Prompt generation device, prompt generation method, and program

Abstract

A prompt generation device according to the present invention comprises: an input information acquisition unit that acquires input information; an information search unit that searches a storage unit storing industrial machine information for industrial machine information pertaining to an industrial machine related to the input information; and a prompt generation unit that generates, on the basis of the result of search performed by the information search unit, a prompt to be transmitted to a generative AI device.

Description

Prompt generation device, prompt generation method, and program

[0001] The present disclosure relates to a prompt generation device, a prompt generation method, and a program.

[0002] Japanese Patent Application Laid-Open Publication No. 2023-058269 discloses an information processing system that uses a chatbot to respond to customer inquiries.

[0003] What is needed is a technique that can better assist users who have problems, questions, etc. related to industrial machinery.

[0004] The present invention aims to solve the above-mentioned problems.

[0005] A first aspect of the present disclosure is a prompt generation device comprising an input information acquisition unit that acquires input information, an information search unit that searches for industrial machinery information, which is information about industrial machinery related to the input information, from a memory unit in which the industrial machinery information is stored, and a prompt generation unit that generates a prompt to be sent to a generation AI device based on the search results by the information search unit.

[0006] A second aspect of the present disclosure is a prompt generation method executed by a computer, comprising: an input information acquisition step for acquiring input information; an information search step for searching industrial machinery information, which is information about industrial machinery related to the input information, from a memory unit in which the industrial machinery information is stored; and a prompt generation step for generating a prompt to be sent to a generation AI device based on the search results of the information search step.

[0007] A third aspect of the present disclosure is a program for causing a computer to execute the prompt generation method according to the second aspect.

[0008] FIG. 1 is a configuration diagram of a prompt generation system according to one embodiment. FIG. 2A is a diagram illustrating a standard question. FIG. 2B is a diagram illustrating a standard question. FIG. 3A is a diagram illustrating one template among a plurality of templates. FIG. 3B is a diagram illustrating a template different from that of FIG. 3A. FIG. 4A is a diagram illustrating a prompt generated by a prompt generation unit. FIG. 4B is a diagram illustrating a prompt different from that of FIG. 4A. FIG. 5 is a diagram illustrating a screen of a display unit on which a prompt and a response of a generation AI device to the prompt are displayed. FIG. 6 is a flowchart showing a prompt generation method according to one embodiment. FIG. 7 is a diagram illustrating a plurality of standard questions displayed on a display unit according to a first modification. FIG. 8 is a configuration diagram of a prompt generation device according to a second modification. FIG. 9 is a graph illustrating a time-series change in injection pressure in an injection process of an injection molding machine. FIG. 10 is a configuration diagram showing a portion of a prompt generation system according to a third modification. FIG. 11 is a diagram illustrating a plurality of industrial machines according to a fourth modification. FIG. 12 is a diagram illustrating a management device and a plurality of industrial machines according to a fifth modification.

[0009] One idea for resolving user problems and questions about industrial machinery is to use a generative artificial intelligence model. For example, it is conceivable to have a generative artificial intelligence model generate responses to user questions about industrial machinery.

[0010] However, in order to obtain an appropriate response from a generative artificial intelligence model, it is necessary to provide the generative artificial intelligence model with an appropriate prompt that corresponds to the content of the question. In this regard, creating an appropriate prompt is not necessarily easy for a user of industrial machinery. For example, a user may want to ask a generative artificial intelligence model about the cause of a malfunction in industrial machinery. In this case, the user is required to create a prompt that can appropriately teach the generative artificial intelligence model information related to the malfunction from various information such as parameters set in the industrial machine and the operating history of the industrial machine. The task of selecting and selecting information necessary to ask a question about industrial machinery and creating an appropriate prompt is a significant burden for the user.

[0011] Based on the above preliminary explanation, one embodiment will be described below.

[0012] FIG. 1 is a configuration diagram of a prompt generation system 10 according to one embodiment.

[0013] The prompt generation system 10 is a computer system that generates a prompt PRT (see also Figures 4A and 4B) including a question regarding the industrial machine 100. The industrial machine 100 is, for example, an injection molding machine 102, but may also be a robot, a machine tool, etc. The prompt PRT is an AI prompt for asking a question to the generation AI device 200. The generation AI device 200 is a computer (computer system) that responds to the prompt PRT using a generative artificial intelligence model. The generative artificial intelligence model includes a text generation artificial intelligence model that generates text in response to the prompt PRT. The text generation artificial intelligence model used by the generation AI device 200 may be an interactive generation model. The interactive generation model is a text generation artificial intelligence model that can generate text in a style that imitates human spoken language.

[0014] As shown in FIG. 1, the prompt generation system 10 includes an industrial machine information storage unit (storage unit) 12 , one or more user input terminals 14 , and a prompt generation device 16 .

[0015] The industrial machine information storage unit 12 is realized by one or more recording media (memories) accessible by the calculation unit 26 (information search unit 38) provided in the prompt generation device 16. A more detailed description of the prompt generation device 16 will be provided later. For example, FIG. 1 shows a control device 104 that controls the industrial machine 100. The control device 104 is a computer such as a numerical control device. A memory (not shown) provided in the control device 104 may realize the industrial machine information storage unit 12. FIG. 1 also shows a management device 300, which is a computer for managing multiple industrial machines 100. A memory (not shown) provided in the management device 300 may realize the industrial machine information storage unit 12. The prompt generation system 10 may be provided with a storage device (storage server, etc.) (not shown) dedicated to realizing the industrial machine information storage unit 12. The industrial machine information storage unit 12 may be realized by at least a portion of a memory unit 28 of the prompt generation device 16 (described later).

[0016] The industrial machinery information storage unit 12 stores industrial machinery information. The industrial machinery information is information related to the industrial machinery 100. Therefore, for example, the industrial machinery information includes information related to the injection molding machine 102. The industrial machinery information includes at least one of setting information, operation history information, and specification information.

[0017] The setting information is information that indicates the settings of the industrial machine 100. The setting information includes operating conditions, parameters, etc. that can be specified by a user to operate the industrial machine 100. More specifically, the setting information includes, for example, molding conditions that are set in the control device 104 of the injection molding machine 102. Examples of molding conditions include, but are not limited to, the nozzle temperature of the nozzle of the injection molding machine 102, the injection speed of the raw material in the injection process, the dwell time in the dwell process, and the dwell pressure in the dwell process. The nozzle is provided at the tip of the injection cylinder 102a of the injection molding machine 102.

[0018] The operation history information is information indicating the operation history of the industrial machine 100. For example, when the industrial machine 100 operates based on the above-mentioned operating conditions and parameters, the operation history information includes information indicating various physical quantities detected by various sensors provided in the industrial machine 100. More specifically, when the injection molding machine 102 executes an injection process, for example, the operation history information includes the maximum pressure of the raw material detected by a pressure sensor (not shown) provided in the injection molding machine 102. Note that the operation history information may also include a change history of the above-mentioned setting information (operating conditions, parameters, etc.). The operation history information may also include a history of alarms that are output when an abnormality occurs in the industrial machine 100, for example.

[0019] The specification information is information indicating the specifications of the industrial machine 100. For example, the specification information may include information indicating the model (model number), serial number, etc. of the industrial machine 100. Furthermore, for example, the specification information may include information indicating the design specifications of the industrial machine 100. In this case, the specification information may include, but is not limited to, information indicating the screw diameter of the screw provided in the injection molding machine 102. The specification information may also include the contents of the instruction manual for the industrial machine 100.

[0020] The industrial machinery information may include peripheral device information. The peripheral device information is information related to peripheral devices of the industrial machine 100. Examples of peripheral devices include a temperature controller, a hot runner, and the like (not shown) that are provided in the mold 106 of the injection molding machine 102. In this case, the peripheral device information may include, for example, temperature information of the temperature controller, the hot runner, and the like detected by a temperature sensor (not shown). The temperature information of the hot runner may be detected by a hot runner controller, which is a controller equipped with a control circuit that controls the hot runner. Note that the peripheral device information is not limited to this temperature information. Furthermore, the peripheral devices of the injection molding machine 102 are not limited to the temperature controller and the hot runner. The peripheral devices of the injection molding machine 102 may include, for example, a resin dryer. The resin dryer is a dryer that pre-dries the raw material (resin) supplied to a cylinder provided in the injection molding machine 102. In this case, the peripheral device information may include, for example, a parameter indicating the target dryness of the resin by the resin dryer.

[0021] The user input terminal 14 is a terminal device (computer) that accepts information input by a user to the prompt generation system 10. The control device 104 of the industrial machine 100 described above may be used as the user input terminal 14. A PC (Personal Computer) 400 or a smart device (such as a tablet terminal) 402 may also be used as the user input terminal 14. As shown in FIG. 1 , the user input terminal 14 includes a communication unit 18, a display unit 20, and an operation unit 22.

[0022] The communication unit 18 includes a communication module (not shown) connected to the network NW. The network NW includes, for example, a local area network (LAN) established in a factory where the industrial machine 100 is installed. The network NW may also include the Internet.

[0023] The display unit 20 includes an output display device (not shown) that can be viewed by a user. The output display device includes, for example, a display panel (not shown) that forms a display screen, a display element, etc. The display panel is, for example, a liquid crystal panel, but is not limited to this.

[0024] The operation unit 22 includes an input device (not shown). The input device includes an operation panel, a pointing device, a keyboard, a mouse, etc. The pointing device includes, for example, a touch panel arranged on the display unit 20 together with the above-mentioned display panel, but is not limited to this. The input device provided in the user input terminal 14 may include a voice input device. The voice input device includes, for example, a microphone.

[0025] The prompt generation device 16 is a computer that generates a prompt PRT based on input information that is information input to the prompt generation system 10. As shown in FIG. 1 , the prompt generation device 16 includes a communication unit 24, a calculation unit 26, and a storage unit 28.

[0026] The communication unit 24 includes a communication module (not shown) connected to the network NW, which allows the communication unit 24 to communicate with the communication unit 18 (user input terminal 14) via the network NW.

[0027] The calculation unit 26 includes a processing circuitry (not shown). The processing circuitry includes one or more processors, such as a central processing unit (CPU) or a graphics processing unit (GPU). The processing circuitry may include an integrated circuit, such as an application specific integrated circuit (ASIC) or a field-programmable gate array (FPGA). The processing circuitry may also include a discrete device.

[0028] The storage unit 28 includes one or more memories. The one or more memories include non-volatile memory. Non-volatile memory is a recording medium that non-temporarily stores programs, tables, maps, etc. For example, non-volatile memory includes ROM (Read Only Memory), flash memory, etc. The storage unit 28 (one or more memories) may include volatile memory. For example, volatile memory includes RAM (Random Access Memory). At least a part of the storage unit 28 (non-volatile memory) may be realized by a recording medium such as a USB (Universal Serial Bus) memory, a memory card, an optical disk, or a magnetic disk.

[0029] The calculation unit 26 includes a display processing unit 30, an input information acquisition unit 32, a keyword extraction unit 34, a search range determination unit 36, an information search unit 38, a template selection unit 40, a prompt generation unit 42, an edit acceptance unit 44, and a prompt transmission unit 46. The display processing unit 30, the input information acquisition unit 32, the keyword extraction unit 34, the search range determination unit 36, the information search unit 38, the template selection unit 40, the prompt generation unit 42, the edit acceptance unit 44, and the prompt transmission unit 46 are realized by the calculation unit 26 (processor) executing a program stored in the storage unit 28 (memory). At least some of the display processing unit 30, input information acquisition unit 32, keyword extraction unit 34, search range determination unit 36, information search unit 38, template selection unit 40, prompt generation unit 42, editing acceptance unit 44, and prompt transmission unit 46 may be realized by the above-mentioned ASIC, FPGA, discrete device, etc.

[0030] The display processing unit 30 executes processing for displaying one or more routine questions 48 (see also FIGS. 2A and 2B ) on the display unit 20. Information indicating the content of the routine questions 48 may be stored in advance in the storage unit 28. The display processing unit 30 transmits the information indicating the routine questions 48 to the user input terminal 14 via the communication unit 24. This enables the user input terminal 14 to display the routine questions 48 on the display unit 20. Note that the specific content of the routine questions 48 may be determined in advance by, for example, the manufacturer of the industrial machine 100.

[0031] 2A is a diagram illustrating a standard question 48 (481). The standard question 48 regarding the injection molding machine 102 is illustrated in FIG.

[0032] The standard questions 48 include questions, confirmations, etc., for the user to identify inquiries to the generation AI device 200. Answers to the standard questions 48 are made by the user via the operation unit 22 of the user input terminal 14. As shown in FIG. 2A , the display processing unit 30, for example, displays options 50 along with the standard questions 48 on the display unit 20. In this case, the user may answer the standard questions 48 by selecting an option 50 displayed along with the standard questions 48. The display processing unit 30 may display radio buttons, check boxes, pull-down lists, etc. on the display unit 20 to allow the user to select an option 50.

[0033] Fig. 2B is a diagram illustrating an example of a standard question 48. Fig. 2B illustrates a plurality of standard questions 48 (standard questions 482, 483, and 484) other than the standard question 481 in Fig. 2A.

[0034] The display processing unit 30 may display one or more other standard questions 48 on the display unit 20 depending on the user's response to the standard question 48. For example, FIG. 2B illustrates three standard questions 48 that may be displayed on the display unit 20 when "I want to know how to deal with molding defects," one of the options 50 in FIG. 2A, is selected. That is, FIG. 2B illustrates a standard question 482 that asks the user about the type of molding defect, a standard question 483 that asks about the period during which the molding defect has occurred, and a standard question 484 that asks about molding conditions. In response to the standard question 482, the user answers the type of molding defect occurring in the injection molding machine 102. In response to the standard question 483, the user may answer the number of molding cycles (cycle range) during which the molding defect has occurred, or the time (period) during which the molding defect has occurred. The display processing unit 30 may display one or more numerical input fields 51, pull-down lists, or the like, along with the standard question 483, to prompt the user to enter the period. In response to the standard question 483, the user may answer with the number of predetermined cycles most recently performed by the injection molding machine 102. In response to the standard question 484, the user answers, for example, the type of raw material (resin, etc.) of the molded product, the type of the molded product (mold 106), the type of screw provided in the injection molding machine 102, etc.

[0035] The display processing unit 30 may display a character input field 52 together with the standard question 48 ( FIG. 2B ). In this case, the user may answer the standard question 48 by inputting (free-form writing) a character string (inquiry sentence) into the character input field 52. Note that the inquiry sentence may be created based on voice information input to the user input terminal 14 via the above-mentioned voice input device.

[0036] The input information acquisition unit 32 ( FIG. 1 ) acquires input information. As described above, the input information is information input to the prompt generation system 10. The input information may include user response information. The user response information is information indicating the content of the user's response to one or more standard questions 48 presented to the user by the display processing unit 30. For example, the user response information indicates the selection result of the above-described option 50, the query entered in the character input field 52, and the voice information entered into the user input terminal 14 via the above-described voice input device. The input information acquisition unit 32 can acquire the user response information from the user input terminal 14 via the communication unit 24. When the above-described voice information is included in the user response information, the input information acquisition unit 32 may create a query based on the voice information.

[0037] The keyword extraction unit 34 extracts predetermined keywords from a query included in the input information (user response information). For example, a keyword list indicating a plurality of keywords determined according to the content of the standard question 48 is stored in advance in the storage unit 28. The keyword extraction unit 34 extracts keywords included in the query by comparing the keyword list with the query. More specifically, for example, in response to standard question 484 in FIG. 2B , the user inputs a query including the type of raw material of the molded product, the type of the molded product, the type of screw provided in the injection molding machine 102, etc. In this case, the keyword extraction unit 34 uses the keyword list to extract from the query the keywords indicating the type of raw material of the molded product, the keywords indicating the type of the molded product, and the keywords indicating the type of screw, etc.

[0038] The search range determination unit 36 ​​determines the search range for industrial machinery information based on the input information acquired by the input information acquisition unit 32. For example, as described above, the user can select an answer to the standard question 48 using the options 50. The options 50 may be pre-associated with the type of industrial machinery information associated with the option 50. For example, "burr," one of the options 50 for the standard question 482 in FIG. 2B , may be pre-associated with the injection speed, packing pressure, and other industrial machinery information (setting information) related to burrs (flash), a type of molding defect. Thus, when the user selects "burr" as an answer to the standard question 482, the search range determination unit 36 ​​may include, in the search range, setting information indicating the injection speed, packing pressure, and other industrial machinery information. Furthermore, for example, "short shot," one of the options 50 for the standard question 482 in FIG. 2B , may be pre-associated with the nozzle temperature, injection speed, and other industrial machinery information (setting information) related to short shots (underfill of the molded product), a type of molding defect. As a result, when the user selects "short shot" as an answer to the standard question 482, the search range determination unit 36 ​​may include setting information indicating the nozzle temperature, injection speed, etc. in the search range. The search range determination unit 36 ​​may determine the search range based on a user instruction. For example, the user may arbitrarily specify at least one type of information from setting information, operation history information, and specification information via the operation unit 22. In this case, the search range determination unit 36 ​​may include at least one type of information specified by the user from setting information, operation history information, and specification information in the search range.

[0039] The search range determination unit 36 ​​may determine the time range of the industrial machinery information to be searched based on the input information. For example, the search range determination unit 36 ​​determines a cycle range or period based on the user's answer to the standard question 483 in FIG. 2B , and includes industrial machinery information corresponding to the cycle range or period in the search range. More specifically, the search range determination unit 36 ​​includes, for example, setting information that was set in the control device 104 during the period, operation history information that indicates physical quantities detected during the period, and the like in the search range.

[0040] The search range determination unit 36 ​​may determine the search range for industrial machinery information based on the keywords extracted by the keyword extraction unit 34. For example, the search range determination unit 36 ​​may determine the search range for industrial machinery information based on a keyword indicating the type of raw material of a molded product, a keyword indicating the type of the molded product, and a keyword indicating the type of screw, etc. Keywords may be associated in advance with the industrial machinery information corresponding to the keywords.

[0041] The information search unit 38 searches for industrial machinery information related to the input information from the industrial machinery information storage unit 12. The information search unit 38 performs a search based on the search range determined by the search range determination unit 36, thereby enabling accurate search for industrial machinery information related to the input information.

[0042] The template selection unit 40 automatically selects a template (template sentence) 54 for the prompt PRT to be sent to the generation AI device 200 from among a plurality of templates 54 created in advance. The template selection unit 40 selects a template 54 based on input information.

[0043] Fig. 3A is a diagram illustrating one template 54 (template 541) among the plurality of templates 54. Fig. 3B is a diagram illustrating another template 54 (template 542) different from that in Fig. 3A.

[0044] FIG. 3A illustrates a template 541 that can be selected by the template selection unit 40 when the answer (selection result) to the standard question 481 in FIG. 2A is "I want to know how to deal with molding defects." FIG. 3B illustrates a template 542 that can be selected by the template selection unit 40 when the answer (selection result) to the standard question 481 in FIG. 2A is "I want to troubleshoot the injection molding machine 102." Each of the multiple templates 54 (template 541, template 542) can include one or more predetermined template sentences 56 (template sentence 561, template sentence 562, template sentence 563) corresponding to each template 54, and one or more blank spaces 58 (blank space 581, blank space 582, blank space 583). The template sentences 56 are stored in advance in the storage unit 28. The blank spaces 58 are provided in advance in the middle of the template 56 or between multiple template sentences 56, corresponding to the industrial machinery information (search range) searched by the information search unit 38. At least one of the multiple blank spaces 58 may be a marker or the like indicating the insertion position of a sentence 60 (see also Figures 4A and 4B).

[0045] The prompt generation unit 42 (FIG. 1) combines the search results for industrial machinery information by the information search unit 38 with one or more standard phrases 56 to generate a prompt PRT to be sent to the generation AI device 200. More specifically, the prompt generation unit 42 generates the prompt PRT to be sent to the generation AI device 200 based on the search results for industrial machinery information by the information search unit 38 and the selection result of a template 54 by the template selection unit 40. In this case, the prompt generation unit 42 can generate the prompt PRT by editing the template 54 based on the search results by the information search unit 38. For example, the prompt generation unit 42 generates the prompt PRT by inserting the industrial machinery information searched for by the information search unit 38 into one or more blank spaces 58 described above.

[0046] FIG. 4A is a diagram illustrating an example of a prompt PRT (prompt PRT1) generated by the prompt generating unit 42.

[0047] FIG. 4A illustrates an example of a prompt PRT1 that can be generated by the prompt generation unit 42 when the user selects "burr" as the answer to the standard question 482 in FIG. 2B. The prompt PRT1 includes a sentence 60 (sentence 60A) indicating that the molded product has burrs. The sentence 60A can be created by inserting a phrase corresponding to the user's answer to the standard question 482 in FIG. 2B into the blank 581 (standard text 561) in FIG. 3A. The prompt PRT1 also includes a sentence 60 (sentence 60B) indicating the industrial machinery information searched by the information search unit 38. If the search range determination unit 36 ​​has determined the time range based on the input information, the prompt generation unit 42 includes the content of the operation history information corresponding to the time range in the sentence 60B of the prompt PRT.

[0048] Fig. 4B is a diagram illustrating another prompt PRT different from that of Fig. 4A. The prompt PRT of Fig. 4A and the prompt PRT of Fig. 4B can be generated using the same template 541 (Fig. 3A).

[0049] FIG. 4B illustrates an example of a prompt PRT2 that can be generated by the prompt generation unit 42 when the user selects "short shot" as the answer to the standard question 482 in FIG. 2B. The prompt PRT2 includes a sentence 60 (sentence 60C) indicating that the molded product has a short shot. Like sentence 60A, sentence 60C can be created by inserting a phrase corresponding to the user's answer to the standard question 482 in FIG. 2B into blank 581 (standard sentence 561) in FIG. 3A. The prompt PRT2 also includes a sentence 60 (sentence 60D) indicating industrial machinery information searched for by the information search unit 38.

[0050] According to this embodiment, the industrial machinery information to be searched differs depending on the input information (user response information). Therefore, as shown by comparing Figures 4A and 4B, the contents of prompt PRT1 and prompt PRT2 generated using the same template 54 may differ.

[0051] The edit accepting unit 44 (FIG. 1) accepts edits to the prompt PRT generated by the prompt generating unit 42. In this case, the display processing unit 30 may execute processing for displaying the prompt PRT on the display unit 20. The user can edit the prompt PRT via the operation unit 22.

[0052] The prompt sending unit 46 sends the prompt PRT to the generating AI device 200 via the communication unit 24. This causes the generating AI device 200 to generate a response to the prompt PRT. The prompt sending unit 46 sends the prompt PRT to the generating AI device 200 in response to, for example, a user's instruction, but may also automatically send the generated prompt PRT to the generating AI device 200 (see also variant example 10 described below).

[0053] The generative AI device 200 is equipped with, for example, an interactive generative model. In this case, the generative AI device 200 can generate text (a response sentence) in a style that imitates colloquial language in response to the prompt PRT.

[0054] The response sentence generated by the generation AI device 200 is transmitted to the prompt generation device 16 (communication unit 24) via the network NW. When the response sentence is received by the prompt generation device 16 (communication unit 24), the display processing unit 30 executes processing to display the response sentence on the display unit 20. This allows the user to check the response sentence.

[0055] FIG. 5 is a diagram illustrating an example of a screen of the display unit 20 on which a prompt PRT and the response of the generating AI device 200 to the prompt PRT are displayed.

[0056] 5 shows a plurality of operation buttons 62 (an edit acceptance button 621 and a send instruction button 622), a prompt display field 64, and an answer display field 66. Each of the plurality of operation buttons 62, the prompt display field 64, and the answer display field 66 is displayed on the display unit 20. The plurality of operation buttons 62 includes an edit acceptance button 621 and a send instruction button 622.

[0057] The edit acceptance button 621 is operated when the user wishes to edit the prompt PRT. By operating the edit acceptance button 621, the user can begin editing the prompt PRT. The send instruction button 622 is operated when the user wishes to send the prompt PRT to the generation AI device 200. By operating the send instruction button 622, the user can send the prompt PRT to the generation AI device 200.

[0058] The prompt display field 64 displays the prompt PRT. The user can edit the prompt PRT displayed in the prompt display field 64. The answer display field 66 displays the response content (AI answer) of the generating AI device 200 to the prompt PRT. This allows the user to check the response content of the generating AI device 200. Furthermore, by displaying the prompt display field 64 and the answer display field 66 side by side, the user can easily compare the prompt PRT with the answer of the generating AI device 200 to the prompt PRT.

[0059] FIG. 6 is a flow chart illustrating a method for generating a prompt according to one embodiment.

[0060] The prompt generation device 16 described above can execute the prompt generation method shown in Fig. 6. The prompt generation method shown in Fig. 6 can be performed by having the calculation unit 26 (processor) execute a program stored in the storage unit 28 (memory). As shown in Fig. 6, the prompt generation method includes an information input acceptance step S1, a keyword extraction step S2, a search range determination step S3, an information search step S4, a template selection step S5, a prompt generation step S6, and an edit acceptance step S7.

[0061] The information input receiving step S1 includes a routine question display processing step S1A and an input information acquisition step S1B. In the routine question display processing step S1A, the display processing unit 30 executes processing for displaying one or more routine questions 48 on the display unit 20 of the user input terminal 14. In the input information acquisition step S1B, the input information acquisition unit 32 acquires input information. The input information may include user answer information indicating the content of the user's answers to the one or more routine questions 48.

[0062] The routine question display processing step S1A and the input information acquisition step S1B may be repeatedly executed as necessary. For example, as described above, one or more different routine questions 48 may be displayed on the display unit 20 in accordance with the user's answer to the routine question 48. In this case, the routine question display processing step S1A and the input information acquisition step S1B are repeated as necessary.

[0063] In the keyword extraction step S2, the keyword extraction unit 34 extracts keywords from the query statement included in the input information. Note that if the input information does not include a query statement, the keyword extraction step S2 may be skipped.

[0064] In a search range determination step S3, the search range determination unit 36 ​​determines a search range based on the input information or keywords. In an information search step S4, the information search unit 38 searches for industrial machinery information based on the determined search range.

[0065] In the template selection step S5, the template selection unit 40 selects a template 54 of the prompt PRT to be sent to the generation AI device 200. The template selection unit 40 selects a template 54 corresponding to the input information from among the multiple templates 54. Note that the template selection step S5 may be executed before the search range determination step S3, or may be executed between the search range determination step S3 and the information search step S4. The template selection step S5 may be executed in parallel with at least one of the search range determination step S3 and the information search step S4.

[0066] In the prompt generation step S6, the prompt generation unit 42 generates a prompt PRT based on the search results by the information search unit 38. The prompt generation unit 42 can generate the prompt PRT by editing the template 54 selected by the template selection unit 40 based on the search results by the information search unit 38.

[0067] In the edit accepting step S7, the edit accepting unit 44 accepts edits to the prompt PRT. The user can edit the prompt PRT via the operation unit 22. Note that the user does not have to edit the prompt PRT.

[0068] This completes the prompt generation method of Figure 6. As described above, the prompt generation device 16 is equipped with a prompt sending unit 46. This allows the prompt generation device 16 to send the generated prompt PRT to the generation AI device 200. In addition, the display processing unit 30 of the prompt generation device 16 executes processing to display the response sentence received from the generation AI device 200 on the display unit 20. This allows the user to check the response sentence.

[0069] The above-described prompt generation system 10 can achieve the following advantageous effects, for example.

[0070] The prompt generation system 10 includes a prompt generation device 16. The prompt generation device 16 includes an information search unit 38. The information search unit 38 searches for industrial machinery information related to input information based on the input information. This reduces the workload of a user who is trying to select industrial machinery information that should be included in the prompt PRT.

[0071] The prompt generation device 16 also includes a prompt generation unit 42. The prompt generation unit 42 generates a prompt PRT based on the search results from the information search unit 38. This reduces the workload of a user who is trying to create a prompt PRT.

[0072] The industrial machinery information includes at least one of setting information, operation history information, and specification information. In this case, the prompt generation unit 42 can generate a prompt PRT that instructs the generation AI device 200 on at least one of the setting information, operation history information, and specification information. By transmitting the prompt PRT to the generation AI device 200, it becomes easier to obtain an accurate response from the generation AI device 200 to a user's question about the industrial machinery 100.

[0073] The industrial machinery information may include peripheral device information. In this case, the prompt generation unit 42 can generate a prompt PRT that instructs the generation AI device 200 about the peripheral device information. By transmitting the prompt PRT to the generation AI device 200, it becomes easier to obtain an accurate response from the generation AI device 200 to a user's question about the industrial machinery 100.

[0074] The prompt generation device 16 includes a search range determination unit 36. The search range determination unit 36 ​​determines a search range based on input information. As described above, the information search unit 38 can accurately search for industrial machinery information related to the input information by performing a search based on the search range. As a result, the prompt generation unit 42 can generate a prompt PRT that includes industrial machinery information for a period (time range) determined based on the input information, for example.

[0075] The prompt generation device 16 includes a display processing unit 30. The display processing unit 30 executes processing for displaying one or more standard questions 48 on the display unit 20. A user can answer the one or more standard questions 48 displayed on the display unit 20 via the operation unit 22. As a result, user answer information indicating the user's answers to the one or more standard questions 48 can be acquired by the input information acquisition unit 32. The display unit 20 and the operation unit 22 can be included in various types of computers, such as the control device 104, the PC 400, and the smart device 402.

[0076] The answer format for at least one standard question 48 may be a multiple-choice format in which the user selects an answer from predetermined options 50. The multiple-choice format is preferable because it places a relatively small burden on the user to input characters.

[0077] The answer format for at least one standard question 48 may be a free-form answer format in which the user inputs characters into a character input field 52 via the operation unit 22. In this case, a query sentence is created by the user inputting characters via the operation unit 22. With regard to this query sentence, the prompt generation device 16 includes a keyword extraction unit 34. The keyword extraction unit 34 extracts predetermined keywords from the query sentence. This allows the search range determination unit 36 ​​to determine a search range based on the keywords extracted by the keyword extraction unit 34. As a result, the information search unit 38 can accurately search for industrial machinery information related to the keywords extracted by the keyword extraction unit 34.

[0078] The prompt generation device 16 includes a template selection unit 40. The template selection unit 40 selects a template 54 for the prompt PRT to be sent to the generation AI device 200 from a plurality of templates 54. The prompt generation unit 42 generates the prompt PRT based on the template 54 selected by the template selection unit 40. This reduces variation in the quality of the prompt PRT for each user. In other words, according to this embodiment, even if the user of the industrial machinery 100 is unfamiliar with creating AI prompts, they can easily create a prompt PRT that is likely to elicit an appropriate response from the generation AI device 200.

[0079] The prompt generating device 16 includes an edit receiving unit 44. The edit receiving unit 44 receives edits using the prompt PRT. The user can edit the prompt PRT via the operation unit 22. This provides convenience to the user.

[0080] One embodiment may be modified as follows. In the following modifications, descriptions that overlap with the embodiment will be omitted as appropriate. In addition, in the drawings used in the following modifications, the same reference numerals are used for the same components as those described in the embodiment.

[0081] (Modification 1) FIG. 7 is a diagram illustrating a plurality of standard questions 48 displayed on the display unit 20 according to Modification 1. In FIG.

[0082] 7 , a plurality of standard questions 48 and a history 67 of answers from the user to each of the plurality of standard questions 48 may be sequentially displayed in a chatbot format on the display unit 20. In this case, the display processing unit 30 executes processing for sequentially displaying the plurality of standard questions 48 and the plurality of answer histories 67 on the display unit 20 based on a chatbot program.

[0083] (Modification 2) FIG. 8 is a diagram showing the configuration of a prompt generation device 16 (prompt generation device 16B) according to Modification 2. In FIG.

[0084] The input information acquisition unit 32 included in the prompt generation device 16B automatically acquires the operation history information stored in the industrial machine information storage unit 12. That is, the input information acquisition unit 32 automatically acquires the operation history information as input information. The input information acquisition unit 32 repeatedly acquires the operation history information, for example, based on a predetermined cycle.

[0085] The prompt generation device 16B further includes an abnormality determination unit 68. Similar to the input information acquisition unit 32, the abnormality determination unit 68 is realized by the calculation unit 26 executing a program stored in the storage unit 28. The abnormality determination unit 68 determines whether an abnormality has occurred in the industrial machine 100 based on the operation history information acquired as input information by the input information acquisition unit 32.

[0086] 9 is a graph illustrating the time series change in injection pressure during the injection process of the injection molding machine 102. The vertical axis of the graph represents the magnitude of the injection pressure (MPa: megapascals), and the horizontal axis of the graph represents time (s: seconds).

[0087] For example, the abnormality determination unit 68 determines whether an abnormality has occurred in the injection molding machine 102 based on whether the peak pressure P1 of the injection molding machine 102 deviates from a predetermined allowable range RNG. The peak pressure P1 is the maximum value of the injection pressure during the injection process. The injection pressure can be detected by a pressure sensor such as a load cell. The pressure sensor is provided, for example, at the rear end of an injection member such as a screw or plunger provided in the injection molding machine 102. The peak pressure P1 shown in FIG. 9 deviates from the predetermined allowable range RNG. In this case, the abnormality determination unit 68 determines that an abnormality has occurred in the injection molding machine 102.

[0088] The conditions for the determination by the abnormality determination unit 68 may be determined as appropriate. For example, the abnormality determination unit 68 may determine that an abnormality has occurred in the injection molding machine 102 when a predetermined number of molding cycles in which the peak pressure P1 deviates from a predetermined allowable range RNG have been executed consecutively. As described above, the industrial machine 100 is not limited to the injection molding machine 102. The conditions for the determination by the abnormality determination unit 68 may be determined as appropriate depending on the type of industrial machine 100.

[0089] When the abnormality determination unit 68 determines that an abnormality has occurred in the industrial machine 100, the search range determination unit 36 ​​determines the search range for industrial machinery information based on the content of the abnormality (the determination condition of the abnormality determination unit 68). In this case, the search range determination unit 36 ​​may determine the time range based on input information (operation history information). The search range determination unit 36 ​​may exclude operation history information that has already been acquired as input information from the search range.

[0090] The information search unit 38 searches for industrial machinery information based on the search range determined by the search range determination unit 36. Furthermore, the prompt generation unit 42 generates a prompt PRT based on the search results by the information search unit 38. The prompt generation unit 42 may generate the prompt PRT based on operation history information acquired as input information. The generated prompt PRT is transmitted to the generation AI device 200 by the prompt transmission unit 46.

[0091] According to this modification, the prompt generation device 16B (abnormality determination unit 68) determines whether or not an abnormality has occurred in the industrial machinery 100. Furthermore, according to this modification, when the abnormality determination unit 68 determines that an abnormality has occurred in the industrial machinery 100, the prompt generation unit 42 can automatically generate a prompt PRT. This enables the prompt generation device 16B to support the user.

[0092] (Modification 3) FIG. 10 is a configuration diagram showing a prompt generation system 10 (prompt generation system 10C) according to Modification 3.

[0093] The prompt generation system 10C is equipped with a monitoring device (predetermined monitoring device) 108. The monitoring device 108 is a device for monitoring the state of the industrial machine 100. The monitoring device 108 is, for example, an alarm device that issues an alarm based on an output signal from a sensor for detecting an abnormality in the industrial machine 100. The monitoring device 108 may be a quality inspection device that inspects the quality of a processed product processed by a machine tool, a molded product formed by the injection molding machine 102, etc. The quality inspection device inspects the appearance of the molded product based on a signal output from an image sensor (camera) that captures an image of the molded product, for example.

[0094] The monitoring device 108 outputs a predetermined signal to the prompt generation device 16 based on the results of monitoring by the monitoring device 108. For example, the alarm device described above outputs a signal indicating the content of the alarm to the prompt generation device 16. Furthermore, when the quality inspection device described above determines that a molded product is defective, it outputs a signal indicating that the molded product is defective to the prompt generation device 16.

[0095] The input information acquisition unit 32 acquires, as input information, a predetermined signal output from the monitoring device 108. In this case, the search range determination unit 36 ​​determines the search range for industrial machinery information based on the acquired predetermined signal. For example, the search range determination unit 36 ​​determines the search range based on the type of alarm, the reason why the molded product was determined to be defective, etc.

[0096] The information search unit 38 searches for industrial machinery information based on the search range determined by the search range determination unit 36. Furthermore, the prompt generation unit 42 generates a prompt PRT based on the search results by the information search unit 38. The generated prompt PRT is transmitted to the generation AI device 200 by the prompt transmission unit 46.

[0097] According to this modification, when a predetermined signal is output from the monitoring device 108, which is an external device to the prompt generation device 16, the prompt generation unit 42 can automatically generate a prompt PRT. This allows the prompt generation device 16 to assist the user. For example, when an alarm occurs, a predetermined alarm message can be presented to the user. According to this modification, not only the alarm message but also advice from the generation AI device 200, for example, can be provided to the user.

[0098] The above-described alarm may be output by the control device 104 of the industrial machine 100. In other words, there may be cases where the control device 104 also functions as the monitoring device 108.

[0099] (Modification 4) FIG. 11 is a diagram showing a plurality of industrial machines 100 (injection molding machines 102) according to Modification 4. In FIG.

[0100] The prompt generation device 16 may be provided in the control device 104. This allows the prompt generation device 16 and the control device 104 to be realized as a single computer. In this case, the prompt generation device 16 and the control device 104 can share hardware resources such as a processor and memory. In addition, the prompt PRT generated by the control device 104 (prompt generation device 16) is sent to the generation AI device 200.

[0101] 11 shows a prompt generation device 16 provided in a first control device 104A, which is one of the multiple control devices 104. The prompt generation device 16 provided in the first control device 104A may be communicatively connected to a control device 104 other than the first control device 104A (control device 104B, control device 104C, ...). This allows a user to cause the prompt generation device 16 to generate a prompt PRT via a control device 104 other than the first control device 104A. In this case, the control device 104 other than the first control device 104A functions as a user input terminal 14.

[0102] The prompt generation device 16 may be provided in each of the plurality of control devices 104. The prompt generation device 16 may also be provided in the PC 400, the smart device 402, etc. (see also FIG. 1).

[0103] (Modification 5) FIG. 12 is a diagram showing a management device 300 and a plurality of industrial machines 100 (injection molding machines 102) according to Modification 5. In FIG.

[0104] The management device 300 is a computer for managing multiple industrial machines 100 (see also one embodiment). The prompt generation device 16 may be provided in the management device 300. This allows the prompt generation device 16 and the management device 300 to be realized as a single computer. In this case, the prompt generation device 16 and the management device 300 can share hardware resources such as a processor and memory. In addition, the prompt PRT generated by the management device 300 (prompt generation device 16) is transmitted to the generation AI device 200. In this case, each of the multiple control devices 104 functions as a user input terminal 14.

[0105] (Variation 6) If the answers to the standard questions 48 do not include any inquiry sentences, the keyword extraction unit 34 may be omitted. For example, if the answers to all the standard questions 48 are multiple-choice, the keyword extraction unit 34 may be omitted.

[0106] (Variation 7) The industrial machinery 100 includes machines that repeatedly execute a predetermined routine (cycle). For example, an injection molding machine 102 can repeatedly execute a predetermined molding cycle (see also one embodiment). Furthermore, a machine tool can repeatedly execute a predetermined machining cycle. A robot can repeatedly execute a predetermined work routine.

[0107] In light of the above, the information search unit 38 may search for industrial machinery information for a predetermined number of cycles. For example, if the input information includes information indicating a certain point in time (period), the information search unit 38 may search for industrial machinery information for a period going back a predetermined number of cycles from that point in time. The predetermined number of cycles may be a predetermined fixed value (constant) or may be designable via, for example, the operation unit 22.

[0108] (Variant 8) There are cases where the generating AI device 200 can access the industrial machinery information storage unit 12 based on access route information. The access route information is information that indicates the storage location of the industrial machinery information in the information and communication network, the access route to the storage location, etc. For example, the access route information includes a network address, a network path, etc. More specifically, the access route information includes, for example, a URL (Uniform Resource Locator), but is not limited to this.

[0109] The prompt generation unit 42 may include the access route information in the prompt PRT. In this case, the specific content of at least a part of the industrial machinery information searched by the information search unit 38 does not need to be described in the prompt PRT.

[0110] According to this modification, the generating AI device 200 can refer to industrial machinery information by accessing the industrial machinery information storage unit 12 based on the access path information indicated by the prompt PRT. For example, the prompt generating unit 42 can include a URL for accessing operation history information indicating the peak pressure P1 in the prompt PRT, instead of the specific numerical value of the peak pressure P1 (see modification 2) of the injection molding machine 102. This allows the generating AI device 200 to refer to the peak pressure P1 corresponding to the URL.

[0111] (Variant 9) The generative artificial intelligence model that can be used by the generative AI device 200 is not limited to a text-generative artificial intelligence model (interactive generative model). For example, the generative AI device 200 may respond to the prompt PRT using an image-generating artificial intelligence model that generates an image, a video-generating artificial intelligence model that generates a video, a voice-generating artificial intelligence model that generates a voice, or the like.

[0112] (Variant 10) The prompt generation device 16 (display processing unit 30) may not display the generated prompt PRT on the display unit 20. For example, the edit acceptance unit 44 may be omitted from the prompt generation device 16. In that case, there is no need to display the prompt PRT on the display unit 20 to allow the user to edit the prompt PRT. In this case, the display processing unit 30 may not display the prompt PRT generated by the prompt generation unit 42 on the display unit 20. Note that if the edit acceptance unit 44 is omitted from the prompt generation device 16, the prompt sending unit 46 may automatically send the prompt PRT generated by the prompt generation unit 42 to the generation AI device 200.

[0113] (Combination of Multiple Modifications) The multiple modifications described above may be combined as appropriate.

[0114] According to the embodiment and the modified examples described above, users who have problems, questions, etc. regarding the industrial machine 100 can be well supported.

[0115] The following additional notes are further disclosed regarding the above embodiment.

[0116] (Supplementary Note 1) The prompt generation device (16) of the present disclosure includes an input information acquisition unit (32) that acquires input information, an information search unit (38) that searches for industrial machinery information, which is information about industrial machinery (100) related to the input information, from a memory unit (12) in which the industrial machinery information is stored, and a prompt generation unit (42) that generates a prompt (PRT) to be sent to a generation AI device (200) based on the search results by the information search unit.

[0117] (Supplementary Note 2) In the prompt generation device described in Supplementary Note 1, the industrial machine information may include at least one of setting information that indicates the settings of the industrial machine, operation history information that indicates the operation history of the industrial machine, and specification information that indicates the specifications of the industrial machine.

[0118] (Supplementary Note 3) In the prompt generation device described in Supplementary Note 2, the prompt generation unit may generate the prompt including the industrial machinery information for a predetermined number of cycles or the industrial machinery information for a period determined based on the input information.

[0119] (Supplementary Note 4) In the prompt generation device according to Supplementary Note 2 or 3, the industrial machine information includes the operation history information, the input information acquisition unit automatically acquires the operation history information stored in the memory unit as the input information, and the device further includes an abnormality determination unit (68) that determines whether or not an abnormality has occurred in the industrial machine based on the operation history information acquired by the input information acquisition unit, and when the abnormality determination unit determines that an abnormality has occurred in the industrial machine, the prompt generation unit may automatically generate the prompt.

[0120] (Supplementary Note 5) In the prompt generation device according to any one of Supplementary Notes 1 to 4, the industrial machine information may include peripheral device information that is information related to peripheral devices of the industrial machine.

[0121] (Supplementary Note 6) The prompt generation device according to any one of Supplementary Notes 1 to 5 may further include a display processing unit (30) that executes processing to display one or more predetermined standard questions (48) on a display unit (20) that can be viewed by a user, and the input information may include answers from the user to the one or more standard questions.

[0122] (Supplementary Note 7) In the prompt generation device according to any one of Supplementary Notes 1 to 6, the input information may include a query statement created by character input via an operation unit (22), and the device may further include a keyword extraction unit (34) that extracts predetermined keywords from the query statement, and the information search unit may search for the industrial machinery information based on the keywords extracted by the keyword extraction unit.

[0123] (Appendix 8) In the prompt generation device described in any one of Appendices 1 to 7, when a predetermined signal is output from a predetermined monitoring device (108), the input information acquisition unit may acquire the predetermined signal as the input information.

[0124] (Supplementary Note 9) The prompt generation device according to any one of Supplementary Notes 1 to 8 may further include an edit receiving unit (44) that receives edits to the prompt generated by the prompt generation unit.

[0125] (Supplementary Note 10) The prompt generation device according to any one of Supplementary Notes 1 to 9 may be provided in a control device (104) that controls the industrial machine.

[0126] (Supplementary Note 11) The prompt generation device according to any one of Supplementary Notes 1 to 10 may be provided in a management device (300) that manages a plurality of the industrial machines.

[0127] (Supplementary Note 12) In the prompt generation device according to any one of Supplementary Notes 1 to 11, the industrial machine may be an injection molding machine (102).

[0128] (Supplementary Note 13) In the prompt generation device according to any one of Supplementary Notes 1 to 12, the generation AI device may be equipped with an interactive generation model.

[0129] (Appendix 14) The prompt generation method of the present disclosure includes an input information acquisition step (S1B) for acquiring input information, an information search step (S4) for searching industrial machinery information, which is information about industrial machinery (100) related to the input information, from a memory unit (12) in which the industrial machinery information is stored, and a prompt generation step (S6) for generating a prompt (PRT) to be sent to a generation AI device (200) based on the search results of the information search step, and is executed by a computer.

[0130] (Supplementary Note 15) A program disclosed herein is a program for causing a computer to execute the prompt generation method described in Supplementary Note 14.

[0131] Although the present disclosure has been described in detail, the present disclosure is not limited to the individual embodiments described above. Various additions, substitutions, modifications, partial deletions, etc. are possible in these embodiments without departing from the gist of the present disclosure or the spirit of the present disclosure derived from the content of the claims and their equivalents. These embodiments can also be implemented in combination. For example, in the above-described embodiments, the order of each operation and the order of each process are shown as examples and are not limited to these. The same applies when numerical values ​​or mathematical expressions are used in the description of the above-described embodiments.

[0132] DESCRIPTION OF SYMBOLS 12...Industrial machine information storage unit (storage unit) 14...User input terminal 16...Prompt generation device 20...Display unit 22...Operation unit 30...Display processing unit 32...Input information acquisition unit 34...Keyword extraction unit 38...Information search unit 40...Template selection unit 42...Prompt generation unit 44...Editing reception unit 48...Standard question 54...Template 68...Abnormality determination unit 100...Industrial machine 102...Injection molding machine 104...Control device 108...Monitoring device (predetermined monitoring device) 200...Generation AI device 300...Management device PRT...Prompt

Claims

1. A prompt generation device comprising: an input information acquisition unit that acquires input information; an information search unit that searches for industrial machinery information, which is information about industrial machinery related to the input information, from a memory unit in which the industrial machinery information is stored; and a prompt generation unit that generates a prompt to be sent to a generation AI device based on the search results by the information search unit.

2. A prompt generation device according to claim 1, wherein the industrial machine information includes at least one of setting information which is information indicating the settings of the industrial machine, operation history information which is information indicating the operation history of the industrial machine, and specification information which is information indicating the specifications of the industrial machine.

3. A prompt generation device according to claim 2, wherein the prompt generation unit generates the prompt including the industrial machinery information for a predetermined number of cycles or the industrial machinery information for a period determined based on the input information.

4. A prompt generation device according to claim 2 or 3, wherein the industrial machine information includes the operation history information, the input information acquisition unit automatically acquires the operation history information stored in the memory unit as the input information, and the device further comprises an abnormality determination unit that determines whether or not an abnormality has occurred in the industrial machine based on the operation history information acquired by the input information acquisition unit, and when the abnormality determination unit determines that an abnormality has occurred in the industrial machine, the prompt generation unit automatically generates the prompt.

5. A prompt generation device according to any one of claims 1 to 4, wherein the industrial machine information includes peripheral device information that is information related to peripheral devices of the industrial machine.

6. A prompt generation device according to any one of claims 1 to 5, further comprising a display processing unit that executes processing for displaying one or more predetermined standard questions on a display unit that can be viewed by a user, and wherein the input information includes the user's answers to the one or more standard questions.

7. A prompt generation device according to any one of claims 1 to 6, wherein the input information includes a query created by character input via an operation unit, and the device comprises a keyword extraction unit that extracts predetermined keywords from the query, and the information search unit searches for the industrial machinery information based on the keywords extracted by the keyword extraction unit.

8. A prompt generation device according to any one of claims 1 to 7, wherein, when a predetermined signal is output from a predetermined monitoring device, the input information acquisition unit acquires the predetermined signal as the input information.

9. A prompt generation device according to any one of claims 1 to 8, further comprising an edit receiving unit that receives edits to the prompt generated by the prompt generation unit.

10. A prompt generation device according to any one of claims 1 to 9, which is provided in a control device that controls the industrial machine.

11. A prompt generation device according to any one of claims 1 to 10, which is provided in a management device that manages a plurality of the industrial machines.

12. A prompt generation device according to any one of claims 1 to 11, wherein the industrial machine is an injection molding machine.

13. A prompt generation device according to any one of claims 1 to 12, wherein the generation AI device is provided with an interactive generation model.

14. A prompt generation method executed by a computer, comprising: an input information acquisition step of acquiring input information; an information search step of searching for industrial machinery information, which is information about industrial machinery related to the input information, from a memory unit in which the industrial machinery information is stored; and a prompt generation step of generating a prompt to be sent to a generation AI device based on the search results from the information search step.

15. A program for causing a computer to execute the prompt generating method according to claim 14.

Images