Support device, support method, and computer program

Abstract

This technology provides users with the ability to interact with artificial intelligence efficiently. [Solution] The control unit is configured to display a screen including a first display area and a second display area on a display device. The control unit performs the following actions each time an information input operation is performed on the first display area: display the input information, which is the information input by the information input operation, on the first display area; and each time an instruction input operation is performed via an input device to instruct processing on the input information, it sends a request signal to the artificial intelligence requesting at least one of a proposal, suggestion, and evaluation based on the input information in accordance with the instruction input operation, receives a generated sentence generated by the artificial intelligence as a response to the request signal, and displays the received generated sentence on the second display area.

Description

Technical Field

[0001] This disclosure relates to a support device.

Background Art

[0002] There is known a technique for assisting a user by using a generative AI (Artificial Intelligence), which is an artificial intelligence that generates a sentence based on information input by the user.

[0003] For example, Patent Document 1 discloses an apparatus for assisting a user's idea by using a generative AI to generate a plurality of category elements as an element group, combining the generated element group to generate a product concept, generating technical content for realizing the concept, and generating a detailed structure of the technical content.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The inventors of the present invention are considering providing a highly convenient system in the process of a user thinking while interacting with an artificial intelligence. However, in the idea support device as disclosed in Patent Document 1, there is a problem that the user cannot efficiently interact with the artificial intelligence.

[0006] One aspect of this disclosure is to provide a technique that enables a user to efficiently interact with an artificial intelligence.

Means for Solving the Problems

[0007] One aspect of this disclosure is a support device comprising a control unit and a communication unit. The control unit is configured to cause a screen including a first display area and a second display area to be displayed on a display device. The communication unit is configured to communicate with artificial intelligence.

[0008] The control unit is configured to display the input information, which is the information entered through the information input operation, in the first display area each time an information input operation is performed on the first display area via an input device configured to accept input operations from the user. The control unit is configured to send a request signal to the artificial intelligence via the communication unit in accordance with the instruction input operation each time an instruction input operation is performed on the input information instructing processing of the input information, to receive a generated sentence relating to at least one of the suggestion, suggestion, and evaluation generated by the artificial intelligence as a response to the request signal, and to display the received generated sentence in the second display area.

[0009] The control unit is configured to display the second generated statement in the second display area in place of the first generated statement, when the first generated statement is displayed in the second display area as a generated statement, and a second generated statement generated based on a new instruction input operation is to be displayed in the second display area as a generated statement, based on the first generated statement that is currently displayed.

[0010] With this configuration, users can interact with artificial intelligence 3 efficiently. In one aspect of this disclosure, the communication unit may be configured to communicate with a database. The control unit may be configured to extract relevant data, which is data related to the input information, from the database via the communication unit when it transmits a request signal to the artificial intelligence. The request signal may include a signal requesting the artificial intelligence to make at least one of a suggestion, indication, and evaluation based on the input information, taking the relevant data into account.

[0011] In one aspect of this disclosure, the input information may be marketing-related information. The related data may include marketing-related data. In one aspect of this disclosure, the control unit may be configured to retrieve multiple marketing data from a database, calculate the similarity between each of the multiple data and the input information, and extract at least one data with a high similarity from the multiple data as relevant data.

[0012] In one aspect of this disclosure, the control unit may be configured to generate natural language text describing numerical data contained in the related data. The request signal may include a signal requesting artificial intelligence to take the text into consideration and make at least one of a suggestion, an indication, and an evaluation.

[0013] With this configuration, the artificial intelligence can be requested to provide suggestions, hints, and evaluations based on objective, relevant data in response to the input information entered in the first display area. As a result, the user can obtain more effective suggestions, hints, and evaluations from the artificial intelligence.

[0014] In one aspect of this disclosure, the control unit may be configured to display both the first display area and the second display area simultaneously on the screen. With this configuration, users can consider what to input into the first display area while viewing the generated text displayed in the second display area without scrolling the screen. This allows users to interact with artificial intelligence efficiently.

[0015] In one aspect of this disclosure, the artificial intelligence may be configured to accept personality settings. The control unit may be configured to set the selected personality to the artificial intelligence each time a selection input operation is performed via an input device to select a personality for the artificial intelligence.

[0016] With this configuration, the quality of the generated text produced by the artificial intelligence can be adjusted based on the personality set for the AI. In one aspect of this disclosure, the input information may be information relating to a product or service.

[0017] In one aspect of this disclosure, the goods or services may be provided by an organization. The request signal may include a signal that requests artificial intelligence to make at least one of the suggestions, suggestions and evaluations regarding the value proposition of the organization to its customers through the goods or services.

[0018] This configuration can help users consider how an organization can provide value to its customers through its products or services. One aspect of the present disclosure is a computer-assisted method, comprising: causing a screen including a first display area and a second display area to be displayed on a display device; and communicating with artificial intelligence. The display includes: whenever an information input operation is performed on the first display area via an input device configured to accept user input operations, causing input information, which is information input by the information input operation, to be displayed on the first display area; whenever an instruction input operation is performed via the input device to instruct processing of the input information, transmitting a request signal to the artificial intelligence requesting at least one of a suggestion, suggestion, and evaluation based on the input information in accordance with the instruction input operation, receiving a generated statement relating to at least one of the suggestion, suggestion, and evaluation generated by the artificial intelligence in response to the request signal, and displaying the received generated statement on the second display area. The display of the generated statement on the second display area includes, when a first generated statement as a generated statement is displayed on the second display area, and a second generated statement generated based on a new instruction input operation is to be displayed on the second display area, displaying the second generated statement on the second display area in place of the displayed first generated statement.

[0019] This support method produces the same effect as the support device described above. In one aspect of this disclosure, a computer program may be provided for causing a computer to perform at least part of the above-described support method. [Brief explanation of the drawing]

[0020] [Figure 1] This is a block diagram showing the configuration of the support device. [Figure 2] It is a diagram for explaining an example of a screen that displays a set of explanatory texts, a first display area, a second display area, and a request section. [Figure 3] It is a diagram for explaining a web page as an interface for interaction between a user and an artificial intelligence. [Figure 4] It is a diagram for explaining an example of a screen that displays a set of explanatory texts, a first display area, a second display area, and a request section. [Figure 5] It is a flowchart showing the processing when the selection operation unit is operated. [Figure 6] It is a flowchart showing the processing of the support device when any of the buttons included in the request section is pressed. [Figure 7] It is a flowchart showing the processing of creating a request based on related data. [Figure 8] It is a diagram for explaining the processing of creating a request based on related data. [Figure 9] It is a diagram for explaining an example of a screen on which an image generation button, an image display section, a summary button, a summary display section, and an output button are displayed. [Figure 10] It is a diagram for explaining an example of a file output when the output button is pressed.

Mode for Carrying Out the Invention

[0021] Hereinafter, exemplary embodiments of the present disclosure will be described with reference to the drawings. [1. First Embodiment] [1-1. Configuration] [1-1-1. Overall Configuration] The support system 100 shown in FIG. 1 is a system for supporting various thoughts that a user conducts while interacting with an artificial intelligence. Examples of various thoughts include consideration of concepts of products or services, consideration of the management philosophy and purpose of an organization, etc. Examples of an organization include a company, a country, a local government, an NPO (Non-Profit Organization), etc.

[0022] The support system 100 comprises a support device 1, a user terminal 2, artificial intelligence 3, and a database 4. Support device 1 is a server connected to a communication network. Support device 1 is connected to the user terminal 2, artificial intelligence 3, and database 4 via the communication network, enabling them to communicate with each other. Examples of communication networks include wide area networks (WANs), local area networks (LANs), the internet, or a combination of these.

[0023] The support device 1 comprises a processor 11, memory 12, storage 13, and a communication interface 14. The processor 11 is configured to perform processing according to a computer program recorded in the storage 13.

[0024] Memory 12 is used as a working area when processing is executed by the processor 11. Examples of memory 12 include RAM (Random Access Memory), ROM (Read Only Memory), and flash memory.

[0025] Storage 13 holds computer programs and data used when executing processes that follow those computer programs. Examples of storage 13 include HDDs (Hard Disk Drives) and SSDs (Solid State Drives).

[0026] The communication interface 14 is an interface that can communicate various types of data with external devices in accordance with a predetermined standard. The support device 1 is configured to communicate with the user terminal 2, artificial intelligence 3, and database 4 through the communication interface 14.

[0027] User terminal 2 is an information terminal such as a smartphone, tablet, or personal computer. User terminal 2 comprises an input device 21, a display device 22, and a communication device 23.

[0028] The input device 21 is an input interface configured to accept various input operations from the user. Examples of input devices 21 include keyboards, mice, and touch panels. The display device 22 is an output interface for displaying various information to the user. The display device 22 is configured to display screen S. An example of the display device 22 is a display.

[0029] The communication device 23 is an interface that can communicate various types of data with the support device 1 according to a predetermined standard. The support device 1 and the user terminal 2 are configured to communicate with each other through the communication interface 14 and the communication device 23.

[0030] Artificial intelligence 3 is configured to generate text based on input information. Artificial intelligence 3 is configured to accept settings related to personality. An example of artificial intelligence 3 is generative AI (Artificial Intelligence). Examples of generative AI include OpenAI's ChatGPT, Google's Gemini, Microsoft's Copilot, and Anthropic's Claude.

[0031] When artificial intelligence 3 receives a request signal from support device 1, it generates a generated statement G as a response to the request signal and transmits it to support device 1. Artificial intelligence 3 generates the generated statement G based on the request contained in the request signal as input information. The request contained in the request signal is also called a prompt.

[0032] Database 4 contains multiple data related to marketing. These multiple data include numerical data. One example of Database 4 is the "Lifestyle Survey," which is consumer attitude survey data provided by Hakuhodo Institute of Life and Living.

[0033] [1-1-2. Structure of the support page] The support page 50 shown in Figure 2 is part of a web page that serves as an interface for interaction between the user and the artificial intelligence 3. An example of the support page 50 is shown in more detail in Figure 3. The support device 1 displays at least a portion of the support page 50 as a screen S on the display device 22 of the user terminal 2 via the communication interface 14. The user can operate the screen S displayed on the display device 22 using the input device 21.

[0034] The support page 50 includes a first display area 51, a second display area 52, a request section 53, a selection operation section 54, and an explanatory text T. The exemplary support page 50 shown in Figure 3 includes four first display areas 51s, 51a, 51b, and 51c as the first display area 51, and three second display areas 52a, 52b, and 52c as the second display area 52. The exemplary support page 50 includes three request sections 53a, 53b, and 53c as the request section 53, and two selection operation sections 54a and 54b as the selection operation section 54. The exemplary support page 50 includes four explanatory texts Ts, Ta, Tb, and Tc as the explanatory text T.

[0035] At the top of the support page 50, there is an explanatory text Ts. Below the explanatory text Ts, there is a first display area 51s. Below the first display area 51s, three sets of explanatory text T, first display area 51, second display area 52, and request section 53 are arranged in order, from explanatory text Ta, first display area 51a, second display area 52a, and request section 53a to explanatory text Tc, first display area 51c, second display area 52c, and request section 53c.

[0036] A sidebar is provided in the left-hand area of ​​the support page 50. The selection operation units 54a and 54b are located on the sidebar. Figure 4 is an example of a screen S that displays a set of explanatory text T, a first display area 51, a second display area 52, and a request section 53. The screen S displays the first display area 51, the second display area 52, the request section 53, input information I, generated text G, and explanatory text T.

[0037] The first display area 51 is an area that displays the input information I, which is the information entered by the user through the input device 21, each time the user performs an information input operation. In other words, the first display area 51 is an input field for the user to enter the input information I.

[0038] An information input operation is, for example, an operation in which, when the first display area 51 is in focus (i.e., the first display area 51 is in a state where input is possible), text as input information I is entered through an input device 21 (for example, a keyboard or touch panel).

[0039] Input information I is not limited to text data such as documents, but may be a file in any format. For example, input information I may be a PDF document file, or an image file such as JPEG or PNG.

[0040] The second display area 52 is an area that displays the generated text G received from the artificial intelligence 3 via the communication interface 14. The generated text G is a sentence generated by the artificial intelligence 3 when one of the buttons included in the request unit 53, which will be described later, is pressed.

[0041] The request section 53 includes at least one of the suggestion button 531, the indication button 532, and the evaluation button 533. In the example shown in Figure 2, the request section 53 includes all of the suggestion button 531, the indication button 532, and the evaluation button 533. However, the request section 53 does not have to include all of the suggestion button 531, the indication button 532, and the evaluation button 533. In the example shown in Figure 3, of the three request sections 53a, 53b, and 53c, request section 53a includes the suggestion button 531 and the indication button 532, but does not include the evaluation button 533. Request section 53b includes the suggestion button 531 and the evaluation button 533, but does not include the indication button 532. Request section 53c includes the suggestion button 531, but does not include the indication button 532 or the evaluation button 533.

[0042] The request unit 53 is configured to request at least one of the following from the artificial intelligence 3: a suggestion, an indication, or an evaluation based on the input information I, in order to support the user's thinking process, and to display the generated sentence G produced by the artificial intelligence 3 in the second display area 52. Details of the processing of the request unit 53 when the user operates the request unit 53 will be described later.

[0043] The selection operation unit 54 is a drop-down menu for making various settings to the artificial intelligence 3. By operating the selection operation unit 54, the user can make the corresponding settings to the artificial intelligence 3.

[0044] For example, the menu items of the selection operation unit 54 may include various personalities of the artificial intelligence 3. Examples of personalities include "Excellent Creator" and "Middle School Creator". The process for configuring various settings for artificial intelligence 3 is carried out by processor 11 based on the flowchart shown in Figure 5.

[0045] First, in S10, the processor 11 detects that a setting has been selected by the user operating the selection control unit 54. For example, it detects that "Excellent Creator" has been selected by the user as the personality of the artificial intelligence 3.

[0046] Next, in S20, the processor 11 sends a request signal containing the setting to the artificial intelligence 3 via the communication interface 14. For example, the request signal sent to the artificial intelligence 3 includes a sentence such as, "You are an excellent creator." By sending this request signal, the artificial intelligence 3 is given a corresponding personality. Based on the set personality, the artificial intelligence 3 generates a generated statement G based on the subsequent request.

[0047] After sending the request signal in S20, the processor 11 terminates the process shown in Figure 5. The item selected in the selection operation unit 54 does not have to be immediately transmitted to the artificial intelligence 3 as a request signal. The item selected in the selection operation unit 54 may be included in the request signal that the processor 11 transmits to the artificial intelligence 3 when processing the request unit 53, which will be described later.

[0048] The item selected in the selection operation unit 54 may be included in the request signal that the processor 11 sends to the artificial intelligence 3 when processing the request unit 53, which will be described later. Regarding a set of explanatory text T, a first display area 51, a second display area 52, and a request section 53, the first display area 51 and the second display area 52 are arranged side by side below the explanatory text T. The first display area 51 is positioned adjacent to the right of the second display area 52. The request section 53 is positioned between the explanatory text T and the second display area 52. The first display area 51 is configured to display input information I. The second display area 52 is configured to display generated text G.

[0049] On screen S, both the first display area 51 and the second display area 52 are configured to be displayed simultaneously. [1-2. Processing] The series of processes executed by the processor 11 when a user operates the request unit 53 will be explained using Figures 6, 7, and 8.

[0050] [1-2-1. Processing of the request section] When any of the buttons included in the request unit 53 are pressed via the communication interface 14 and the input device 21 of the user terminal 2, the processor 11 starts the process shown in Figure 6.

[0051] First, in S100, the processor 11 performs a request creation process to create a request signal to be sent to the artificial intelligence 3. In the request creation process, the processor 11 creates a request (i.e., a prompt) to be included in the request signal based on the input information I. In this embodiment, the request creation process differs depending on whether the suggestion button 531, the indication button 532, or the evaluation button 533 is pressed.

[0052] (A) When the suggestion button 531 is pressed When the suggestion button 531 is pressed, the processor 11 includes in the request the input information I displayed in one or more first display areas 51 corresponding to the suggestion button 531, and a sentence instructing the processor 11 to suggest a decision target, which is the object that the user wants to decide on, based on the input information I. The decision target is predetermined by the user. The processor 11 may also include related data, which is data related to the input information I, obtained from the storage 13 or from the database 4 by a method described later, in the request.

[0053] For example, if the input information I contains the characteristics of a certain product, and the target for determination is the target market for that product, the processor 11 will create a request that includes the instruction, "(Input Information) Please suggest a target market for this product based on this information." "(Input Information)" is a copy of the input information I. The target market is the group of consumers to whom the product or service is intended.

[0054] (B) If the suggestion button 532 is pressed When the suggestion button 532 is pressed, the processor 11 includes in the request input information I displayed in one or more first display areas 51 corresponding to the suggestion button 532, and a sentence instructing the processor to present suggestions for the user to think about the object to be decided based on the input information I.

[0055] For example, if the target of a certain product is entered as input information I, and the target to be determined is the target of that product, the processor 11 creates a request that includes the instruction "(Input Information) Please provide suggestions based on the following data regarding this content. (Related Data)" and related data. "(Related Data)" is a sentence based on related data. The processor 11 may use related data that is already stored in storage 13, or it may use related data obtained from database 4 using the method described later.

[0056] (C) If rating button 533 is pressed When the evaluation button 533 is pressed, the processor 11 includes in the request the input information I displayed in one or more first display areas 51 corresponding to the evaluation button 533, and a sentence instructing the user to perform an evaluation to think about the object to be decided based on the input information I.

[0057] For example, if the target of a certain product is entered as input information I, and the target to be determined is the target of that product, the processor 11 creates a request that includes the instruction "(Input Information) Evaluate this content based on the evaluation criteria. (Evaluation Criteria)" and the evaluation criteria. "(Evaluation Criteria)" may be a copy of the evaluation criteria already stored in storage 13, or criteria may be created as evaluation criteria using related data obtained from database 4 in the method described later.

[0058] Next, in S110, the processor 11 transmits the request generated in S100 to the artificial intelligence 3 as a request signal via the communication interface 14. The processing from S110 onward is the same regardless of whether the suggestion button 531, the indication button 532, or the evaluation button 533 is pressed.

[0059] Next, in S120, the processor 11 removes the generated statement G displayed in the second display area 52 from the second display area 52. If the generated statement G is not displayed in the second display area 52, the processor 11 does not need to do anything.

[0060] Next, in S130, the processor 11 displays the generated sentence G received from the artificial intelligence 3 in the second display area 52. After that, the processor 11 terminates the process shown in Figure 6.

[0061] In this way, whenever an instruction input operation is performed via the input device 21 to instruct the processor 11 to process the input information I, the processor 11 sends a request signal to the artificial intelligence 3 via the communication interface 14 in accordance with the instruction input operation, requesting at least one of a proposal, suggestion, and evaluation based on the input information I.

[0062] In this embodiment, the instruction input operation is the operation of pressing one of the buttons on the request unit 53 via the input device 21 in order to instruct the artificial intelligence 3 to provide at least one of a suggestion, indication, and evaluation regarding the input information I.

[0063] The processor 11 receives a generated statement G, which is generated by the artificial intelligence 3 in response to a request signal, relating to at least one of a proposal, suggestion, and evaluation, and displays the received generated statement G on the display device 22 of the user terminal 2 via the communication interface 14.

[0064] When the processor 11 is displaying a generated statement G in the second display area 52 and wants to display a generated statement G generated based on a new instruction input operation in the second display area 52, it displays the new generated statement G in the second display area 52 instead of the currently displayed generated statement G.

[0065] [1-2-2. Request creation process using related data] In step S100 of Figure 6, the processor 11 may include in the request instructions to extract related data, which is data related to the input information I, from the database 4 via the communication interface 14, and to make at least one of the following based on the input information I: a suggestion, an evaluation, or a proposal, based on the related data. The request creation process using related data will be explained below with reference to the flowchart in Figure 7 and Figure 8.

[0066] When the processor 11 performs request creation processing using related data, if any of the buttons included in the request unit 53 are pressed by the user, it starts the processing shown in Figures 7 and 8. First, in S200, processor 11 retrieves multiple data points from database 4. These data points may be marketing-related data.

[0067] Next, in S210, the processor 11 performs embedding on both the input information I and the multiple data points. Embedding is a process used in natural language processing and machine learning to convert text data such as words and sentences into numerical vectors that are easy for artificial intelligence 3 to handle. In Figure 8, "Emb i" is the numerical vector obtained by performing embedding on the input information I. "Emb Dj" is the multiple numerical vectors obtained by performing embedding on the multiple data points acquired in S200.

[0068] Next, in S220, the processor 11 calculates the similarity between the input information I and each of the multiple data points. Specifically, it calculates the cosine similarity between the numerical vector of the input information I obtained by embedding in S210 and each of the numerical vectors of the multiple data points. The similarity may be calculated by methods other than cosine similarity.

[0069] Next, in S230, the processor 11 uses the similarity calculated in S220 to extract at least one data with high similarity from the multiple data as related data. For example, the top three data with high similarity are extracted as related data. In Figure 8, "Emb A", "Emb B", and "Emb C" are the related data extracted as the top three data with high similarity.

[0070] Next, in S240, processor 11 creates natural language sentences that explain the numerical data included in the extracted related data. For example, a sentence explaining the numerical data might be: "The percentage of people who answered 'I like Japanese food' to the question 'Please tell us what applies to your diet' decreased by about 3 points from the previous survey, reaching 42.1% in 2022. Regarding the gender difference, women were about 10 points higher." In this case, the numerical data for "the percentage of people who answered 'I like Japanese food' to the question 'Please tell us what applies to your diet'" was 45.1% in 2021 and 42.1% in 2022. The numerical data for "men in 2022" was 37.1%, and the numerical data for "women in 2022" was 47.1%.

[0071] As can be understood from the above explanation, the multiple data obtained from database 4 in S200 may be statistical data of the response results of a group of respondents to multiple questions obtained from a lifestyle awareness survey stored in database 4. Multiple data may be prepared for each question. Each of the multiple data may be data that summarizes the results of surveys conducted multiple times for a single question in chronological order. If multiple answer choices are provided for a question, each of the multiple data may include chronological data of the response rate for each choice for the corresponding single question. The response rate for a single choice may include the response rate by respondent's demographic attribute.

[0072] Texts describing numerical data can be created in various ways. One example is to prepare a template text that includes missing values ​​in advance and replace the missing values ​​with numerical data. In the example above, missing values ​​include values ​​related to the observation year (time), observed value (statistical value), and the amount of change in the observed value (statistical value), such as "2022", "3 points", and "42.1%".

[0073] In Figure 8, "Text A," "Text B," and "Text C" are natural language sentences that describe the numerical data contained in the data corresponding to "Emb A," "Emb B," and "Emb C" from among multiple data sets.

[0074] Next, in S250, the processor 11 creates a request (i.e., a prompt) to be included in the request signal to be sent to the artificial intelligence 3. The request includes input information I and the text created in S240. The request includes a sentence instructing that at least one of the following—a suggestion, an evaluation, and an evaluation based on the input information I—below the sentence created in S240. In Figure 8, the request includes "Text A," "Text B," and "Text C." Furthermore, the request includes a sentence instructing that these be used to provide useful suggestions regarding the input information I.

[0075] Subsequently, processor 11 completes the process shown in Figure 7 and returns to the process shown in Figure 6. In S110, processor 11 sends the generated request as a request signal to artificial intelligence 3. In this way, the processor 11 may extract relevant data from the database 4, which is data related to the input information I. The processor 11 may also create natural language sentences that describe the numerical data contained in the extracted relevant data. The request may include instructions for the processor 11 to make at least one of the following based on the created sentences: a suggestion, an indication, and an evaluation based on the input information I.

[0076] [1-3. Effects] According to the embodiments described above, the following effects can be obtained. (1a) The user can efficiently interact with the artificial intelligence 3 by using the support system 100.

[0077] A specific example of use is shown below. The example below shows the procedure for a user to create a product concept for "○○ Tofu" while interacting with artificial intelligence 3. A concept is the value that an organization provides to its demanders through a product or service in marketing (i.e., value proposition). Demanders are, for example, buyers of products or recipients of services. Demanders may also be customers or consumers.

[0078] The user determines several elements to create a concept. Based on these elements, the user creates the concept. In the following example, the elements include "target" and "target insights" in marketing, but are not limited to these; other elements may also be included.

[0079] "Target" refers to the group of consumers who are the target audience for a product or service. For example, the target for "○○ Tofu" is "men and women in their 20s and 30s who are highly interested in health and nutrition."

[0080] "Target insights" represent the target's subconscious, values, and essential inner desires. For example, the target insight for "○○ Tofu" is: "I want to eat a nutritious meal in the morning to feel energized. However, I'm especially busy in the mornings and don't have even 5 minutes to spare." Hereafter, target insights will also be simply referred to as insights.

[0081] Users create concepts based on these multiple elements. For example, a user might create the concept "Nutritious XX Tofu for busy mornings" based on the multiple elements in the example above.

[0082] The user uses the support system 100 to determine the above-mentioned elements and concepts. In Figure 3, the explanatory text Ts contains the sentence, "Please define the characteristics of the product for which you want to create a concept."

[0083] First, the user inputs the characteristics of the product for which they want to create a concept into the first display area 51s via the input device 21. The user may also input the price and country of origin of the product. For example, the user inputs the following text into the first display area 51s as a characteristic of "○○ Tofu": "×× Tofu Shop is a long-established tofu shop that has been in business for about 70 years. Its signature product is a firm tofu called "○○ Tofu". It uses 2.8 times the amount of soybeans as regular tofu and is known to be very nutritious, including protein. On the other hand, it is low in calories, just like regular tofu. It is commonly eaten as "tofu steak" rather than as cold tofu, and it does not easily fall apart even when used in dishes such as mapo tofu."

[0084] Next, the explanatory text Ta contains the sentence, "First, let's decide on a target." When the user presses the suggestion button 531 on the request unit 53a via the input device 21, the generated text Ga1 relating to the target corresponding to the product's characteristics is displayed in the second display area 52a.

[0085] Generated text Ga1 is generated by artificial intelligence 3 using the product characteristics entered by the user in the first display area 51s as input information I. Generated text Ga1 represents candidate target groups for the product as suggested by artificial intelligence 3. For example, generated text Ga1 is: "1. Health-conscious young generation: Men and women in their 20s and 30s who are highly interested in health and nutrition. 2. Households that enjoy cooking: Households that enjoy cooking as a hobby, especially housewives and househusbands in their 30s to 50s. 3. Eco-conscious consumers: Across all age groups, but especially common among younger generations."

[0086] Next, the user enters the product's target audience in the first display area 51a. The user may copy at least a portion of the generated text Ga1 displayed in the second display area 52a to the first display area 51a. The user may also add, modify, or delete parts of the text copied to the first display area 51a. For example, the user copies a portion of the generated text Ga1 and enters the sentence "Men and women in their 20s and 30s who are highly interested in health and nutrition" into the first display area 51a.

[0087] Next, when the user presses the suggestion button 532 on the request unit 53a via the input device 21, the generated statement Ga1 corresponding to the product's characteristics, which was displayed in the second display area 52a, is deleted, and a new generated statement Ga2 representing a suggestion based on the content entered in the first display area 51a is displayed.

[0088] Generated text Ga2 is generated by artificial intelligence 3 using the product characteristics entered by the user in the first display area 51s and the target product entered in the first display area 51a as input information I. Generated text Ga2 represents the artificial intelligence 3's suggestion regarding the target product entered by the user in the first display area 51a, based on the data in database 4. For example, generated text Ga2 is: "In response to the question, 'Do you live a healthy lifestyle?', 28.5% of people in their 20s answered 'Neither agree nor disagree,' which is a higher percentage than the overall average. This suggests that people in their 20s are not yet confident about whether they live a healthy lifestyle. Therefore, emphasizing the high nutritional value and low calorie content of ○○ tofu will make a strong appeal to health-conscious young couples."

[0089] The user may modify the target of the product entered in the first display area 51a, taking into account the suggestions in the generated statement Ga2. Next, the explanatory text Tb contains the sentence, "Next, let's set the target insights." When the user presses the suggestion button 531 on the request unit 53b via the input device 21, the generated text Gb1 regarding the insights corresponding to the product's target is displayed in the second display area 52b.

[0090] The generated sentence Gb1 is a generated sentence G generated by artificial intelligence 3 using the product characteristics entered by the user in the first display area 51s and the product target entered in the first display area 51a as input information I. The generated sentence Gb1 represents candidate insights for the product target proposed by artificial intelligence 3. For example, the generated sentence Gb1 is: "1. I want to eat healthy meals easily, but I don't want to compromise on the quality or nutritional value of the ingredients. 2. I want to save time on cooking in my busy daily life, but I want to provide meals that consider the health of my family. 3. I want to try new ingredients and dishes, but I don't want to fail, and I want my family to be happy."

[0091] Next, the user enters the product's target insights into the first display area 51b. The user may copy at least a portion of the generated text Gb1 displayed in the second display area 52b into the first display area 51b. The user may add, modify, or delete parts of the text copied into the first display area 51b. For example, the user copies a portion of the generated text Gb1 and enters the sentence, "I want to save time on cooking in my busy daily life, but I also want to provide meals that consider my family's health," into the first display area 51b.

[0092] Next, when the user presses the evaluation button 533 on the request unit 53b via the input device 21, the generated statement Gb1 corresponding to the product's target insight, which was displayed in the second display area 52b, is deleted, and a new generated statement Gb2 related to the evaluation based on the content entered in the first display area 51b is displayed.

[0093] Generated text Gb2 is generated by artificial intelligence 3 using the following as input information I: product characteristics entered by the user in the first display area 51s, the product target entered in the first display area 51a, and the product target insight entered in the first display area 51b. Generated text Gb2 represents the evaluation by artificial intelligence 3 of the product target insight entered by the user in the first display area 51b, based on predetermined evaluation criteria. The predetermined evaluation criteria are, for example, "empathy and discoverability." Generated text Gb2 is, for example, "Evaluation result: The given insight is a 'correct insight'. Reason for evaluation: Empathy: The target group, people in their 20s and 30s, have a high interest in health and beauty, so their desire for nutritious and convenient food is highly relatable. Discoverability: The presented insight can be said to be discoverable. Many people may think they don't have time for breakfast, but the point that they "want to eat a nutritious meal in the morning" implies a desire to obtain nutrients from real food rather than protein supplements." The sentence is: "

[0094] The user may modify the target insights for the product entered in the first display area 51b, based on the evaluation of the generated text Gb2. Next, the explanatory text Tc contains the sentence, "We will create a concept using the elements we have set so far." When the user presses the suggestion button 531 on the request unit 53c via the input device 21, the generated text Gc1 related to the product concept is displayed in the second display area 52c.

[0095] The generated text Gc1 is generated by artificial intelligence 3 using the following input information I: the product characteristics entered by the user in the first display area 51s, the product target entered in the first display area 51a, and the product target insights entered in the first display area 51b. The generated text Gc1 represents a candidate product concept proposed by artificial intelligence 3. For example, the generated text Gc1 is the following sentence: "Concept candidate 1: Nutritious, hassle-free healthy food Concept candidate 2: Protect your family's health with just one serving Concept candidate 3: Easy and healthy for busy people."

[0096] Next, the user enters the product concept into the first display area 51c. The user may copy at least a portion of the generated text Gc1 displayed in the second display area 52c to the first display area 51c. The user may add, modify, or delete parts of the text copied to the first display area 51c. For example, the user copies a portion of the generated text Gc1, modifies it further, and enters the text "Concept: Nutritious, hassle-free tofu steak" into the first display area 51c.

[0097] In this way, the user can create multiple elements for determining the product concept, as well as the product concept itself, by interacting with the artificial intelligence 3 using the support system 100. In the process of creating the product concept, the user can obtain at least one of the following from the artificial intelligence 3: a suggestion, an indication, or an evaluation. Therefore, by using the support system 100, the user can receive support from the artificial intelligence 3 when thinking about various things.

[0098] (1b) When any of the buttons included in the request unit 53 is pressed, the processor 11 of the support device 1 executes the process shown in Figure 6. As a result, the generated statement G generated by the artificial intelligence 3 based on the input information I is displayed in the second display area 52.

[0099] With this configuration, the user can obtain the generated text G by pressing any of the buttons included in the request unit 53, without having to create the request (i.e., prompt) to send to the artificial intelligence 3 themselves. Therefore, the user can interact with the artificial intelligence 3 efficiently.

[0100] (1c) When the processor 11 is displaying a generated statement G in the second display area 52 and wants to display a generated statement G generated based on a new instruction input operation in the second display area 52, it displays the new generated statement G in the second display area 52 instead of the displayed generated statement G.

[0101] With this configuration, older generated sentences G are not displayed in the second display area 52, and only the latest generated sentences G are displayed. Therefore, the visibility of the generated sentences G displayed in the second display area 52 can be improved.

[0102] (1d) On screen S, the first display area 51 and the second display area 52 are arranged side by side. On screen S, both the first display area 51 and the second display area 52 are configured to be displayed simultaneously.

[0103] With this configuration, the user can view the generated text G displayed in the second display area 52 while the screen S is displayed on the display device 22, without scrolling the screen S, and consider what to input into the first display area 51. This allows the user to interact with the artificial intelligence 3 efficiently.

[0104] (1e) In step S100 of Figure 6, the processor 11 may include in the request instructions to extract relevant data, which is data related to the input information I, from the database 4 via the communication interface 14, and to make at least one of the following based on the input information I: suggestion, evaluation, and proposal, based on the relevant data. That is, in step S100 of Figure 6, the processor 11 may perform the processing shown in Figures 7 and 8.

[0105] With this configuration, suggestions, suggestions, and evaluations based on objective, relevant data can be made for the input information I entered into the first display area 51. As a result, the user can obtain more effective suggestions, suggestions, and evaluations from the artificial intelligence 3.

[0106] (1f) The processor 11 may generate natural language sentences that describe the numerical data contained in the extracted related data. The request may also include instructions for the processor 11 to make at least one of the following based on the generated sentences: suggestions, indications, and evaluations based on the input information I.

[0107] With this configuration, the natural language text describing the numerical data can be generated in less time than if AI 3 were to generate it, because the processor 11, rather than AI 3, creates the text. In addition, the content of the text describing the numerical data can be made more stable than if AI 3 were to generate it. As a result, the user can interact with AI 3 more efficiently.

[0108] (1g) The user can set a personality for the artificial intelligence 3 by operating the selection operation unit 54. With this configuration, the quality of the generated text G produced by artificial intelligence 3 can be adjusted based on the personality set for artificial intelligence 3.

[0109] [1-4. Correspondence between terms] In the above embodiment, the processor 11 corresponds to an example of a control unit, and the communication interface 14 corresponds to an example of a communication unit. Pressing any of the buttons included in the request unit 53 corresponds to an example of an instruction input operation.

[0110] [2. Other Embodiments] While embodiments of this disclosure have been described above, it goes without saying that this disclosure is not limited to the embodiments described above and can take various forms.

[0111] (2a) In the above embodiment, if a generated statement G is displayed in the second display area 52, the processor 11 deletes the generated statement G displayed in the second display area 52 in S120. However, the processor 11 may delete the generated statement G from the second display area 52 after saving the generated statement G as history in the storage 13. When the processor 11 receives a predetermined input operation, it may display the history of generated statements G saved in the storage 13 in the second display area 52 again, instead of other generated statements G displayed in the second display area 52. A predetermined input operation is, for example, the user pressing a history button located near the second display area 52 via the input device 21.

[0112] Multiple history entries of generated statements G are stored in storage 13. The generated statement G displayed again in the second display area 52 may be one selected by the user from multiple history entries. The generated statement G displayed again in the second display area 52 may be the generated statement G corresponding to the history entry immediately before or immediately after the currently displayed generated statement G.

[0113] (2b) In the above embodiment, the first display area 51 and the second display area 52 are arranged side by side on the support page 50. However, the first display area 51 and the second display area 52 do not have to be arranged side by side. For example, the first display area 51 and the second display area 52 may be arranged vertically. The first display area 51 and the second display area 52 may be arranged adjacent to each other or spaced apart. Other objects may be placed between the first display area 51 and the second display area 52.

[0114] (2c) In the above embodiment, the instruction input operation is the operation of pressing any of the buttons on the request unit 53 via the input device 21. However, the instruction input operation is not limited to this. For example, the instruction input operation may be an operation of directly instructing the artificial intelligence 3 via the input device 21 to process the input information I. The processing of the input information I may be at least one of proposal, suggestion, and evaluation.

[0115] (2d) In the above embodiment, the support page 50 shown in Figure 3 shows four first display areas 51s, 51a, 51b, and 51c as the first display area 51. Three second display areas 52a, 52b, and 52c are shown as the second display area 52. Three request areas 53a, 53b, and 53c are shown as the request area 53. Two selection operation areas 54a and 54b are shown as the selection operation area 54. Four explanatory texts Ts, Ta, Tb, and Tc are shown as the explanatory text T.

[0116] However, the number of the first display area 51, the second display area 52, and the request section 53 is not limited to these, and there should be at least one of each. The number of selection operation sections 54 and explanatory text T may be one or more. The selection operation sections 54 and explanatory text T may not be provided at all.

[0117] (2e) As shown in Figure 9, the support page 50 may further include at least one of the following: an image generation button 61, a summary button 62, and an output button 63. The image generation button 61 requests the artificial intelligence 3 to generate an image based on the input information I that has already been entered, and displays the image generated by the artificial intelligence 3 on the image display unit 611.

[0118] When the image generation button 61 is pressed, the processor 11 sends a request signal to the artificial intelligence 3 via the communication interface 14 and the input device 21 of the user terminal 2, requesting that the artificial intelligence generate an image based on at least one of the input information I that has already been input. When the processor 11 receives an image corresponding to the request from the artificial intelligence 3, it displays the image on the image display unit 611. For example, when the image generation button 61 is pressed, an image based on the product concept, which is input information I input into the first display area 51c in the usage example described above, is displayed on the image display unit 611.

[0119] The summary button 62 requests the artificial intelligence 3 to generate a summary of the input information I that has already been entered, and displays the summary generated by the artificial intelligence 3 on the summary display unit 621. An example of a summary is one in which the concept and multiple elements for creating the concept, and the input information I corresponding to each of the concept and multiple elements, are summarized within a predetermined number of characters, as in the usage example described above.

[0120] When the summary button 62 is pressed, the processor 11 sends a request signal to the artificial intelligence 3 via the communication interface 14 and the input device 21 of the user terminal 2, requesting that the artificial intelligence generate a summary of the input information I that has already been entered. When the processor 11 receives a summary corresponding to the request from the artificial intelligence 3, it displays the summary on the summary display unit 621. For example, when the summary button 62 is pressed, the summary display unit 621 displays a table summarizing the product target as input information I entered in the first display area 51a, the product target insight as input information I entered in the first display area 51b, and the product concept as input information I entered in the first display area 51c, as in the usage example described above. The input information I is not limited to the product target, insight, and concept; it may also include other information. Other information may be included in the summary.

[0121] The output button 63 outputs a summary of the input information I that has already been entered to the output file 631. The summary output to the output file 631 may be obtained by acquiring the information displayed on the summary display unit 621, or by requesting the artificial intelligence 3 to generate a new summary based on the input information I. The output file 631 may also include the image displayed on the image display unit 611.

[0122] For example, when the output button 63 is pressed, the processor 11 outputs the image displayed on the image display unit 611 and the content displayed on the summary display unit 621 in a predetermined format via the communication interface 14 and the input device 21 of the user terminal 2. For example, when the output button 63 is pressed, an output file 631 is output in the format shown in Figure 10, as a file summarizing the product's target, insights, concept, image, and other information in the usage example described above. The output file 631 can be used as a creative brief in the advertising field.

[0123] Figure 9 shows an example of screen S in which the image generation button 61, image display unit 611, summary button 62, summary display unit 621, and output button 63 are displayed. (2f) In the above embodiment, the procedure for creating a product concept called "○○ Tofu" was described as a specific example of the use of the support system 100. However, the use of the support system 100 is not limited to this. The support system 100 may be used to create a concept for any product or service. The support system 100 may be used to create various elements other than a product or service concept. The support system 100 may be used to support various thoughts that the user engages in, not limited to products or services. For example, the support system 100 may be used to create an organization's management philosophy or purpose. In this case, the user may input information about the organization's customers, the organization's history, etc., as input information I.

[0124] (2g) Multiple functions of one component in the above embodiment may be realized by multiple components, or one function of one component may be realized by multiple components. Multiple functions of multiple components may be realized by one component, or one function realized by multiple components may be realized by one component. Some of the configurations of the above embodiment may be omitted. At least some of the configurations of the above embodiment may be added to or replaced with the configurations of other above embodiments.

[0125] (2h) The present disclosure can be implemented in various forms other than the support device described above. For example, it can be implemented in the form of a system in which the support device is a component, a computer program for causing a computer to function as the support device, a non-transitional physical recording medium such as a semiconductor memory on which the computer program is recorded, a support method, and so on.

[0126] [Technical Concept Disclosed in This Specified Specification] [Item 1] It is a support device, A control unit configured to cause a display device to display a screen including a first display area and a second display area, A communication unit configured to communicate with artificial intelligence, Equipped with, The control unit, Each time an information input operation is performed on the first display area via an input device configured to accept user input operations, the input information, which is the information entered through the information input operation, is displayed on the first display area. Each time an instruction input operation is performed via the input device to instruct processing of the input information, a request signal is transmitted to the artificial intelligence via the communication unit in accordance with the instruction input operation, requesting at least one of the proposal, suggestion, and evaluation based on the input information; a generated sentence relating to at least one of the proposal, suggestion, and evaluation generated by the artificial intelligence is received as a response to the request signal; and the received generated sentence is displayed in the second display area. Execute, When the first generated statement, as the generated statement, is displayed in the second display area, and a second generated statement, as the generated statement, generated based on a new instruction input operation, is to be displayed in the second display area, the second generated statement is to be displayed in the second display area in place of the displayed first generated statement. Support equipment.

[0127] [Item 2] The support device described in item 1, The aforementioned communication unit is further configured to communicate with a database, The control unit is configured to extract related data, which is data related to the input information, from the database via the communication unit when transmitting the request signal to the artificial intelligence. The request signal includes a signal that requests the artificial intelligence to make at least one of the proposal, suggestion, and evaluation based on the input information, taking into account the relevant data. Support equipment.

[0128] [Item 3] The support device described in item 2, The aforementioned input information is related to marketing, The aforementioned related data includes marketing data, Support equipment.

[0129] [Item 4] A support device as described in item 2 or item 3, The control unit is configured to acquire multiple marketing-related data from the database, calculate the similarity between each of the multiple data and the input information, and extract at least one data with a high similarity from the multiple data as the related data. Support equipment.

[0130] [Item 5] A support device described in any one of items 2 to 4, The control unit is configured to generate natural language sentences that describe the numerical data included in the related data. The request signal includes a signal that requests the artificial intelligence to make at least one of the proposal, suggestion, and evaluation, taking the text into consideration. Support equipment.

[0131] [Item 6] A support device described in any one of items 1 through 5, The control unit is configured to display both the first display area and the second display area simultaneously on the screen. Support equipment.

[0132] [Item 7] A support device described in any one of items 1 through 6, The aforementioned artificial intelligence is configured to accept settings related to personality, The control unit is configured to set the selected personality of the artificial intelligence to the artificial intelligence each time a selection input operation is performed via the input device to select the personality of the artificial intelligence. Support equipment.

[0133] [Item 8] A support device described in any one of items 1 through 7, The aforementioned input information is information about a product or service. Support equipment.

[0134] [Item 9] The support device described in item 8, The aforementioned goods or services are provided by the organization, The request signal includes a signal requesting the artificial intelligence to make at least one of the proposals, suggestions, and evaluations relating to the value proposition of the organization to its customers through the goods or services, Support equipment.

[0135] [Item 10] A computer-based assistance method, To display a screen including a first display area and a second display area on a display device, Communicating with artificial intelligence, Includes, To display the above means, Each time an information input operation is performed on the first display area via an input device configured to accept user input operations, the input information, which is the information entered through the information input operation, is displayed on the first display area. Each time an instruction input operation is performed via the input device to instruct processing of the input information, a request signal is transmitted to the artificial intelligence requesting at least one of the proposal, suggestion, and evaluation based on the input information in accordance with the instruction input operation, a generated sentence relating to at least one of the proposal, suggestion, and evaluation generated by the artificial intelligence is received as a response to the request signal, and the received generated sentence is displayed in the second display area. Includes, Displaying the generated statement in the second display area includes, when the first generated statement is displayed in the second display area, and a second generated statement generated based on a new instruction input operation is to be displayed in the second display area, displaying the second generated statement in the second display area instead of the displayed first generated statement. How to help.

[0136] [Item 11] A computer program that causes a computer to perform the support methods described in item 10. [Explanation of Symbols]

[0137] 1...Support device, 3...Artificial intelligence, 11...Processor, 14...Communication interface, 21...Input device, 22...Display device, 51, 51a, 51b, 51c, 51s...First display area, 52, 52a, 52b, 52c...Second display area, 53, 53a, 53b, 53c...Request section, 531...Suggestion button, 532...Indication button, 533...Evaluation button, G, Ga1, Ga2, Gb1, Gb2, Gc1...Generated text, I...Input information, S...Screen.

Claims

1. It is a support device, A control unit configured to cause a display device to display a screen including a first display area and a second display area, A communication unit configured to communicate with artificial intelligence, Equipped with, The control unit, Each time an information input operation is performed on the first display area via an input device configured to accept user input operations, the input information, which is the information entered through the information input operation, is displayed on the first display area. Each time an instruction input operation is performed via the input device to instruct processing of the input information, a request signal is transmitted to the artificial intelligence via the communication unit in accordance with the instruction input operation, requesting at least one of the proposal, suggestion, and evaluation based on the input information; a generated sentence relating to at least one of the proposal, suggestion, and evaluation generated by the artificial intelligence is received as a response to the request signal; and the received generated sentence is displayed in the second display area. Execute, When the first generated statement, as the generated statement, is displayed in the second display area, and a second generated statement, as the generated statement, generated based on a new instruction input operation, is to be displayed in the second display area, the second generated statement is to be displayed in the second display area in place of the displayed first generated statement. Support equipment.

2. The support device according to claim 1, The aforementioned communication unit is further configured to communicate with a database, The control unit is configured to extract related data, which is data related to the input information, from the database via the communication unit when transmitting the request signal to the artificial intelligence. The request signal includes a signal that requests the artificial intelligence to make at least one of the proposal, suggestion, and evaluation based on the input information, taking into account the relevant data. Support equipment.

3. The support device according to claim 2, The aforementioned input information is related to marketing, The aforementioned related data includes marketing data, Support equipment.

4. The support device according to claim 3, The control unit is configured to acquire multiple marketing-related data from the database, calculate the similarity between each of the multiple data and the input information, and extract at least one data with a high similarity from the multiple data as the related data. Support equipment.

5. The support device according to claim 3, The control unit is configured to generate natural language sentences that describe the numerical data included in the related data. The request signal includes a signal that requests the artificial intelligence to make at least one of the proposal, suggestion, and evaluation, taking the text into consideration. Support equipment.

6. The support device according to claim 1, The control unit is configured to display both the first display area and the second display area simultaneously on the screen. Support equipment.

7. The support device according to claim 1, The aforementioned artificial intelligence is configured to accept settings related to personality, The control unit is configured to set the selected personality of the artificial intelligence to the artificial intelligence each time a selection input operation is performed via the input device to select the personality of the artificial intelligence. Support equipment.

8. The support device according to claim 1, The aforementioned input information is information about a product or service. Support equipment.

9. The support device according to claim 8, The aforementioned goods or services are provided by the organization, The request signal includes a signal requesting the artificial intelligence to make at least one of the proposals, suggestions, and evaluations relating to the value proposition of the organization to its customers through the goods or services, Support equipment.

10. A computer-based assistance method, To display a screen including a first display area and a second display area on a display device, Communicating with artificial intelligence, Includes, To display the above means, Each time an information input operation is performed on the first display area via an input device configured to accept user input operations, the input information, which is the information entered through the information input operation, is displayed on the first display area. Each time an instruction input operation is performed via the input device to instruct processing of the input information, a request signal is transmitted to the artificial intelligence requesting at least one of a proposal, suggestion, and evaluation based on the input information in accordance with the instruction input operation, a generated sentence relating to at least one of the proposal, suggestion, and evaluation generated by the artificial intelligence is received as a response to the request signal, and the received generated sentence is displayed in the second display area. Includes, Displaying the generated statement in the second display area includes, when the first generated statement is displayed in the second display area, and a second generated statement generated based on a new instruction input operation is to be displayed in the second display area, displaying the second generated statement in the second display area instead of the displayed first generated statement. How to help.

11. A computer program for causing a computer to execute the support method described in claim 10.

Images