Task assistance device, non-transitory computer-readable medium, know-how utilization system, and task assistance method

Abstract

A task assistance device (20) comprises a control unit (21) that, upon receiving an input (51) of a problem relating to a target task from a user, gives the input (51) to a model (24), which has learned know-how (25) about a plurality of tasks, adjusts the randomness of an output from the model (24), depending on the content of the input (51), acquires, from the model (24), solution information utilizing the know-how (25) to address the problem, and outputs the acquired solution information to the user. The model (24) is, for example, generative artificial intelligence.

Description

Business support device, non-transitory computer-readable medium, know-how utilization system, and business support method CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority from Japanese Patent Application No. 2024-150094, filed in Japan on August 30, 2024, the entire disclosure of which is incorporated herein by reference.

[0002] The present disclosure relates to a business support device, a program, a know-how utilization system, and a business support method.

[0003] Patent document 1 discloses that second level script data is created based on first level script data, and a lecture including a voice that speaks the text data of the second level script data and a video of an avatar lecturer is output.

[0004] Patent No. 7473270

[0005] In Patent Document 1, output control based on the target of application of know-how is not considered.

[0006] The purpose of this disclosure is to enable output control based on the application of know-how, such as adjusting the output from generative AI depending on the type of business for which the learned know-how of the generative AI is to be used. "AI" is an abbreviation for artificial intelligence.

[0007] The business support device according to the present disclosure includes a control unit that, upon receiving input of a problem related to a target business from a user, provides the input to a model that has been trained on know-how related to a plurality of businesses, adjusts the randomness of the output from the model depending on the content of the input, obtains information on a solution to the problem that utilizes the know-how from the model, and outputs the obtained information on the solution to the user.

[0008] The business support method disclosed herein includes the steps of: when a computer receives input of a problem related to a target business from a user, providing the input to a model that has been trained with know-how related to multiple businesses, and adjusting the randomness of the output from the model depending on the content of the input; the computer obtaining, from the model, information on a solution to the problem that utilizes the know-how; and the computer outputting the obtained information on the solution to the user.

[0009] According to the present disclosure, output control based on the target of application of know-how becomes possible.

[0010] While the present disclosure has been described with reference to exemplary embodiments, it is to be understood that the present disclosure is not limited to the disclosed exemplary embodiments and is not to be construed as limiting the scope of the present disclosure.

[0011] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings.

[0012] In each drawing, the same or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of the same or corresponding parts will be omitted or simplified as appropriate.

[0013] The configuration of a know-how utilization system 10 according to this embodiment will be described with reference to FIG.

[0014] The know-how utilization system 10 includes a business support device 20 and a terminal device 30. Although a plurality of terminal devices are shown in Fig. 1, for the sake of convenience, these terminal devices will be described as a single terminal device 30.

[0015] The business support device 20 is a computer such as a server that belongs to a cloud computing system or other computing system and is 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.

[0016] The business support device 20 can communicate with the terminal device 30 via a 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 include at least one wireless network, at least one optical network, or any combination thereof. The wireless network may be, 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.

[0017] The outline of this embodiment will be described with reference to FIGS.

[0018] When the business support device 20 receives an input 51 of a problem related to a target business from the user 11 via the terminal device 30, the business support device 20 provides the input 51 to a model 24 that has been trained with know-how 25 related to multiple businesses, and adjusts the randomness of the output from the model 24 depending on the content of the input 51. The know-how 25 refers to specific or specialized knowledge, technology, techniques, or information. The know-how 25 is typically conveyed through explanations using words, images, or actions. The know-how 25 can be applied to tasks such as screwing or assembly, operation of applications or software, or business procedures, but is 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 to the problem that utilizes the know-how 25. The business support device 20 outputs the acquired solution information 52 to the user 11 via the terminal device 30.

[0019] According to this embodiment, it is possible to adjust the way in which the model 24 outputs the know-how 25 learned by the model 24 depending on the type of business to which the know-how 25 is to be applied. In other words, it is possible to control the output based on the application target of the know-how 25.

[0020] Model 24 is a generative AI, such as an LLM, that outputs text corresponding to a prompt input from user 11. "LLM" stands for large language model. Model 24 may output information in a non-text format, such as an image, in addition to or instead of text.

[0021] For example, when the user 11 inputs a prompt including a problem into the terminal device 30, the terminal device 30 transmits the input prompt to the business assistance device 20. When the business assistance device 20 receives the prompt from the terminal device 30, it provides the received prompt as input 51 to the model 24 and adjusts the temperature of the generative AI according to the content of the received prompt, thereby adjusting the randomness of the output from the model 24. 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 generated information, as described below. The business assistance device 20 acquires text including a solution corresponding to the prompt from the model 24 as solution information 52. The business assistance device 20 transmits the acquired text to the terminal device 30. When the terminal device 30 receives the text, it displays the received text on a screen or outputs it as audio.

[0022] The know-how 25 is accumulated and learned as text, electronic documents, audio, images, or any combination thereof. The know-how 25 includes knowledge gained by veterans or experts in a particular field, practical techniques or methods cultivated through experience in that field, or all of these.

[0023] For example, the minimum value of the temperature of the generative AI is 0 and the maximum value is 2, with the smaller the value, the more strict the output, and the larger the value, the more creative the output. In other words, the closer the temperature of the generative AI is to 0, the more limited the range of know-how 25 applied by the model 24, making it less likely that serendipity or diversity will be included in the output from the model 24. On the other hand, the closer the temperature of the generative AI is to 2, the wider the range of know-how 25 applied by the model 24, making it more likely that serendipity or diversity will be included in the output from the model 24. If the temperature of the generative AI is set high, tricky know-how 25 may be forcibly selected from the know-how 25 rather than know-how that everyone uses.

[0024] As an example, assume that user 11 is an employee of a vehicle manufacturer. The "specific field" is vehicle development. The rigidity design of a vehicle relates to quality or safety. The exterior and interior design relates to creativity. The design of a function that is not essential to the vehicle's functions relates to entertainment or creativity. When user 11 inputs a question about the rigidity design of a vehicle as a prompt, the business assistance device 20 determines that the content of the prompt relates to quality or safety. The business assistance device 20 then 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 the exterior or interior design, or the design of a function that is not essential to the vehicle's functions, the business assistance device 20 determines that the content of the prompt relates to entertainment or creativity. The business assistance device 20 then sets the temperature of the generative AI to 1 or higher. In this way, the rigor or creativity of the output can be controlled depending on the development target.

[0025] As another example, assume that the user 11 is a software developer. The "specific field" is the development of entertainment applications such as games. In this example, although the application itself is entertainment-related, software quality is also required. Therefore, as in the above example, the determination of the business assistance device 20 changes depending on the question entered by the user 11 as a prompt. If the business assistance device 20 determines that the content of the prompt is related 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 assistance device 20 determines that the content of the prompt is related to entertainment or creativity, it sets the temperature of the generative AI to 1 or higher. The temperature can be set using any method, such as assigning a fixed value based on the determination result, or assigning an adaptive temperature based on the weight or ratio between quality or safety and entertainment or creativity.

[0026] The criterion for adjusting the temperature of the generative AI may be a different criterion from whether the prompt content is related to quality or safety, or whether it is related to entertainment or creativity. For example, when a question about a task with a set procedure is input, the temperature of the generative AI may be set low. On the other hand, when a question about improving a process is input, the temperature of the generative AI may be set high. When a question about an exceptional situation, something that humans would not normally think of, or something that is unclear whether it can be achieved, is input, the temperature of the generative AI may be set high.

[0027] If diversity parameters such as handedness, gender, or country or region have been learned along with know-how 25, the temperature of the generative AI may be set higher for questions that include conditions that do not fall under the learned parameters. For example, if it is known when learning a certain piece of knowledge what kind of attributes the knowledge should be applied to, it is possible to learn the attributes as diversity parameters and set the temperature of the generative AI higher only for questions from people with different attributes.

[0028] The business assistance device 20 may adjust the randomness of the output from the model 24 further based on the department information 53. The department information 53 is information about the department in charge of the target business within the organization. Alternatively, the department information 53 is information about the department to which the user 11 belongs within the organization.

[0029] When the user 11 inputs the task while participating in a meeting, the business support device 20 may adjust the randomness of the output from the model 24 further based on the meeting information 54. The meeting information 54 is information about the meeting in which the user 11 is participating, 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 if the meeting is not a brainstorming session. If the meeting is an audio conference or a video conference, a chatbot running on the business support device 20 may blend in with the participants of the meeting and automatically recognize the utterances of the user 11 as prompts without going through the terminal device 30.

[0030] The configuration of the task assistance device 20 according to this embodiment will be described with reference to FIG.

[0031] The business support device 20 includes a control unit 21 , a storage unit 22 , and a communication unit 23 .

[0032] 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 specific processing. "CPU" is an abbreviation for central processing unit. "GPU" is an abbreviation for graphics processing unit. An example of the programmable circuit is an FPGA. "FPGA" is an abbreviation for field-programmable gate array. An example of the dedicated circuit is an ASIC. "ASIC" is an abbreviation for application specific integrated circuit. The control unit 21 controls each part of the business assistance device 20 and executes processing related to the operation of the business assistance device 20.

[0033] 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, a RAM, a ROM, or a flash memory. "RAM" is an abbreviation for random access memory. "ROM" is an abbreviation for read only memory. RAM is, for example, an SRAM or a DRAM. "SRAM" is an abbreviation for static random access memory. "DRAM" is an abbreviation for dynamic random access memory. ROM is, for example, an EEPROM. "EEPROM" is an abbreviation for electrically erasable programmable read only memory. Flash memory is, for example, an SSD. "SSD" is an abbreviation for solid-state drive. Magnetic memory is, for example, an HDD. "HDD" is an abbreviation for hard disk drive. The storage unit 22 functions, for example, as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 22 stores information used in the operation of the business assistance device 20 and information obtained by the operation of the business assistance device 20 .

[0034] 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 (registered trademark), 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 be an interface compatible with other standards such as USB, HDMI (registered trademark), or Bluetooth (registered trademark). "USB" is an abbreviation for Universal Serial Bus. "HDMI (registered trademark)" 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 in the operation of the business assistance device 20 and transmits information obtained by the operation of the business assistance device 20.

[0035] The functions of the business assistance device 20 are realized by executing a program according to this embodiment on a processor serving as the control unit 21. That is, the functions of the business assistance device 20 are realized by software. The program causes a computer to execute the operations of the business assistance device 20, thereby causing the computer to function as the business assistance device 20. That is, the computer functions as the business assistance device 20 by executing the operations of the business assistance device 20 in accordance with the program.

[0036] The program can be stored on a non-transitory computer-readable medium. Examples of the non-transitory computer-readable medium include flash memory, magnetic recording devices, optical disks, magneto-optical recording media, and ROMs. The program can be distributed by selling, transferring, or lending portable media such as SD cards, DVDs, or CD-ROMs that store 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 can also be distributed by storing it in the storage of a server and transferring it from the server to another computer. The program can also be provided as a program product.

[0037] A computer temporarily stores a program stored on a portable medium or transferred from a server in its main storage device. The computer then reads the program stored in the main storage device with its processor and executes processing in accordance with the read program. The computer may also read the program directly from the portable medium and execute processing in accordance with the program. The computer may also execute processing in accordance with the received program each time a program is transferred from the server to the computer. Processing may also be executed using a so-called ASP-type service that realizes functions simply by issuing execution instructions and obtaining results, without transferring the program from the server to the computer. "ASP" is an abbreviation for application service provider. A program is information used for processing by a computer and includes something equivalent to a program. For example, data that is not a direct instruction to a computer but has properties that define computer processing falls under the category of "something equivalent to a program."

[0038] Some or all of the functions of the business assistance device 20 may be realized 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 assistance device 20 may be realized by hardware.

[0039] The operation of the task assistance device 20 according to this embodiment will be described with reference to Fig. 3. The operation described below corresponds to the task assistance method according to this embodiment. That is, the task assistance method according to this embodiment includes steps S1 to S5 shown in Fig. 3.

[0040] When the user 11 inputs an issue related to a target task into the terminal device 30, the terminal device 30 transmits the issue input 51 to the task assistance device 20. The control unit 21 receives the input 51 from the terminal device 30 via the communication unit 23.

[0041] 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, it determines in S1 whether the content of the input 51 is related to quality or safety, or to entertainment or creativity.

[0042] When the control unit 21 determines that the content of the input 51 is related to quality or safety, it reduces the randomness of the output from the model 24 that has learned know-how 25 related to multiple businesses in S2. On the other hand, when the control unit 21 determines that the content of the input 51 is related to entertainment or creativity, it increases the randomness of the output from the model 24 in S3. A table that defines how to adjust the randomness for each keyword, such as "quality," "safety," "creative," or "entertainment," may be stored in advance in the storage unit 22. The control unit 21 may refer to this table and automatically determine how to adjust the randomness depending on the keyword included in the input 51.

[0043] The control unit 21 may adjust the randomness of the output from the model 24 further based on the department information 53. The department information 53 may be stored in advance 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.

[0044] For example, if the name of the department in the organization responsible for the target work or the department to which the user 11 belongs is the "Quality Control Department," the control unit 21 may decrease the randomness of the output from the model 24. On the other hand, if the name of the department in the organization responsible for the target work or the department to which the user 11 belongs is the "Creative Design Department," the control unit 21 may increase the randomness of the output from the model 24.

[0045] When the user 11 inputs 51 the task while participating in a conference, the control unit 21 may adjust the randomness of the output from the model 24 further based on conference information 54. The conference information 54 may be pre-stored in the storage unit 22. Alternatively, the control unit 21 may receive the conference information 54 from the terminal device 30 via the communication unit 23.

[0046] For example, if the name of the meeting in which user 11 is participating is a "safety review meeting," the control unit 21 may decrease the randomness of the output from the model 24. On the other hand, if the name of the meeting in which user 11 is participating is an "entertainment planning meeting," the control unit 21 may increase the randomness of the output from the model 24. The control unit 21 may monitor the conversation during the meeting and adaptively determine how to adjust the randomness in accordance with the flow of the conversation.

[0047] In S2 or S3, the control unit 21 adjusts the randomness of the output from the model 24 depending on the content of the input 51, and then in S4, provides the input 51 to the model 24 and acquires information on a solution to the problem that utilizes the know-how 25 from the model 24 as solution information 52. Then, in S5, the control unit 21 transmits the acquired solution information 52 to the terminal device 30 via the communication unit 23. Upon receiving the solution information 52 from the business assistance device 20, the terminal device 30 outputs the received solution information 52 to the user 11 by displaying it on a screen or outputting it as audio.

[0048] As a modified example, the control unit 21 may cause the model 24 to learn how to adjust the randomness. In this modified example, the control unit 21 causes the model 24 to adjust the randomness after the learning level of the model 24 reaches a standard.

[0049] As another modification, the user 11 may be allowed to specify the randomness. In this modification, when the control unit 21 receives a specification of the randomness from the user 11 via the terminal device 30, the control unit 21 sets the randomness according to the specification instead of adjusting the randomness in S2 or S3. According to this modification, if the content of the input 51 is related to quality or safety, incorrect setting can be avoided by manual setting.

[0050] As yet 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, the control unit 21 may also transmit information about the adjusted randomness to the terminal device 30 when transmitting the solution information 52 to the terminal device 30 via the communication unit 23. Upon receiving the randomness information from the business assistance device 20, the terminal device 30 visualizes the randomness of the output from the model 24 to the user 11 by displaying the received randomness information on a screen or outputting it as audio.

[0051] As yet another modified example, the control unit 21 may identify the user 11 via the terminal device 30. In this modified example, the control unit 21 customizes the way in which randomness is adjusted for the user 11. For example, attribute information for the user 11 is stored in advance in the storage unit 22, and the control unit 21 refers to this information to customize the way in which randomness is adjusted for the user 11.

[0052] The present disclosure is not limited to the above-described embodiments. For example, two or more blocks shown in the block diagrams may be integrated, or one block may be divided. Two or more steps shown in the flowcharts may be executed in parallel or in a different order, instead of being executed in chronological order as described, depending on the processing capabilities of the device executing each step, or as needed. Other modifications are possible within the scope of the present disclosure.

[0053] Some embodiments of the present disclosure are exemplified below. However, it should be noted that the embodiments of the present disclosure are not limited to these. [Supplementary Note 1] A business assistance device including a control unit that, upon receiving an input of a problem related to a target business from a user, provides the input to a model that has learned know-how related to a plurality of businesses and adjusts randomness of an output from the model depending on the content of the input, acquires information on a solution to the problem that utilizes the know-how from the model, and outputs the acquired information on the solution to the user. [Supplementary Note 2] The business assistance device according to Supplementary Note 1, wherein the control unit reduces the randomness when determining that the content of the input is related to quality. [Supplementary Note 3] The business assistance device according to Supplementary Note 1 or Supplementary Note 2, wherein the control unit reduces the randomness when determining that the content of the input is related to safety. [Supplementary Note 4] The business assistance device according to any one of Supplements 1 to 3, wherein the control unit increases the randomness when determining that the content of the input is related to entertainment. [Supplementary Note 5] The business support device according to any one of Supplementary Notes 1 to 4, wherein the control unit increases the randomness when it determines that the content of the input is related to creativity. [Supplementary Note 6] The business support device according to any one of Supplementary Notes 1 to 5, wherein the control unit adjusts the randomness further based on information about a department in an organization that is in charge of the target task. [Supplementary Note 7] The business support device according to any one of Supplementary Notes 1 to 6, wherein the control unit adjusts the randomness further based on information about a department in an organization to which the user belongs. [Supplementary Note 8] The business support device according to any one of Supplementary Notes 1 to 7, wherein, when the user inputs the assignment while participating in a meeting, the control unit adjusts the randomness further based on information about the meeting. [Supplementary Note 9] The business support device according to any one of Supplementary Notes 1 to 8, wherein the control unit causes the model to learn how to adjust the randomness, and after a learning level of the model reaches a standard, causes the model to adjust the randomness.[Supplementary Note 10] The business assistance device according to any one of Supplementary Notes 1 to 9, wherein, upon receiving a designation of the randomness from the user, the control unit sets the randomness in accordance with the designation instead of adjusting the randomness. [Supplementary Note 11] The business assistance device according to any one of Supplementary Notes 1 to 10, wherein the control unit notifies the user of the adjusted randomness when outputting information on the solution to the user. [Supplementary Note 12] The business assistance device according to any one of Supplementary Notes 1 to 11, wherein the control unit identifies the user and customizes a manner of adjusting the randomness for the user. [Supplementary Note 13] The business assistance device according to any one of Supplementary Notes 1 to 12, wherein the model is a generative artificial intelligence. [Supplementary Note 14] The business assistance device according to Supplementary Note 13, wherein the control unit adjusts the randomness by adjusting a temperature of the generative artificial intelligence. [Supplementary Note 15] A program that causes a computer to function as the business assistance device according to any one of Supplementary Notes 1 to 14. [Supplementary Note 16] A know-how utilization system comprising: the business support device according to any one of Supplements 1 to 14; and a terminal device used by the user, the terminal device transmitting the input to the business support device and receiving the solution information from the business support device. [Supplementary Note 17] A business support method including: when a computer receives input of a problem related to a target business from a user, providing the input to a model that has learned know-how related to multiple businesses and adjusting randomness of an output from the model depending on the content of the input; the computer acquiring solution information for the problem that utilizes the know-how from the model; and the computer outputting the acquired solution information to the user. [Supplementary Note 18] The business support method according to Supplementary Note 17, wherein the adjusting includes decreasing the randomness when it is determined that the content of the input relates to quality or safety. [Supplementary Note 19] The business support method according to Supplementary Note 17 or Supplementary Note 18, wherein the adjusting includes increasing the randomness when it is determined that the content of the input relates to entertainment or creativity.[Supplementary Note 20] The business support method according to any one of Supplementary Note 17 to Supplementary Note 19, wherein the adjusting includes adjusting the randomness based further on information about a department in an organization that is in charge of the target business or information about a department to which the user belongs.

[0054] REFERENCE SIGNS LIST 10 Know-how utilization system 11 User 20 Business support device 21 Control unit 22 Storage unit 23 Communication unit 24 Model 25 Know-how 30 Terminal device 40 Network 51 Input 52 Solution information 53 Department information 54 Meeting information

Claims

1. A business support device having a control unit that, when it receives input from a user about a problem related to a target business, provides the input to a model that has been trained with know-how related to multiple businesses, adjusts the randomness of the output from the model depending on the content of the input, obtains information on a solution to the problem that utilizes the know-how from the model, and outputs the obtained information on the solution to the user.

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 security.

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

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

6. The business support device according to claim 1, wherein the control unit adjusts the randomness further based on information about a department in an organization that is in charge of the target business.

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

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

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

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

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

12. The business support device according to claim 1, wherein the control unit identifies the user and customizes the way in which the randomness is adjusted for the user.

13. The business support device according to claim 1, wherein the model is a generative artificial intelligence.

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 non-transitory computer-readable medium storing a program that causes a computer to function as the business support device according to any one of claims 1 to 14.

16. A know-how utilization system comprising: a business support device according to any one of claims 1 to 14; and a terminal device used by the user, which transmits the input to the business support device and receives the solution information from the business support device.

17. A business support method comprising: when a computer receives input from a user of a problem related to a target business, providing the input to a model that has been trained with know-how related to multiple businesses and adjusting the randomness of the output from the model depending on the content of the input; the computer obtaining information on a solution to the problem that utilizes the know-how from the model; and the computer outputting the obtained information on the solution to the user.

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

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

20. The business support method described in claim 17, wherein the adjusting step includes adjusting the randomness based further on information about the department within the organization that is responsible for the target business or information about the department to which the user belongs.

Images