Business support devices, programs, know-how utilization systems, and business support methods

Abstract

This enables output control based on the application of know-how. [Solution] The business support device 20, upon receiving an input 51 of a task related to a target task from the user, provides the input 51 to a model 24 that has learned know-how 25 related to multiple tasks, adjusts the randomness of the output from the model 24 according to the content of the input 51, obtains information on solutions to the task that utilize the know-how 25 from the model 24, and outputs the obtained solution information to the user. The model 24 is, for example, a generative artificial intelligence.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses creating second-level script data based on first-level script data and outputting a lecture including voice that voices the text data of the second-level script data and video of an avatar instructor.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In Patent Document 1, output control based on the application target of know-how has not been studied.

[0005] An object of the present disclosure is to enable output control based on the application target of know-how, such as adjusting the output manner from a generative AI according to what kind of business the learned know-how of the generative AI is utilized for. "AI" is an abbreviation for artificial intelligence.

Means for Solving the Problems

[0006] The business support device according to the present disclosure, when receiving an input of a problem related to a target business from a user, gives the input to a model that has learned know-how related to a plurality of businesses, and adjusts the randomness of the output from the model according to the content of the input, acquires information on a solution utilizing the know-how for the problem from the model, The acquired information of the solution is output to the user. It is equipped with a control unit.

[0007] The business support methods related to this disclosure are as follows: When a computer receives input from a user regarding a task related to the target task, it provides this input to a model that has learned know-how related to multiple tasks, and adjusts the randomness of the output from the model according to the content of the input. The computer obtains information from the model regarding a solution to the problem that utilizes the know-how, The computer outputs the acquired solution information to the user. Includes. [Effects of the Invention]

[0008] According to this disclosure, output control based on the scope of application of the know-how becomes possible. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows the configuration of the know-how utilization system according to the embodiment of this disclosure. [Figure 2] This is a block diagram showing the configuration of a business support device according to an embodiment of this disclosure. [Figure 3] This is a flowchart showing the operation of the business support device according to the embodiment of this disclosure. [Modes for carrying out the invention]

[0010] Hereinafter, one embodiment of this disclosure will be described with reference to the figures.

[0011] In each figure, identical or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate.

[0012] Referring to Figure 1, the configuration of the know-how utilization system 10 according to this embodiment will be described.

[0013] The know-how utilization system 10 comprises a business support device 20 and a terminal device 30. Although Figure 1 shows multiple terminal devices, for the sake of explanation, these terminal devices will be described as a single terminal device 30.

[0014] The business support device 20 is a computer, such as a server, belonging to a cloud computing system or other computing system, installed in a facility such as a data center. The terminal device 30 is a mobile device such as a mobile phone, smartphone, or tablet, or a PC, used by the user 11. "PC" is an abbreviation for personal computer.

[0015] The business support device 20 can communicate with the terminal device 30 via the network 40. The network 40 includes the Internet, at least one WAN, at least one MAN, or any combination thereof. "WAN" is an abbreviation for wide area network. "MAN" is an abbreviation for metropolitan area network. The network 40 may also include at least one wireless network, at least one optical network, or any combination thereof. The wireless network is, for example, an ad hoc network, a cellular network, a wireless LAN, a satellite communication network, or a terrestrial microwave network. "LAN" is an abbreviation for local area network.

[0016] The outline of this embodiment will be described with reference to Figures 1 and 2.

[0017] When the business support device 20 receives an input 51 of an issue regarding a target business from the user 11 via the terminal device 30, it provides the input 51 to a model 24 that has learned know-how 25 regarding a plurality of businesses, and adjusts the randomness of the output from the model 24 according to the content of the input 51. The know-how 25 refers to specific or specialized knowledge, techniques, methods, or information. The know-how 25 is typically transmitted by explanations using words, images, or actions. Examples of the application targets of the know-how 25 include operations such as screwing or assembly, operations of applications or software, or procedures for performing a business, but the application targets are not limited to these. The business support device 20 acquires solution information 52 from the model 24. The solution information 52 is information on a solution that utilizes the know-how 25 for an issue. The business support device 20 outputs the acquired solution information 52 to the user 11 via the terminal device 30.

[0018] According to the present embodiment, the way of output from the model 24 can be adjusted according to how the learned know-how 25 of the model 24 is utilized in what kind of business. That is, output control based on the application target of the know-how 25 becomes possible.

[0019] The model 24 is, for example, a generative AI such as an LLM, and outputs text corresponding to a prompt based on an input of the prompt which is an instruction from the user 11. "LLM" is an abbreviation of large language model. In addition to or instead of text, the model 24 may output information in a form other than text, such as an image.

[0020] For example, when user 11 inputs a prompt including a task into terminal device 30, terminal device 30 transmits the input prompt to business support device 20. When business support device 20 receives the prompt from terminal device 30, it provides the received prompt to model 24 as input 51, and adjusts the randomness of the output from model 24 by adjusting the temperature of the generative AI according to the content of the received prompt. Here, the temperature of the generative AI is one of the parameters that control the behavior of the generative AI, and is related to the randomness or creativity of the information generated as described later. Business support device 20 acquires, as solution information 52, text including a solution corresponding to the prompt from model 24. Business support device 20 transmits the acquired text to terminal device 30. When terminal device 30 receives the text, it displays the received text on the screen or outputs it as audio.

[0021] Knowledge 25 is stored and learned as text, electronic documents, audio, images, or any combination thereof. Knowledge 25 includes the knowledge obtained by veterans or experts in a specific field, practical techniques or methods cultivated through experience in that field, or all of these.

[0022] For example, assume that the minimum value of the temperature of the generative AI is 0 and the maximum value is 2, and the smaller the value, the more precise the output, and the larger the value, the more creative the output. That is, the closer the temperature of the generative AI is to 0, the more limited the range of knowledge 25 applied by model 24, and the less likely it is that serendipity or diversity is included in the output from model 24. On the other hand, the closer the temperature of the generative AI is to 2, the more the range of knowledge 25 applied by model 24 is expanded, and the more likely it is that serendipity or diversity is included in the output from model 24. When the temperature of the generative AI is set high, tricky things rather than those used by everyone may be forcibly selected from knowledge 25.

[0023] As an example, let's assume User 11 is an employee of a vehicle manufacturer. Let's assume the "specific field" is vehicle development. Vehicle rigidity design relates to quality or safety. Exterior and interior design relates to creativity. Designing functions that are not essential to the vehicle's functionality relates to entertainment or creativity. When User 11 inputs a question about vehicle rigidity design as a prompt, the business support device 20 determines that the content of the prompt relates to quality or safety. Then, the business support device 20 sets the temperature of the generative AI to 0 or a value close to 0. On the other hand, when User 11 inputs a question about exterior or interior design, or the design of functions that are not essential to the vehicle's functionality as a prompt, the business support device 20 determines that the content of the prompt relates to entertainment or creativity. Then, the business support device 20 sets the temperature of the generative AI to 1 or higher. In this way, the rigor or creativity of the output can be controlled according to the development target.

[0024] As another example, suppose user 11 is a software developer. Let's say the "specific field" is the development of entertainment applications such as games. In this example, although the application itself is related to entertainment, it also needs to be of good software quality. Therefore, as in the example above, the business support device 20's judgment changes depending on what kind of question user 11 inputs as a prompt. If the business support device 20 determines that the content of the prompt relates to quality or safety, it sets the temperature of the generative AI to 0 or a value close to 0. On the other hand, if the business support device 20 determines that the content of the prompt relates to entertainment or creativity, it sets the temperature of the generative AI to 1 or higher. Any setting method can be used to set the temperature, such as assigning a fixed numerical value according to the judgment result, or assigning an adaptive temperature according to the weight or ratio of quality or safety to entertainment or creativity.

[0025] When adjusting the temperature of a generative AI, criteria other than whether the prompt relates to quality or safety, or to entertainment or creativity, may be used. For example, the generative AI temperature may be set low when a question is entered about a procedure-defined task. On the other hand, the generative AI temperature may be set high when a question is entered to improve a process. The generative AI temperature may also be set high when a question is entered about exceptional cases, things that humans would not normally think of, or things whose feasibility is uncertain.

[0026] If diversity parameters such as dominant hand, gender, or country or region have been learned along with Know-how 25, the generative AI's "temperature" may be set higher for questions that include conditions not covered by the learned parameters. For example, when learning a certain piece of knowledge, if it is known what kind of people that knowledge should be applied to, those attributes can be learned as diversity parameters, and the generative AI's "temperature" can be set higher only for questions from people with different attributes.

[0027] The business support device 20 may further adjust the randomness of the output from model 24 based on department information 53. Department information 53 is information about the department within the organization that is responsible for the target business. Alternatively, department information 53 is information about the department within the organization to which user 11 belongs.

[0028] If user 11 inputs tasks while participating in a meeting, the business support device 20 may adjust the randomness of the output from model 24 based on the meeting information 54. The meeting information 54 is information about the meeting that user 11 is participating in, such as the meeting name or agenda. For example, if the meeting is a brainstorming session, the temperature of the generative AI may be set higher than in other cases. If the meeting is an audio or video conference, a chatbot operating on the business support device 20 may blend in with the meeting participants and automatically recognize user 11's statements as prompts without going through the terminal device 30.

[0029] Referring to Figure 2, the configuration of the business support device 20 according to this embodiment will be described.

[0030] The business support device 20 comprises a control unit 21, a storage unit 22, and a communication unit 23.

[0031] The control unit 21 includes at least one processor, at least one programmable circuit, at least one dedicated circuit, or any combination thereof. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. "CPU" is an abbreviation for central processing unit. "GPU" is an abbreviation for graphics processing unit. The programmable circuit is, for example, an FPGA. "FPGA" is an abbreviation for field-programmable gate array. The dedicated circuit is, for example, an ASIC. "ASIC" is an abbreviation for application specific integrated circuit. The control unit 21 controls each part of the business support device 20 and executes processes related to the operation of the business support device 20.

[0032] The storage unit 22 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or any combination thereof. The semiconductor memory is, for example, RAM, ROM, or flash memory. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read-only memory. RAM is, for example, SRAM or DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. ROM is, for example, EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read-only memory. Flash memory is, for example, SSD. "SSD" is an abbreviation for solid-state drive. Magnetic memory is, for example, HDD. "HDD" is an abbreviation for hard disk drive. The storage unit 22 functions, for example, as main memory, auxiliary memory, or cache memory. The memory unit 22 stores information used for the operation of the business support device 20 and information obtained through the operation of the business support device 20.

[0033] The communication unit 23 includes at least one communication module. The communication module is, for example, an interface compatible with a wired LAN communication standard such as Ethernet®, or an interface compatible with a wireless LAN communication standard such as IEEE 802.11. "IEEE" is an abbreviation for Institute of Electrical and Electronics Engineers. The communication module may also be an interface compatible with other standards such as USB, HDMI®, or Bluetooth®. "USB" is an abbreviation for Universal Serial Bus. "HDMI®" is an abbreviation for High-Definition Multimedia Interface. The communication unit 23 communicates with the terminal device 30. The communication unit 23 receives information used for the operation of the business support device 20 and transmits information obtained through the operation of the business support device 20.

[0034] The functions of the business support device 20 are realized by executing the program according to this embodiment on the processor acting as the control unit 21. In other words, the functions of the business support device 20 are realized by software. The program causes the computer to perform the operations of the business support device 20, thereby causing the computer to function as the business support device 20. That is, the computer functions as the business support device 20 by performing the operations of the business support device 20 according to the program.

[0035] The program can be stored on a non-temporary computer-readable medium. Examples of non-temporary computer-readable media include flash memory, magnetic recording devices, optical discs, magneto-optical recording media, or ROM. The program can be distributed, for example, by selling, transferring, or lending portable media such as SD cards, DVDs, or CD-ROMs containing the program. "SD" is an abbreviation for Secure Digital. "DVD" is an abbreviation for digital versatile disc. "CD-ROM" is an abbreviation for compact disc read only memory. The program may also be distributed by storing it in server storage and transferring it from the server to other computers. The program may also be provided as a program product.

[0036] A computer, for example, stores a program stored on a portable medium or a program transferred from a server in its main memory. Then, the computer reads the program stored in the main memory with its processor and executes the processing according to the read program. The computer may also read the program directly from the portable medium and execute the processing according to the program. The computer may also execute the processing according to the received program sequentially each time a program is transferred to the computer from a server. Processing may also be performed by a so-called ASP-type service, which does not transfer programs from the server to the computer, but realizes its function only through execution instructions and result retrieval. "ASP" is an abbreviation for application service provider. A program includes information used for processing by an electronic computer that is equivalent to a program. For example, data that is not a direct instruction to the computer but has the nature of defining the computer's processing falls under "equivalent to a program".

[0037] Some or all of the functions of the business support device 20 may be implemented by a programmable circuit or a dedicated circuit as the control unit 21. In other words, some or all of the functions of the business support device 20 may be implemented by hardware.

[0038] Referring to Figure 3, the operation of the business support device 20 according to this embodiment will be described. The operation described below corresponds to the business support method according to this embodiment. That is, the business support method according to this embodiment includes steps S1 to S5 shown in Figure 3.

[0039] When user 11 inputs a task related to the target task into terminal device 30, terminal device 30 transmits the task input 51 to the business support device 20. Control unit 21 receives input 51 from terminal device 30 via communication unit 23.

[0040] When the control unit 21 receives input 51 from the terminal device 30 via the communication unit 23, that is, when it receives input 51 of a task related to the target business from the user 11 via the terminal device 30, in S1 it determines whether the content of input 51 relates to quality or safety, or to entertainment or creativity.

[0041] If the control unit 21 determines that the content of input 51 relates to quality or safety, in S2 it reduces the randomness of the output from the model 24, which has learned know-how 25 related to multiple tasks. On the other hand, if the control unit 21 determines that the content of input 51 relates to entertainment or creativity, in S3 it increases the randomness of the output from the model 24. A table defining how to adjust randomness for each keyword such as "quality," "safety," "creativity," or "entertainment" may be pre-stored in the storage unit 22. The control unit 21 may refer to this table and automatically determine how to adjust randomness according to the keywords included in input 51.

[0042] The control unit 21 may further adjust the randomness of the output from the model 24 based on the department information 53. The department information 53 may be pre-stored in the storage unit 22. Alternatively, the control unit 21 may receive the department information 53 from the terminal device 30 via the communication unit 23.

[0043] For example, if the department responsible for the target task within the organization, or the department to which user 11 belongs, is named "Quality Control Department," the control unit 21 may reduce the randomness of the output from model 24. On the other hand, if the department responsible for the target task within the organization, or the department to which user 11 belongs, is named "Creative Design Department," the control unit 21 may increase the randomness of the output from model 24.

[0044] If user 11 inputs a task 51 while participating in a meeting, the control unit 21 may adjust the randomness of the output from model 24 based on the meeting information 54. The meeting information 54 may be pre-stored in the storage unit 22. Alternatively, the control unit 21 may receive the meeting information 54 from the terminal device 30 via the communication unit 23.

[0045] For example, if the name of the meeting in which user 11 is participating is "Safety Review Meeting," the control unit 21 may reduce the randomness of the output from model 24. On the other hand, if the name of the meeting in which user 11 is participating is "Entertainment Planning Meeting," the control unit 21 may increase the randomness of the output from model 24. The control unit 21 may monitor the conversation during the meeting and adaptively decide how to adjust the randomness according to the flow of the conversation.

[0046] In S2 or S3, the control unit 21 adjusts the randomness of the output from the model 24 according to the content of the input 51, and in S4, it provides the input 51 to the model 24 and obtains information on solutions to the problem using know-how 25 as solution information 52 from the model 24. Then, in S5, the control unit 21 transmits the obtained solution information 52 to the terminal device 30 via the communication unit 23. When the terminal device 30 receives the solution information 52 from the business support device 20, it outputs the received solution information 52 to the user 11 by displaying it on the screen or outputting it as sound.

[0047] As one variation, the control unit 21 may teach the model 24 how to adjust the randomness. In this variation, after the model 24's learning level reaches a certain standard, the control unit 21 has the model 24 adjust the randomness.

[0048] As another variation, the user 11 may be allowed to specify the randomness. In this variation, when the control unit 21 receives the randomness specification from the user 11 via the terminal device 30, in S2 or S3, instead of adjusting the randomness, it sets the randomness according to the specification. According to this variation, if the content of input 51 relates to quality or safety, manual setting can be used to avoid missetting.

[0049] As another variation, the control unit 21 may notify the user 11 of the adjusted randomness when outputting the solution information 52 to the user 11. That is, in S5, when the control unit 21 transmits the solution information 52 to the terminal device 30 via the communication unit 23, it may also transmit the adjusted randomness information to the terminal device 30. When the terminal device 30 receives the randomness information from the business support device 20, it visualizes the randomness of the output from model 24 to the user 11 by displaying the received randomness information on the screen or outputting it as sound.

[0050] In yet another modification, the control unit 21 may identify the user 11 via the terminal device 30. In this modification, the control unit 21 customizes the method of adjusting the randomness for the user 11. For example, information about the user 11's attributes is pre-stored in the storage unit 22, and the control unit 21 refers to this information to customize the method of adjusting the randomness for the user 11.

[0051] This disclosure is not limited to the embodiments described above. For example, two or more blocks described in the block diagram may be combined, or one block may be divided. Instead of executing two or more steps described in the flowchart in chronological order as described, they may be executed in parallel or in a different order, depending on the processing capacity of the device performing each step, or as necessary. Other modifications are possible without departing from the spirit of this disclosure.

[0052] Some embodiments of the present disclosure are described below. However, it should be noted that the embodiments of the present disclosure are not limited to these. [Note 1] When the system receives input from the user regarding a task related to the target task, it provides this input to a model that has already learned know-how related to multiple tasks, and adjusts the randomness of the output from the model based on the content of the input. Information on solutions to the aforementioned problems, utilizing the aforementioned know-how, is obtained from the aforementioned model. The acquired information of the solution is output to the user. A business support device equipped with a control unit. [Note 2] The control unit, when it determines that the content of the input is related to quality, reduces the randomness, as described in Appendix 1, for the business support device. [Note 3] The control unit determines that the content of the input is related to safety, and then reduces the randomness, as described in Appendix 1 or Appendix 2. [Note 4] The control unit, when it determines that the content of the input is related to entertainment, increases the randomness, as described in any one of the appendices 1 to 3, for the business support device. [Note 5] The control unit, when it determines that the content of the input is related to creativity, increases the randomness, the business support device according to any one of the appendices 1 to 4. [Note 6] The control unit adjusts the randomness based on information of the departments within the organization that are responsible for the target operations, as described in any one of the items in Appendix 1 to Appendix 5. [Note 7] The control unit adjusts the randomness based on information about the department to which the user belongs within the organization, as described in any one of the items in Appendix 1 to Appendix 6. [Note 8] If the user inputs the task while participating in a meeting, the control unit further adjusts the randomness based on the meeting information, as described in any one of Appendix 1 to Appendix 7 of the business support device. [Note 9] The control unit, The model is trained to learn how to adjust the randomness. A business support device according to any one of the appendices 1 to 8, wherein, after the learning level of the aforementioned model reaches a certain standard, the randomness is adjusted in the aforementioned model. [Note 10] The business support device according to any one of the appendices 1 to 9, wherein the control unit, upon receiving a specification of randomness from the user, sets the randomness according to the specification instead of adjusting it. [Note 11] The control unit notifies the user of the adjusted randomness when outputting information of the solution to the user, the business support device according to any one of the appendices 1 to 10. [Note 12] The control unit, Identify the aforementioned user, A business support device according to any one of the appendices 1 to 11, which customizes the method of adjusting the randomness for the user. [Note 13] The aforementioned model is a generative artificial intelligence, a business support device as described in any one of the items from Appendix 1 to Appendix 12. [Note 14] The control unit adjusts the randomness by adjusting the temperature of the generative artificial intelligence, as described in Appendix 13. [Note 15] A program that enables a computer to function as a business support device as described in any one of the items from Appendix 1 to Appendix 14. [Note 16] A business support device described in any one of the items from Appendix 1 to Appendix 14, The terminal device used by the aforementioned user, The input is transmitted to the business support device. The information of the aforementioned solution is received from the business support device. Terminal device and A know-how utilization system equipped with these features. [Note 17] When a computer receives input from a user regarding a task related to the target task, it provides this input to a model that has learned know-how related to multiple tasks, and adjusts the randomness of the output from the model according to the content of the input. The computer obtains information from the model regarding a solution to the problem that utilizes the know-how, The computer outputs the acquired solution information to the user. Business support methods including those mentioned above. [Note 18] The aforementioned adjustment is a business support method as described in Appendix 17, which includes reducing the randomness if it is determined that the content of the input relates to quality or safety. [Note 19] The aforementioned adjustment includes increasing the randomness if it is determined that the content of the input is related to entertainment or creativity, as described in Appendix 17 or Appendix 18 of the business support method. [Note 20] The aforementioned adjustment includes adjusting the randomness based on information of the department responsible for the aforementioned task within the organization, or information of the department to which the user belongs, as described in any one of the items in Appendix 17 to Appendix 19. [Explanation of Symbols]

[0053] 10. Know-how utilization system 11 users 20 Business support equipment 21 Control Unit 22 Memory section 23 Communications Department 24 Models 25 Know-how 30 Terminal devices 40 Networks 51 inputs 52 Solution information 53 Department information 54 Meeting Information

Claims

1. When the system receives input from the user regarding a task related to the target task, it provides this input to a model that has already learned know-how related to multiple tasks, and adjusts the randomness of the output from the model based on the content of the input. Information on solutions to the aforementioned problems, utilizing the aforementioned know-how, is obtained from the aforementioned model. The acquired information of the solution is output to the user. A business support device equipped with a control unit.

2. The business support device according to claim 1, wherein the control unit reduces the randomness when it determines that the content of the input is related to quality.

3. The business support device according to claim 1, wherein the control unit reduces the randomness when it determines that the content of the input is related to safety.

4. The business support device according to claim 1, wherein the control unit increases the randomness when it determines that the content of the input is related to entertainment.

5. The business support device according to claim 1, wherein the control unit increases the randomness when it determines that the content of the input is related to creativity.

6. The business support device according to claim 1, wherein the control unit further adjusts the randomness based on information of the department in the organization responsible for the target business.

7. The business support device according to claim 1, wherein the control unit further adjusts the randomness based on information about the department to which the user belongs within the organization.

8. The business support device according to claim 1, wherein if the user inputs the task while participating in a meeting, the control unit further adjusts the randomness based on the information of the meeting.

9. The control unit, The model is trained to learn how to adjust the randomness. The business support device according to claim 1, wherein, after the learning level of the model reaches a standard, the randomness is adjusted in the model.

10. The business support device according to claim 1, wherein the control unit, upon receiving a specification of randomness from the user, sets the randomness according to the specification instead of adjusting it.

11. The business support device according to claim 1, wherein the control unit notifies the user of the adjusted randomness when outputting information of the solution to the user.

12. The control unit, Identify the aforementioned user, The business support device according to claim 1, wherein the method of adjusting the randomness is customized for the user.

13. The aforementioned model is a generative artificial intelligence, as described in claim 1, for the business support device.

14. The business support device according to claim 13, wherein the control unit adjusts the randomness by adjusting the temperature of the generative artificial intelligence.

15. A program that causes a computer to function as a business support device according to any one of claims 1 to 14.

16. A business support device according to any one of claims 1 to 14, The terminal device used by the aforementioned user, The input is transmitted to the business support device. The information of the aforementioned solution is received from the business support device. Terminal device and A know-how utilization system equipped with these features.

17. When a computer receives input from a user regarding a task related to the target task, it provides this input to a model that has learned know-how related to multiple tasks, and adjusts the randomness of the output from the model according to the content of the input. The computer obtains information from the model regarding a solution to the problem that utilizes the know-how, The computer outputs the acquired solution information to the user. Business support methods including those mentioned above.

18. The business support method according to claim 17, wherein the adjustment includes reducing the randomness when it is determined that the content of the input relates to quality or safety.

19. The business support method according to claim 17, wherein the adjustment includes increasing the randomness when it is determined that the content of the input is related to entertainment or creativity.

20. The business support method according to claim 17, wherein the adjustment further includes adjusting the randomness based on information of the department in the organization responsible for the target business or information of the department to which the user belongs.

Images