Proposal support device

Abstract

To provide a proposal support device for supporting a new proposal for business activity to a customer.SOLUTION: The proposal support device 1 includes a first prompt creation module 11 that creates a first prompt instructing the generation AI3 to create a plurality of proposal candidates, a model creation module 13 that acquires past proposal data including a plurality of past proposals and including a first explanatory variable indicating a feature of each of the past proposals and an objective variable indicating a contract success or failure and creates a model indicating a relationship between the first explanatory variable and the objective variable, a second prompt creation module 12 that creates a second prompt instructing the generation AI3 to create a second explanatory variable indicating a feature of each of the proposal candidates, and a scoring module 14 that inputs the second explanatory variable to the model and calculates a first score of each of the proposal candidates.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to a proposal support device that supports new proposals for sales activities to customers. [Background technology]

[0002] Being able to make an attractive proposal to a customer is extremely important in sales activities. In addition to the content of the proposal, an appealing expression that accurately conveys its appeal is also an important element. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-120803 Summary of the Invention [Problem to be solved by the invention]

[0004] Patent Document 1 describes a creation support device that accepts a new inquiry including information on required specifications and supports the creation of a proposal including information on bidding specifications corresponding to the new inquiry. In Patent Document 1, the similarity between the content included in the new inquiry and the content included in past inquiries or past proposals is calculated, and content useful for creating a proposal is extracted from history data associated with the past inquiries using the similarity.

[0005] However, since Patent Document 1 extracts content from past historical data, it cannot generate new proposals. Furthermore, the proposals in Patent Document 1 are subject to the required specifications written in a new quotation, and the content of the proposal is bound by the required specifications, making it unsuitable for generating new proposals.

[0006] One aspect of the present invention relates to a proposal support device that allows for the creation of novel proposal candidates that are not bound by past proposals by having a generation AI generate proposal candidates, and that can eliminate proposal candidates that are unlikely to be concluded, such as unusual proposal candidates, by evaluating the proposal candidates made by the generation AI based on the content of other proposals made in the past and whether or not they were concluded. [Means for solving the problem]

[0007] A proposal support device according to one aspect of the present invention comprises: a first prompt creation module that creates a first prompt that instructs a first generation AI to generate a plurality of suggestion candidates; a model creation module that acquires past proposal data including a plurality of past proposals, the past proposal data including a first explanatory variable indicating characteristics of each of the past proposals and a target variable indicating whether or not a contract has been concluded, and creates a model indicating the relationship between the first explanatory variable and the target variable; a second prompt creation module that creates a second prompt that instructs a second generation AI to generate second explanatory variables that indicate characteristics of each of the proposal candidates; a scoring module that inputs the second explanatory variable into the model and calculates a first score for each of the proposal candidates; Includes. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 shows a proposal support device 1 according to the first embodiment and an external device connected to the proposal support device 1. As shown in FIG. [Figure 2] FIG. 2 shows the functions and operations of the proposal support device 1 according to the first embodiment. [Figure 3A] FIG. 3A shows an example of user input items for creating the first prompt in the first embodiment. [Figure 3B] FIG. 3B shows an example of the first prompt sent to Generation AI3. [Figure 3C]FIG. 3C shows an example of a response from Production AI3 to the first prompt shown in FIG. 3B. [Figure 4] FIG. 4 shows an example of past proposal data for creating a model in the first embodiment. [Figure 5] FIG. 5 shows a list of explanatory variables generated in the first embodiment. [Figure 6A] FIG. 6A shows an example of a second prompt sent to generation AI3 when variable B1 is sought as the second explanatory variable. [Figure 6B] FIG. 6B shows an example of a second prompt sent to generation AI3 to determine variables P1-P3. [Figure 6C] FIG. 6C shows an example of a second prompt sent to generation AI3 to ask for variable R3. [Figure 6D] FIG. 6D shows an example of a second prompt sent to Generation AI3 to ask for variable R4. [Figure 6E] FIG. 6E shows an example of a second prompt sent to Generation AI3 to ask for variable R5. [Figure 6F] FIG. 6G shows an example of a second prompt sent to generation AI3 to ask for variable R6. [Figure 7] FIG. 7 shows an example of proposal candidate data generated in the first embodiment. [Figure 8] FIG. 8 shows the functions and operations of a proposal support device 1a according to the second embodiment. [Figure 9] FIG. 9 is a flowchart showing the process by which the latent score calculation module 16 calculates the latent score. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Each embodiment described below shows an example of the present invention and does not limit the content of the present invention. Furthermore, not all of the configurations and operations described in each embodiment are necessarily essential as the configurations and operations of the present invention. Note that the same components are given the same reference numerals, and redundant explanations will be omitted.

[0010] <1. First embodiment> <1-1.Configuration> FIG. 1 shows a proposal support device 1 according to the first embodiment and external devices connected to the proposal support device 1. The proposal support device 1 is a computer system including a CPU, memory, etc. (not shown). The proposal support device 1 may be configured with a single computer or multiple computers connected via a network. The proposal support device 1 is connected to external devices such as a database 2 and a generation AI 3.

[0011] The database 2 stores past proposal data and other data. The database 2 is not limited to data stored in a single storage device, but may be data stored in multiple storage devices. The proposal support device 1 acquires various data from the database 2 and performs processes such as prompt creation, model creation, and scoring.

[0012] The generative AI 3 includes a large-scale language model (LLM). The large-scale language model is a language model constructed using large amounts of text data and deep learning technology, and processes tasks such as text generation, translation, question answering, text summarization, and sentiment analysis in response to prompts sent from the proposal support device 1. It is desirable for the large-scale language model to have an attention mechanism. The attention mechanism is a mechanism for extracting important parts from the input, and greatly contributes to improving the processing speed and accuracy of the large-scale language model.

[0013] The generation AI 3 may further include an image generation AI. The image generation AI is a system that generates images from prompts written in text, and uses, for example, a diffusion model. Note that the "image" in the following description may also be a video. The generation AI 3 may further include a presentation material generation AI.

[0014] The proposal support device 1 sends a prompt to the generation AI 3 and obtains an output from the generation AI 3.

[0015] <1-2. Functions and operations> 2 shows the functions and operations of a proposal support device 1 according to the first embodiment. The proposal support device 1 includes a first prompt creation module 11, a second prompt creation module 12, a model creation module 13, a scoring module 14, and a proposal selection module 15. These modules are implemented by loading programs into memory included in the proposal support device 1 and executing them by a CPU.

[0016] The past proposal data stored in the database 2 includes, for each of a plurality of past proposals, text, an actual proposal or the like, a first explanatory variable, and a target variable. Details of the past proposal data will be described later with reference to FIG.

[0017] The first prompt creation module 11 receives user input such as information about the proposal recipient and creates a first prompt that instructs the creation AI 3 to generate multiple proposal candidates. A specific example of creating the first prompt will be described later with reference to Figures 3A to 3C.

[0018] The second prompt creation module 12 acquires multiple proposal candidates generated by the generation AI 3 and creates a second prompt that instructs the generation AI 3 to generate second explanatory variables from the proposal candidates. The second explanatory variables are not necessarily created based solely on the text of the proposal candidates, but may be created by referring to the text of past proposals, the actual proposal documents of past proposals, or the first explanatory variables of past proposals. Specific examples of creating a second prompt will be described below with reference to Figures 6A to 6F.

[0019] The model creation module 13 acquires the first explanatory variables and the dependent variables of each of the multiple past proposals to be learned from the database 2, and performs machine learning from the combination of the first explanatory variables and the dependent variables to create a model showing the relationship between the first explanatory variables and the dependent variables.

[0020] The scoring module 14 acquires second explanatory variables for each of the multiple proposal candidates to be predicted from the generation AI 3, inputs the second explanatory variables into the model, and calculates a first score for each of the multiple proposal candidates.

[0021] The proposal selection module 15 selects one or more proposals from the plurality of proposal candidates based on the first score.

[0022] In this application, the generation AI3 that generates proposal candidates in response to the first prompt may be referred to as the first generation AI, and the generation AI3 that generates the second explanatory variables in response to the second prompt may be referred to as the second generation AI. Furthermore, the generation AI3 (see FIG. 8) that generates presentation materials in response to the third prompt may be referred to as the third generation AI. The first to third generation AIs may be the same generation AI or may be different generation AIs.

[0023] <1-3. Details of the first prompt> 3A shows an example of user input items for creating a first prompt in the first embodiment. The user can specify a proposal recipient (e.g., a specialized company) and a proposal object (e.g., creating an advertising page for a product) from an input device (not shown) of the proposal support device 1 or an input device of a computer (not shown) connected to the proposal support device 1 via a network. If the user wants to limit the proposal recipient or proposal object to a specific or narrow range, the user can input specific information. Alternatively, if the user does not want to limit the proposal recipient or proposal object, the user does not need to input specific information such as the proposal recipient's attributes, company name, reference information, etc.

[0024] FIG. 3B shows an example of a first prompt sent to the generation AI 3. The first prompt creation module 11 creates a first prompt based on user input information, including a description for explaining the proposed recipient and the proposed object (e.g., "There is a specialized company that creates product advertising pages") and a template for the generation AI 3 to generate proposal candidates (e.g., "Please provide 10 proposal ideas to get work from this company"). When creating the first prompt, the user may provide the input information to the generation AI 3 to have the generation AI 3 create the description. The template may be stored in advance. The number of proposal candidates generated by the generation AI 3 is not limited to 10, and may be around 100.

[0025] Figure 3C shows an example of a response from the generation AI3 to the first prompt shown in Figure 3B. The generation AI3 generates multiple suggestions using the information provided by the first prompt and filling in the missing information with the most likely probabilistic content. The suggestions generated by the generation AI3 are shown again in Figure 7 as "Topic" and "Summary."

[0026] <1-4. Details of model creation> 4 shows an example of past proposal data for creating a model in the first embodiment. The past proposal data includes, for each of a plurality of past proposals, an ID, text, a first explanatory variable, and a target variable, as well as an actual proposal (not shown). Note that the second score is not required information in the first embodiment, and will be described later with reference to FIG. 8.

[0027] The text includes a theme, an outline, and a field, and the content manually input when it was actually proposed in the past can be used as is.

[0028] The first explanatory variables include variables B0 to B11, variables P1 to P3, and variables R1 to R6, and the specific contents of these will be described later with reference to Fig. 5. The first explanatory variables can be generated by the proposal support device 1 or can be generated by the generation AI 3, and the method for generating the first explanatory variables will be described together with the method for generating the second explanatory variables.

[0029] The objective variable indicates whether a deal was successfully concluded when it was actually proposed in the past, using a value of 1 or 0.

[0030] The model creation module 13 creates a function representing the relationship between the first explanatory variables and the dependent variables as a model, based on the first explanatory variables and the dependent variables for a plurality of past proposals.

[0031] <1-5. Details of variable generation> 5 shows a list of explanatory variables generated in the first embodiment. Since the second explanatory variables are input to a model created using the first explanatory variables, the first explanatory variables and the second explanatory variables have common explanatory variable items. However, the first explanatory variables indicating the characteristics of past proposals and the second explanatory variables indicating the characteristics of new proposal candidates differ in whether or not there is performance data for the proposals, so the methods for generating the explanatory variables may differ.

[0032] <1-5-1. Variables B0 to B11> The variables B0 to B11 are variables derived from the text of the proposal data or the contents of the actual proposal or the like.

[0033] The variable B0 is obtained by converting the fields contained in the text of the proposal data into codes such as industrial classifications.

[0034] When variables B1 to B11 are determined as first explanatory variables, they are mainly obtained from the content of actual proposals, etc., or from the text of proposal data, or other data. The generation AI 3 may be provided with the content of actual proposals, etc., the text of proposal data, or other data to generate variables B1 to B11. Variables obtained from other data may include attribute information related to the proposal process (e.g., a value of 1 for "referral" and a value of 0 for "public offering"), the implementation form (e.g., a value of 1 for "collaboration" and a value of 0 for "contract"), or the number of proposers or attribute information of the proposers. On the other hand, when variables B1 to B11 are obtained as second explanatory variables, since there is no actual proposal, a generation method different from that for the first explanatory variables is used as follows.

[0035] FIG. 6A shows an example of a second prompt sent to the generation AI3 when the variable B1 is determined as the second explanatory variable. The second prompt creation module 12 provides the generation AI3 with the text of multiple past proposals (see FIG. 4) and the text of the proposal candidate (see FIG. 7), extracts the top five past proposals with the highest thematic similarity to the proposal candidate, and weights the variable B1 of the top five past proposals by whether or not they were successful. By weighting the average by whether or not they were successful (e.g., a weight of 1 for successful and a weight of 0.5 for unsuccessful), more weight is placed on the successful data. In this way, even though the proposal candidate does not have performance data, the variable B1 of the proposal candidate can be generated by using the variable B1 of a similar past proposal. The variables B2 to B11 of the proposal candidate can also be generated in a similar manner. Here, the case of extracting the top five similarities has been described, but the number of similarities does not have to be five. Furthermore, while the case of weighting the average by whether or not they were successful has been described, weighting by similarity may also be performed.

[0036] The proposal candidate variables B1 to B3 can also be used as the estimated cost, estimated number of personnel, and estimated construction period when actually proposing the contents of this proposal candidate.Since each of the proposal candidate variables B1 to B3 is a weighted average based on the success or failure of past proposals, it is possible to present an estimate that is more likely to result in a successful outcome.

[0037] <1-5-2. Variables P1 to P3> 5 again, variables P1 to P3 are variables derived only from the text of the proposal data. The variables P1 to P3 are examples, and the number of variables may be further increased by, for example, decomposing the viewpoint.

[0038] 6B shows an example of a second prompt sent to the generation AI 3 to determine variables P1 to P3. The second prompt creation module 12 provides the generation AI 3 with the text of a proposal candidate (see FIG. 7) and requests it to evaluate the difficulty, profitability, and cost. While FIG. 6B shows a second prompt for determining variables P1 to P3 as second explanatory variables, the same can be applied to the first explanatory variables.

[0039] <1-5-3. Variables R1 to R6> 5 again, variables R1 to R6 are variables derived by referring to past proposal data. The variables R1 to R6 are examples, and the number of variables may be further increased by, for example, decomposing the viewpoint.

[0040] Variable R1 is the number of hits in a search of past proposal data using the theme keyword, and the more proposals that contain the same keyword, the larger the value. Variable R2 is the number of types of past actual proposal documents (proposals, estimates, specifications, minutes, daily reports, etc.) that are hit in a search using the theme keyword, and the larger the value, the more proposals that have reached a higher proposal phase. Variables R1 and R2 can be obtained by performing a process of extracting keywords from the theme and a search process. These processes may be performed by the proposal support device 1 or may be performed by the generation AI 3.

[0041] The variables R3 (evaluation of the task), R4 (evaluation of the implementation method), R5 (evaluation of variables P1, P2, and P3), and R6 (evaluation of variables B1, B2, and B3) can be generated by the generation AI3 using a technique called retrieval-augmented generation (RAG). Examples of second prompts sent to the generation AI3 to determine variables R3 through R6 are shown in Figures 6C through 6F, respectively. While these figures show second prompts for determining variables R3 through R6 as second explanatory variables, the same can be applied to the first explanatory variables. However, if there is no past proposal data to refer to, or if there is not enough of it, it is not necessary to refer to past proposal data when determining variables R3 through R6 as first explanatory variables.

[0042] <1-6. Scoring details> 7 shows an example of proposal candidate data generated in the first embodiment. The proposal candidate data includes an ID, text, and a second explanatory variable for each of a plurality of proposal candidates.

[0043] The text includes a theme, an outline, and a field, where the theme and outline are used as is from the text of the proposed candidate generated in FIG. 3C, and the field is obtained from the proposed object entered by the user in FIG. 3A.

[0044] Figure 7 also shows the first score obtained by inputting the second explanatory variable into the model. The first score is a value corresponding to the objective variable in past proposal data, i.e., a value indicating the probability that each proposal candidate will result in a trade. The larger the first score, the higher the probability that the proposal will be accepted by the client. Therefore, by selecting proposal candidates with a large first score, it is possible to make proposals with a high probability of trade execution.

[0045] <1-7.Effects> According to the first embodiment, the proposal support device 1 a first prompt generation module 11 that generates a first prompt that instructs the generation AI 3 to generate a plurality of proposal candidates; a model creation module 13 that acquires past proposal data including a plurality of past proposals, the past proposal data including a first explanatory variable indicating the characteristics of each of the past proposals and a target variable indicating whether or not a contract has been concluded, and creates a model indicating the relationship between the first explanatory variable and the target variable; a second prompt generation module 12 that generates a second prompt that instructs the generation AI 3 to generate second explanatory variables that indicate the characteristics of each of the proposal candidates; a scoring module 14 that inputs the second explanatory variables into the model and calculates a first score for each of the proposal candidates; Includes.

[0046] According to this, by having the generation AI3 generate new proposal candidates and calculating a first score based on past proposal data, it is possible to obtain free ideas that go beyond simply rehashing past proposals, and then use the first score to evaluate the likelihood of a successful transaction. The generation AI3 can have illusions, which are responses that deviate from the prompt requirements, but since the first score can be used to eliminate outlandish proposals, this phenomenon is actually advantageous from the perspective of generating new proposals, and the capabilities of the generation AI3 can be utilized without requiring perfection.

[0047] According to the first embodiment, the second prompt instructs the generation AI3 to generate second explanatory variables based on first explanatory variables of past suggestions similar to each of the suggestion candidates.

[0048] According to this, since second explanatory variables can be generated even for proposal candidates with no track record, it is possible to fill in the gaps in the second explanatory variables. Also, by using a combination of a second explanatory variable generated based on a first explanatory variable and a second explanatory variable generated without being based on the first explanatory variable, it is possible to perform highly accurate evaluation of proposal candidates.

[0049] 2. Second embodiment <2-1. Functions and operations> 8 shows the functions and operations of a proposal support device 1a according to the second embodiment. In addition to the various modules included in the proposal support device 1 described with reference to FIG. 2, the proposal support device 1a further includes a potential score calculation module 16, a content information acquisition module 17, and a third prompt creation module 18. These modules are implemented by loading programs into memory included in the proposal support device 1a and executing them by a CPU.

[0050] The past suggestion data stored in database 2 further includes a second score for each past suggestion. The second score is obtained by scoring module 14 inputting the first explanatory variable into the model. An example of the second score is shown in FIG. 4.

[0051] The potential score calculation module 16 calculates potential scores for keywords included in the text of the proposals (see FIG. 7) selected by the proposal selection module 15, using the method shown in FIG. 9. The potential score indicates the potential of the keywords themselves to contribute to closing a deal.

[0052] FIG. 9 is a flowchart showing the process by which the latent score calculation module 16 calculates a latent score. In 161, the latent score calculation module 16 extracts keywords from the text of the selected proposal. In 162, the latent score calculation module 16 searches past proposals using the extracted keywords. The search in 162 is not limited to a match search, but may also be a similarity search. In 163, the latent score calculation module 16 weights the second scores of the searched past proposals based on whether or not they were traded (for example, a weight of 1 for traded and a weight of 0.5 for traded). The higher the second score of a past proposal containing that keyword and the more often it was actually traded, the higher the latent score obtained. Using keywords with high latent scores in presentation materials can increase the possibility of closing a deal.

[0053] Referring again to FIG. 8, the content information acquisition module 17 searches a database (not shown) of the company (the proposer company) or searches the web to acquire content information that will form the basis of presentation materials, such as the company's product information and web pages.

[0054] The third prompt creation module 18 creates a third prompt that instructs the generation AI 3 to create presentation materials based on the proposal data (text, variables B1 to B3, etc.) selected by the proposal selection module 15 and content information.

[0055] The third prompt includes a prompt that instructs the generation AI 3 to generate text for a presentation that is highly appealing. The third prompt preferably instructs the generation AI 3 to always include keywords with high potential scores in the text for the presentation, or to use keywords with high potential scores multiple times in the text for the presentation.

[0056] The third prompt includes a prompt that instructs the generation AI 3 to generate an image for a compelling presentation. The third prompt that instructs the generation AI 3 to generate an image preferably includes keywords with a high potential score, and the third prompt may be generated by the generation AI 3.

[0057] The third prompt includes a prompt that instructs the Generation AI3 to create a presentation using these generated texts and images.

[0058] <2-2.Effects> According to the second embodiment, the proposal support device 1a a latent score calculation module 16 that extracts keywords from the proposal candidates selected based on the first score and calculates latent scores of the keywords; a third prompt generation module 18 that generates a third prompt that instructs the generation AI 3 to generate presentation materials for the selected proposal candidates; further comprising The scoring module 14 further inputs the first explanatory variables into the model to calculate a second score for each of the past suggestions; The latent score calculation module 16 searches past proposal data by the keyword, and calculates a latent score based on the second score of the searched past proposal data; The third prompt creation module 18 creates a third prompt to include the selected keywords in the presentation material based on the potential scores.

[0059] This allows you to create highly appealing presentation materials by using keywords selected based on their potential scores. [Explanation of symbols]

[0060] 1, 1a... proposal support device, 2... database, 3... generation AI, 11... first prompt creation module, 12... second prompt creation module, 13... model creation module, 14... scoring module, 15... proposal selection module, 16... potential score calculation module, 17... content information acquisition module, 18... third prompt creation module

Claims

1. a first prompt creation module that creates a first prompt that instructs a first generation AI to generate a plurality of suggestion candidates; a model creation module that acquires past proposal data including a plurality of past proposals, the past proposal data including a first explanatory variable indicating characteristics of each of the past proposals and a target variable indicating whether or not a contract has been concluded, and creates a model indicating the relationship between the first explanatory variable and the target variable; a second prompt creation module that creates a second prompt that instructs a second generation AI to generate second explanatory variables that indicate characteristics of each of the suggestion candidates; a scoring module that inputs the second explanatory variables into the model and calculates a first score for each of the proposal candidates; A proposal support device comprising:

2. The proposal support device according to claim 1, The second prompt instructs the second generation AI to generate the second explanatory variables based on the first explanatory variables of the past proposals similar to each of the candidate proposals. Proposal support device.

3. The proposal support device according to claim 1, a latent score calculation module that extracts keywords from the proposal candidates selected based on the first score and calculates latent scores of the keywords; a third prompt creation module that creates a third prompt that instructs a third generation AI to create a presentation material for the selected proposal candidate; further comprising The scoring module further inputs the first explanatory variables into the model to calculate a second score for each of the past suggestions; the potential score calculation module searches the past proposal data by the keyword, and calculates the potential score based on the second score of the searched past proposal data; the third prompt creation module creates the third prompt so that the selected keyword is included in the presentation material based on the potential score. Proposal support device.

Images