to the current negotiation details and determine whether it has been completed, not completed, or partially completed." The implementation status management unit 219 stores the determined implementation status in the negotiation details storage unit 231, associating it with the corresponding next action. This ensures that the implementation status of each next action is continuously managed across multiple negotiations.

[0052] The report generation unit 214 can extract next actions from past sales negotiations that have been determined by the implementation status management unit 219 to be unimplemented, and include them in the sales negotiation report. The report generation unit 214 can also include the next actions determined to be unimplemented as a list of unaddressed next actions in the sales negotiation report. This makes it possible for sales representatives to grasp in an overview the items that were agreed upon in past sales negotiations but have not yet been implemented (unfinished business). The report generation unit 214 can exclude next actions that have been determined to be completed from the sales negotiation report, or include them with a note indicating that they have been completed. For next actions determined to be unimplemented, the report generation unit 214 can also include in the sales negotiation report the date and time of the sales negotiation in which the next action was agreed upon, as well as the period of time that has passed without implementation.

[0053] The evaluation unit 215 can evaluate a business deal based on the implementation status of the next actions. For example, if there are many next actions that were agreed upon in past business deals but have not yet been implemented, the evaluation unit 215 can include in the evaluation results that there is a delay in the progress of the sales process. In addition, the feedback generation unit 216 can generate feedback that includes a recommendation to prioritize the implementation of the next actions that have been determined to be unimplemented.

[0054] <Non-duplicate recommended actions and feedback> The feedback generated by the feedback generation unit 216 includes recommended actions. The feedback generation unit 216 refers to the feedback history storage unit 235, which stores recommended actions included in feedback generated in the past, and generates new feedback by excluding recommended actions that are the same as those previously presented. This avoids the repeated presentation of advice that has already been given in the past, and provides only new advice that takes into account the previous history.

[0055] Sales opportunity reports and feedback can be generated separately. A sales opportunity report is information that organizes the facts and status of a sales opportunity, such as the history of the opportunity, the progress of decisions made, the changes in the customer's issues, and the status of the implementation of next actions. On the other hand, feedback is advice (including recommended actions) that indicates what the sales representative should do next. The report generation unit 214 can include the feedback generated by the feedback generation unit 216 in the sales opportunity report. In other words, the feedback may be output as part of the sales opportunity report or may be output separately from the sales opportunity report.

[0056] <Generated using knowledge> The management server 2 may further include a knowledge acquisition unit 220 and a knowledge storage unit 234. Knowledge refers to information about customers, deals, or the company that contributes to the generation of deal reports, evaluations, or feedback, other than deal content derived from voice data. The knowledge storage unit 234 is a storage device that stores knowledge. The knowledge acquisition unit 220 acquires knowledge related to the current deal from the knowledge storage unit 234 or from an external system.

[0057] Knowledge includes, for example, at least one of the following: materials used in negotiations (proposals, quotations, product catalogs, specifications, white papers, case studies, price lists, contracts or contract templates, etc.), customer communication history (email history, chat history, inquiry response history, call logs, etc.), information held by business systems (customer information, deal information, activity history, negotiation phase, etc. held by CRM / SFA systems), information related to the company's sales activities (sales activity definitions, sales methods, talk scripts, FAQs, past successful or unsuccessful deals, competitor information, etc.), and external information (publicly available information from customer companies, industry reports, etc.). The knowledge acquisition unit 220 may search for relevant knowledge using the customer identifier or deal identifier assigned to the current negotiation, or it may search for knowledge semantically related to the content of the current negotiation using a large-scale language model.

[0058] The report generation unit 214 can generate a sales negotiation report based on past sales negotiation content, current sales negotiation content, and knowledge acquired by the knowledge acquisition unit 220. For example, the report generation unit 214 can generate a sales negotiation report that more accurately organizes the history of the negotiation by referring to customer requests included in the history of past emails and proposal content described in proposal materials. Similarly, the evaluation unit 215 and the feedback generation unit 216 can generate evaluations or feedback based on the knowledge acquired. This makes it possible to generate more accurate sales negotiation reports, evaluations, and feedback that take into account information that cannot be grasped from sales negotiation audio data alone.

[0059] In addition to the processing flow shown in Figure 4, the implementation status management unit 219 may perform a step of determining the implementation status of next actions included in past business negotiations based on the current business negotiation content, and the knowledge acquisition unit 220 may perform a step of acquiring knowledge related to the current business negotiation. In this case, the report generation unit 214 will generate a business negotiation report based on the next actions determined to be unimplemented and the acquired knowledge.

[0060] <Disclosure Items> Furthermore, this disclosure also includes the following configurations. [Item 1] A voice acquisition unit that acquires audio data of business negotiations, A business negotiation content acquisition unit that acquires the details of the current business negotiation from the aforementioned audio data, wherein the details of the current business negotiation include the next action, which is an action to be taken that has been explicitly stated by the parties in the business negotiation. A business negotiation content storage unit that stores the acquired details of the current business negotiation, including the next action, A past business negotiation content acquisition unit acquires past business negotiation content from the aforementioned business negotiation content storage unit, Regarding the next actions included in the aforementioned past business negotiations, the implementation status is determined based on the current business negotiations, and the implementation status is associated with the next action and stored in the system; A report generation unit that generates a sales negotiation report based on both the content of past sales negotiations and the content of the current sales negotiation, wherein the report generation unit includes in the sales negotiation report the next actions included in the content of past sales negotiations that indicate that the implementation status has not been implemented, An information processing system equipped with the following features. [Item 2] The aforementioned business negotiation content acquisition unit is an information processing system as described in item 1, which extracts at least one of the following as the business negotiation content: purpose, summary, decisions, next actions, customer challenges, and customer requirements. [Item 3] A feedback generation unit generates feedback that includes recommended actions, which are actions that are recommended based on the current business negotiation and are not explicitly stated in the current business negotiation, based on both the content of the past business negotiation and the content of the current business negotiation. The system further comprises a feedback history storage unit that stores the generated feedback, The information processing system according to item 1, wherein the feedback generation unit generates the feedback by excluding the recommended actions that are the same as past feedback stored in the feedback history storage unit. [Item 4] The information processing system described in item 3, wherein the report generation unit includes the feedback generated by the feedback generation unit in the sales negotiation report. [Item 5] Furthermore, we have a knowledge acquisition department to acquire knowledge related to business negotiations. The information processing system described in item 1, wherein the report generation unit generates the business negotiation report based on the knowledge in addition to the past business negotiation details and the current business negotiation details. [Item 6] The information processing system described in item 5 includes, among other things, at least one of the following: materials used in business negotiations, email history with customers, chat history with customers, inquiry response history, and definitional information relating to the company's sales activities. [Item 7] The information processing system described in item 1, wherein the report generation unit extracts the differences between the content of past business negotiations and the content of the current business negotiation, and includes information indicating changes in the customer's challenges or requirements in the business negotiation report. [Item 8] The information processing system described in item 1, wherein the report generation unit generates the business negotiation report by weighting it according to the recency of multiple past business negotiation details when they have been acquired. [Item 9] The information processing system described in item 1, further comprising an evaluation unit that evaluates a business negotiation based on both the content of past business negotiations and the content of the current business negotiation. [Item 10] The evaluation unit is an information processing system described in item 9 that evaluates business negotiations using a large-scale language model. [Item 11] The information processing system described in item 10 specifies evaluation criteria for the prompts given to the large-scale language model. [Item 12] The information processing system according to item 1, further comprising a linking unit that links the content of the current business negotiation to past business negotiations based on the semantic similarity between the content of the current business negotiation and the content of past business negotiations. [Item 13] The information processing system described in item 1, further comprising a linking unit that links the details of the current business negotiation to a customer or deal based on customer information or deal information obtained from an external CRM system or SFA system. [Item 14] Steps to acquire audio data of the business negotiation, The steps include obtaining the details of the business negotiation from the aforementioned audio data, including the next action, which is the action to be taken by the parties in the negotiation, and The steps include recording the details of the current business negotiation, including the next action, in the business negotiation content storage unit, The steps include: obtaining past negotiation details from the aforementioned negotiation details storage unit, Regarding the next actions included in the aforementioned past business negotiations, the step of determining the implementation status based on the content of the current business negotiations, A step of generating a sales opportunity report based on both the content of past sales opportunities and the content of the current sales opportunity, wherein the next actions included in the content of past sales opportunities that are not yet implemented are included in the sales opportunity report. A method of information processing performed by a computer. [Item 15] A program that causes a computer to perform each of the steps described in item 14. [Explanation of Symbols]

[0061] 1 User terminal 2 Management Server 219 Implementation Status Management Department 220 Knowledge Acquisition Department 234 Knowledge Memory Unit 235 Feedback history storage unit

Claims

1. A voice acquisition unit that acquires audio data of business negotiations, A business negotiation content acquisition unit that acquires the details of the current business negotiation from the aforementioned audio data, wherein the details of the current business negotiation include the next action, which is an action to be taken that has been explicitly stated by the parties in the business negotiation. A business negotiation content storage unit stores the acquired details of the current business negotiation, including the next action, A past business negotiation content acquisition unit acquires past business negotiation content from the aforementioned business negotiation content storage unit, Regarding the next actions included in the aforementioned past business negotiations, the implementation status is determined based on the current business negotiations, and the implementation status is associated with the next action and stored in the system; A report generation unit that generates a sales negotiation report based on both the content of past sales negotiations and the content of the current sales negotiation, wherein the report generation unit includes in the sales negotiation report the next actions included in the content of past sales negotiations that indicate that the implementation status has not been implemented, An information processing system equipped with the following features.

2. The information processing system according to claim 1, wherein the business negotiation content acquisition unit extracts at least one of the following as the business negotiation content: purpose, summary, decisions, next actions, customer issues, and customer requirements.

3. A feedback generation unit generates feedback that includes recommended actions, which are actions that are recommended based on the current business negotiation and are not explicitly stated in the current business negotiation, based on both the content of the past business negotiation and the content of the current business negotiation. The system further comprises a feedback history storage unit that stores the generated feedback, The information processing system according to claim 1, wherein the feedback generation unit generates the feedback by excluding the recommended actions that are the same as past feedback stored in the feedback history storage unit.

4. The information processing system according to claim 3, wherein the report generation unit includes the feedback generated by the feedback generation unit in the business negotiation report.

5. Furthermore, we have a knowledge acquisition department to acquire knowledge related to business negotiations. The information processing system according to claim 1, wherein the report generation unit generates the business negotiation report based on the knowledge in addition to the past business negotiation details and the current business negotiation details.

6. The information processing system according to claim 5, wherein the knowledge includes at least one of the following: materials used in business negotiations, email history with customers, chat history with customers, inquiry response history, and definition information relating to the company's sales activities.

7. The information processing system according to claim 1, wherein the report generation unit extracts the difference between the content of past business negotiations and the content of the current business negotiation, and includes information indicating a change in the customer's challenges or requirements in the business negotiation report.

8. The information processing system according to claim 1, wherein the report generation unit generates the business negotiation report by weighting it according to the recency of multiple past business negotiation details when a number of past business negotiation details have been acquired.

9. The information processing system according to claim 1, further comprising an evaluation unit that evaluates a business negotiation based on both the content of past business negotiations and the content of the current business negotiation.

10. The information processing system according to claim 9, wherein the evaluation unit evaluates business negotiations using a large-scale language model.

11. The information processing system according to claim 10, wherein the prompt given to the large-scale language model specifies the criteria for evaluation.

12. The information processing system according to claim 1, further comprising a linking unit that links the contents of the current business negotiation to past business negotiations based on the semantic similarity between the contents of the current business negotiation and the contents of past business negotiations.

13. The information processing system according to claim 1, further comprising a linking unit that links the details of the current business negotiation to a customer or case based on customer information or case information obtained from an external CRM system or SFA system.

14. Steps to acquire audio data of the business negotiation, The steps include obtaining the details of the business negotiation, including the next action which is the action to be taken as explicitly stated by the parties in the negotiation, from the aforementioned audio data, The steps include recording the details of the current business negotiation, including the next action, in the business negotiation content storage unit, The steps include: obtaining past negotiation details from the aforementioned negotiation details storage unit, Regarding the next actions included in the aforementioned past business negotiations, the step of determining the implementation status based on the content of the current business negotiations, A step of generating a sales opportunity report based on both the content of past sales opportunities and the content of the current sales opportunity, wherein the next actions included in the content of past sales opportunities that are not yet implemented are included in the sales opportunity report. A method of information processing performed by a computer.

15. A program for causing a computer to perform each of the steps described in claim 14.

Images