Data processing apparatus, data processing method, and data processing program

Abstract

To provide a data processing device, a data processing method, and a program capable of acquiring reviews of various personas assumed for an application and utilizing the reviews for feedback of development of the application.SOLUTION: The data processing system performs, as the specific processing, processing of receiving specifications information regarding development content of the application, inputting the specifications information and a plurality of personas generated in advance for the review to the generative AI model together with instruction information for instructing the review of the application, acquiring the review of the application of the persona, and outputting the review in a predetermined format.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a data processing device, a data processing method, and a data processing program. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Quality assurance reviews are often conducted during application development. However, due to budget and schedule constraints, it is sometimes not possible for QA engineers to conduct reviews, posing the challenge of not being able to obtain sufficient reviews. If sufficient reviews are not obtained, the system is released without knowing whether it is good or bad until it actually reaches users, and if user ratings are low, users may abandon the system. Additionally, DevOps tools (such as Google Lighthouse) are currently used as an alternative to reviews, but while they can detect bugs and defects, they have the challenge of not being able to evaluate reviews by expected personas. [Means for solving the problem]

[0005] A first aspect of the technology of the present disclosure is a data processing device that includes an input unit that accepts specification information regarding the development content of an application, a processing unit that inputs the specification information and multiple personas that have been generated in advance for the review, along with instruction information that instructs a review of the application, into a generative AI model to obtain reviews of the application by the personas, and an output unit that outputs the reviews in a predetermined format.

[0006] A second aspect of the technology of the present disclosure is a data processing method in which a computer performs processing including accepting specification information regarding the development content of an application, inputting the specification information and multiple personas generated in advance for the review into a generative AI model along with instruction information instructing a review of the application, obtaining reviews of the application for the personas, and outputting the reviews in a predetermined format.

[0007] A third aspect of the technology of the present disclosure is a data processing program for causing a computer to execute a process including accepting specification information regarding the development content of an application, inputting the specification information and a plurality of personas generated in advance for the review into a generative AI model together with instruction information instructing a review of the application, obtaining reviews of the application for the personas, and outputting the reviews in a predetermined format. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a conceptual diagram illustrating an example of a configuration of a data processing system. [Figure 2] FIG. 2 is a conceptual diagram showing an example of main functions of a data processing device and a user terminal. [Figure 3] This is an image comparing the development process between the conventional method and this method. [Figure 4] FIG. 10 is a diagram for explaining an outline of a specification process. [Figure 5] 2 shows a schematic functional configuration of a specific processing unit of the data processing device. [Figure 6] This is an example of review analysis. [Figure 7] 10 is a diagram illustrating an example of an operational flow of specific processing by a data processing device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an example of an embodiment of a data processing device, a data processing method, and a program according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), or an APU (Accelerated Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] FIG. 1 shows an example of the configuration of a data processing system 10 according to the embodiment.

[0017] As shown in Fig. 1, the data processing system 10 includes a data processing device 12 and a user terminal 14. An example of the data processing device 12 is a server. An example of the user terminal 14 is a smartphone. In this embodiment, the data processing device 12 is an example of a "data processing device" according to the technology of the present disclosure.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the person 20 by outputting the data in a form of expression that the person 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the user terminal 14.

[0024] As shown in FIG. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "data processing program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a generative AI model 58. The generative AI model 58 is used by the specific processing unit 290.

[0026] The generative AI model 58 is a so-called generative AI (Artificial Intelligence). An example of the generative AI model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generative AI models. The generative AI model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the generative AI model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The generative AI model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0027] In the user terminal 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48. In addition, instruction information for the specific processing may be output from the user terminal 14 to the data processing device 12.

[0028] Next, the processing of the specific processing unit 290 when the data processing device 12 performs specific processing for reviewing the development content of an application will be described.

[0029] In the specific processing of this embodiment, a generative AI model 58 is used in the application development process to generate a persona for review, and the development content is reviewed. Figure 3 illustrates a comparison of the development process between the conventional method and the present method. In the conventional development flow, the development process is followed by testing, acceptance, release, and user review. In such a development flow, even if an unnecessary function is identified during the user review stage, it is difficult to review the function again because the function has already been implemented and released. In recent development processes, QA engineers have been reviewing developed functions. However, reviews by QA engineers require costs in terms of manpower and schedule, and can be difficult to implement. Therefore, in this method, as an example, a generative AI review using a persona generated by a generative AI is performed in the post-development process, thereby enabling development reviews to be realized at low cost and in a short period of time.

[0030] Fig. 4 is a diagram for explaining an overview of the identification process. Specifically, as shown in Fig. 4, the data processing device 12 of the present disclosure acquires specification information 70 including the source code of a developed application from the development platform 16. The development platform 16 stores version information such as the source code and images of the application as the specification information 70. The data processing device 12 generates a persona 72 for review. The data processing device 12 uses the specification information 70 and the persona 72 to generate a review of the developed application.

[0031] As shown in FIG. 5, the identification processing unit 290 includes an input unit 291, a persona generation unit 292, a processing unit 293, and an output unit 294.

[0032] The input unit 291 receives specification information 70 relating to the development content of an application. The specification information 70 is a version of source code, images, etc. to be reviewed. In , source code is managed individually for each version, and, for example, an updated version of source code is the subject of review. Furthermore, the specification information 70 may include, as information relating to the application screen, an image showing the interface screen of the display screen, screen operation information, screen transition information, etc. The screen operation information is, for example, information on the function of the screen UI where interactions (selection, display switching, voting, etc.) occur through operations on the screen.

[0033] The persona generation unit 292 uses the profile information to input instruction information instructing the generation of a persona based on the profile information and profile specification information into the generation AI model 58 to generate a persona 72. The profile specification information includes basic personal information such as occupation, gender, and age, as well as hobby / preference specifications, as information associated with the application. Since specifying all of the basic personal information is cumbersome, it is also possible to specify a range, type, and excluded items. For occupation, the target items and excluded items are specified; for gender, male / female; and for age, the age range. Hobbies / preferences may be specified based on the characteristics of the application. For example, for a music playback application, a favorite music genre is specified as information related to the application. For a food-related application, favorite dishes, groceries, etc. are specified as information related to the application. This allows the generation of a persona with perspectives that influence application reviews. The generated persona 72 includes the generated personal information and hobby / preference information. The personas 72 are generated for each persona as a persona image that is assumed to represent a single virtual user. Each persona 72 has personal information and hobby / preference information, such as, for example, "Persona A / Personal Information / Occupation: Business Manager, Gender: Male, Age: 45, ..." or "Persona B / Personal Information / Occupation: Housewife, Gender: Female, Age: 38, ...." Each persona is input into the generation AI model 58 to become data that can be reviewed from the perspective of that persona. Each persona 72 generated in this way is treated as attribute data for a single virtual user that has personal information and hobby / preference information, and is stored in a database in the storage 50.

[0034] The processing unit 293 inputs the specification information 70 and the persona 72, along with instruction information instructing a review, into the generative AI model 58 to obtain a review of the application by the persona. Here, the instruction information includes an instruction to output a review of the source code. In this case, the processing unit 203 obtains the persona's review of the application's source code based on the output from the generative AI model 58. If the instruction information includes an instruction regarding an evaluation of the application's functions, the processing unit 293 obtains a review including an evaluation of the functions. The evaluation of the functions can be an evaluation regarding whether the functions are necessary or not, or an evaluation regarding usability. The evaluation regarding whether the functions are necessary or not can be obtained as a graded evaluation, such as "unnecessary / slightly unnecessary / neither necessary nor necessary." In addition, an explanation of which parts of the functions were evaluated as unnecessary / necessary may be obtained together with the graded evaluation. Obtaining such evaluations as reviews makes it possible to identify functions that are difficult to use, functions that are rarely used / unnecessary, etc. Furthermore, if the specification information 70 includes information regarding screens, the processing unit 293 obtains a review including an evaluation of the screens. The evaluation of the screen can be output, for example, as an evaluation of the degree of preference for the screen design, an evaluation of the necessity / ease of the screen UI, and an evaluation of the necessity / ease of screen transitions.

[0035] The output unit 294 outputs the reviews in a predetermined format. The reviews may be displayed in a list for each persona, or may be displayed by switching between individual personas.

[0036] Furthermore, in the persona generation unit 292, the persona 72 generates personas for the QA engineer side who reviews the development content from a development perspective, and for the user side. The developer side may be generated as a first persona 72A, and the user side may be generated as a second persona 72B. In this case, the processing unit 293 acquires the reviews of the first persona 72A and the second persona 72B as reviews.

[0037] Furthermore, the output unit 294 may output the analysis results of the review. When performing an analysis, in the data processing device 12, the input unit 291 accepts a designation of an analysis for the review. The processing unit 293 further inputs the designation of the analysis to the generative AI model 58, and obtains the designated analysis results for the review. The output unit 294 outputs the analysis results together with the review.

[0038] FIG. 6 is an example of review analysis. In the example shown in FIG. 6, a radar chart shows the results of quantifying and analyzing reviews by category. In the example, analysis results 74 are displayed for each evaluation item of the application. As examples of evaluation items for the application, values ​​for "operability," "visibility," "efficiency of information acquisition," "fun," "accuracy of information," and "comfort" are output. Note that these evaluation items are merely examples, and other items may also be used. Furthermore, the analysis is not limited to evaluation items, and review trends may be analyzed based on basic personal information and hobbies / preferences of personas. Furthermore, in addition to obtaining individual reviews for personas, personas may be clustered by attributes, and review trends for personas for each cluster may be obtained as analysis results.

[0039] Next, the operation of the data processing system 10 will be described. An example of the flow of the specific processing will be described with reference to Fig. 5. The flow of the specific processing shown in Fig. 7 is an example of the "data processing method" according to the technology of the present disclosure.

[0040] In step S100, persona generation unit 29 uses the profile designation information to input instruction information instructing the generation of a persona in accordance with the profile information and the profile designation information to generative AI model 58, thereby generating persona 72. Note that the processing of this step may be omitted if persona 72 is generated in advance as pre-processing.

[0041] In step S102, the input unit 291 receives specification information 70 relating to the development content of the application.

[0042] In step S104, the processing unit 293 inputs the specification information 70 and the persona 72 together with instruction information instructing a review into the generative AI model 58, and obtains a review of the application by the persona.

[0043] In step S106, the output unit 294 outputs the review in a predetermined format, and the process ends.

[0044] As described above, the data processing system according to this embodiment makes it possible to obtain reviews from various personas that are expected for an application and to use the reviews as feedback for the development of the application.

[0045] Furthermore, by using generative AI to generate a large number of personas depicting user profiles with various attributes and automatically generating reviews based on the personas, it is possible to provide a virtual review platform. Furthermore, it is possible to obtain a large number of reviews of an application multiple times before release, which allows for anticipation of negative reviews and consideration of improvements and countermeasures.

[0046] One example of the target audience for this system is companies that develop and operate web systems and applications. Application modifications require consideration of the characteristics of users and competitors, making UI / UX changes an important decision point. It is also expected to be used by mid-sized and large companies that employ specialized QA teams as a countermeasure. It is also expected to be used by venture companies that want to collect reviews before releasing new products but find it difficult to hire QA or testers. Developers who are interested in technologies related to the company in question are also expected to be users.

[0047] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[0048] In the above embodiment, the case of reviewing the development content of an application has been described as an example, but the present invention is not limited to this. For example, the present method may be applied so that a review is performed using the design specifications and screen previews of the application in the review stage as the specification information 70.

[0049] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0050] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0051] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0052] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0053] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0054] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[0055] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0056] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0057] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0058] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0059] The following additional notes are provided regarding the above-described embodiments. <Appendix 1> an input unit that receives specification information regarding the development content of the application; a processing unit that inputs the specification information and a plurality of personas generated in advance for review into a generative AI model together with instruction information instructing a review of the application, and acquires reviews of the application by the personas; an output unit that outputs the review in a predetermined format; 2. A data processing device comprising:

[0060] <Appendix 2> further comprising a persona generation unit; The data processing device of claim 1, wherein the persona generation unit uses at least profile designation information including information associated with the application to input instruction information instructing the generation of a persona in accordance with the profile designation information and the profile designation information into a generative AI model to generate the persona.

[0061] <Appendix 2> The specification information uses at least information on source code acquired for the application from a predetermined development platform; the instruction information includes content instructing output of a review of the source code; 2. The data processing device of claim 1, wherein the processing unit obtains the persona's review of the source code of the application through output from the generative AI model.

[0062] <Appendix 3> The specification information uses at least information on source code acquired for the application from a predetermined development platform; the instruction information includes content instructing output of a review of the source code; 3. The data processing device of claim 1, wherein the processing unit obtains the persona's review of the source code of the application by output from the generative AI model.

[0063] <Appendix 4> the specification information includes an image showing a screen of the application; 4. The data processing device according to any one of appendices 1 to 3, wherein the processing unit acquires the reviews including at least quality details for an image showing the screen.

[0064] <Appendix 5> The specification information includes information about a screen of the application, 5. The data processing device according to any one of appendices 1 to 4, wherein the processing unit acquires the reviews including ratings for an image showing the screen.

[0065] <Appendix 6> the input unit accepts a specification of an analysis of the review; The processing unit further inputs the analysis specification into the generative AI model to obtain a specified analysis result for the review; 6. The data processing device according to any one of appendices 1 to 5, wherein the output unit outputs the analysis results together with the review.

[0066] <Appendix 7> the persona generation unit generates, as the personas, a first persona that performs a review from the perspective of development content including source code of the application, and a second persona that performs a review from the perspective of a user of the application; 3. The data processing device according to claim 2, wherein the processing unit acquires, as the reviews, reviews from the first persona and reviews from the second persona. [Explanation of symbols]

[0067] 10 Data Processing System 12 Data Processing Device 14 User terminal 290 Special Processing Department 291 Input section 292 Persona Generation Department 292 Processing section 294 Output Section< / url:>

Claims

1. an input unit that receives specification information regarding the development content of the application; a processing unit that inputs the specification information and a plurality of personas generated in advance for review into a generative AI model together with instruction information instructing a review of the application, and acquires reviews of the application by the personas; an output unit that outputs the review in a predetermined format; 2. A data processing device comprising:

2. further comprising a persona generation unit; 2. The data processing device according to claim 1, wherein the persona generation unit uses at least profile designation information including information associated with the application to input instruction information instructing the generation of a persona in accordance with the profile designation information and the profile designation information into a generative AI model to generate the persona.

3. The specification information uses at least information on source code acquired for the application from a predetermined development platform; the instruction information includes content instructing output of a review of the source code; The data processing device according to claim 1 , wherein the processing unit obtains the persona's review of the source code of the application by output from the generative AI model.

4. The instruction information includes an instruction regarding evaluation of the functionality of the application; The data processing device according to claim 1 , wherein the processing unit acquires the reviews including evaluations of the functions.

5. The specification information includes information about a screen of the application, The data processing device according to claim 1 , wherein the processing unit acquires the reviews including ratings of the screens.

6. the input unit accepts a specification of an analysis of the review; The processing unit further inputs the analysis specification into the generative AI model to obtain a specified analysis result for the review; The data processing device according to claim 1 , wherein the output unit outputs the analysis results together with the review.

7. the persona generation unit generates, as the personas, a first persona that performs a review from the perspective of development content including source code of the application, and a second persona that performs a review from the perspective of a user of the application; The data processing device according to claim 2 , wherein the processing unit acquires, as the reviews, reviews from the first persona and reviews from the second persona.

8. We accept specification information regarding the development of the application, Inputting the specification information and a plurality of personas pre-generated for review into a generative AI model together with instruction information instructing a review of the application, and obtaining reviews of the application for the personas; and outputting the review in a predetermined format.

9. We accept specification information regarding the development of the application, Inputting the specification information and a plurality of personas pre-generated for review into a generative AI model together with instruction information instructing a review of the application, and obtaining reviews of the application for the personas; and outputting the review in a predetermined format.

Images