Function map generating method and system

Abstract

To provide a method of and a system for generating a function map using an artificial intelligence model.SOLUTION: A function map generating method according to the present invention has step S310 of acquiring a difficult point and first data relating to the difficult point from a first response content of a first query corresponding to the difficult point, step S320 of acquiring a use target and second data relating to the use target from a second response content of a second query corresponding to the user target, function guidance step S331 of acquiring an implemented function and a kind of the target based on the difficult pint and the use target, function associating step S332 of acquiring a required function based on the kind of the target, function comparison step S333 of comparing meanings of the implemented function with the requested function to acquire a content of difference set, and function map generating step S340 of generating a function map based on the kind of the target, the implemented function and the content of the difference set.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to human-computer interaction mechanisms, and in particular to a method and system for generating functional maps based on artificial intelligence models. [Background technology]

[0002] In today's era of comprehensive digital transformation, a website's user interface (UI) and user experience (UX) are becoming increasingly important. UI and UX not only directly affect the user experience, but also directly relate to efficiency. For example, an administration website must display data according to importance and provide quick links to related data. Therefore, websites with convenient operating procedures and intuitive, easy-to-manage dashboards have become a key theme in webpage design. However, achieving these goals requires UI / UX designers to repeatedly interview customers and accurately understand their needs, which undoubtedly increases the time and cost of website development.

[0003] In a typical UI / UX design and development process, a UI / UX designer conducts a preliminary needs interview with the client, creates a function map for the website based on the type of function, such as image monitoring, device control, or event notification, and then creates an initial wireframe so the client can confirm the functionality. Wireframes have no visual elements and are intended to show the website's structure, functions, and procedures. If the client has new needs or opinions, the UI / UX designer conducts another interview, updates the function map, re-creates the wireframe, and repeats this process until an agreement is reached. Finally, the website development team moves on to the UI design stage based on the wireframe, creating mockups and prototypes. Summary of the Invention [Problem to be solved by the invention]

[0004] Throughout the design and development cycle, needs interviews are an important and unavoidable step in the entire development process. However, because customers may not understand their needs, multiple interviews are required to elicit core needs and supplement any necessary related information. Before proceeding with UI design and development, differences in understanding between the two parties often require revisions and reconfirmation until both parties reach an agreement. Therefore, needs interviews take a lot of time in the development cycle, and because they are cumbersome and not highly standardized, it is difficult to streamline them. [Means for solving the problem]

[0005] The present invention provides a method and system for generating functional maps based on artificial intelligence (AI), which can effectively reduce the time cost required for needs interviews.

[0006] The method for generating a function map based on an artificial intelligence model includes the following steps executed by a processor: In the first query step, an artificial intelligence model is used to obtain a difficulty point and first data related to the difficulty point from a first response content of a first query corresponding to the difficulty point; In the second query step, an artificial intelligence model is used to obtain a use object and second data related to the use object from a second response content of a second query corresponding to the use object; In the completeness determination step, the following steps are included: In the function induction step, an artificial intelligence model is used to obtain an implemented function and an object type based on the difficulty point and the use object; In the function association step, an artificial intelligence model is used to obtain a required function based on the object type; In the function comparison step, an artificial intelligence model is used to perform a semantic comparison between the implemented function and the required function to obtain the content of a difference set; In the function map generation step, a function map is generated based on the object type, the implemented function, and the content of the difference set.

[0007] In one embodiment of the present invention, the first query step includes: generating a prompt corresponding to a first response content; executing a noun capture program through an artificial intelligence model based on the prompt corresponding to the first response content to obtain a first noun response result; and executing a meaning capture program through an artificial intelligence model to obtain the difficulty point and first data related to the difficulty point based on the first response content and the first noun response result.

[0008] In one embodiment of the present invention, the second query step includes: generating a prompt corresponding to the second response content; executing a noun capture program through an artificial intelligence model based on the prompt corresponding to the second response content to obtain a second noun response result from the second response content; and executing a semantic capture program through the artificial intelligence model to obtain a target of use and second data related to the target of use based on the second response content and the second noun response result.

[0009] In one embodiment of the present invention, the feature map generation method further includes a third query step, in which the third query step includes: receiving a third response content of a third query corresponding to a data source; generating a prompt corresponding to the third response content; executing a noun capture program through an artificial intelligence model based on the prompt corresponding to the third response content to obtain a third noun response result from the third response content; and executing a semantic capture program through the artificial intelligence model to obtain source information based on the third response content and the third noun response result.

[0010] In one embodiment of the present invention, the functional map generating step further comprises updating the functional map based on the source information.

[0011] In one embodiment of the present invention, the function map generation step further includes generating prompts corresponding to the difficulties and the target of use, and using an artificial intelligence model to execute a function guidance program based on the prompts to obtain the performed functions and the target types.

[0012] In one embodiment of the present invention, the function associating step includes generating a prompt corresponding to the type of object, and using an artificial intelligence model to run a function associating program based on the prompt to obtain the requested function.

[0013] In one embodiment of the present invention, the function map generation step includes generating a function map based on the implemented function and the type of object after the function induction step, and updating the function map based on the contents of the difference set after the function comparison step.

[0014] The functional map generation system based on an artificial intelligence model of the present invention includes an artificial intelligence model, an interactive interface, and a processor coupled to the artificial intelligence model and the interactive interface. In response to the interactive interface receiving a first response content of a first query corresponding to a difficulty point, the processor is configured to use the artificial intelligence model to obtain the difficulty point and first data related to the difficulty point from the first response content. In response to the interactive interface receiving a second response content of a second query corresponding to a use object, the processor is configured to use the artificial intelligence model to obtain second data representing the use object and related to the use object from the second response content. The processor is further configured to use the artificial intelligence model to obtain an implementation function and an object type based on the difficulty point and the use object, obtain a request function based on the object type, use the artificial intelligence model to perform a semantic comparison between the implementation function and the request function, obtain the content of a difference set, and generate a functional map based on the object type, the implementation function, and the content of the difference set. [Effects of the Invention]

[0015] Based on the above, by using an artificial intelligence model to capture important information and organize it into a function map, customer needs can be grasped quickly and accurately, reducing the number of multiple interviews between designers and customers and effectively reducing the time cost involved in needs interviews. [Brief explanation of the drawings]

[0016] [Figure 1] FIG. 1 is a block diagram of a functional map generation system according to one embodiment of the present invention. [Figure 2] 1 is a schematic diagram of a robot structure according to one embodiment of the present invention; [Figure 3] 1 is a flowchart of a method for generating a functional map according to one embodiment of the present invention. [Figure 4] FIG. 1 is a schematic structural diagram of functional map generation according to an embodiment of the present invention; [Figure 5A] FIG. 1 is a schematic diagram of a plurality of prompt templates according to one embodiment of the present invention. [Figure 5B] FIG. 1 is a schematic diagram of a plurality of prompt templates according to one embodiment of the present invention. [Figure 5C] FIG. 1 is a schematic diagram of a plurality of prompt templates according to one embodiment of the present invention. [Figure 6] FIG. 2 is a schematic diagram of a question generation program according to an embodiment of the present invention. [Figure 7] 1 is a schematic structural diagram of a noun capture program according to an embodiment of the present invention; [Figure 8] 1 is a schematic structural diagram of a semantic capture program according to an embodiment of the present invention; [Figure 9] 2 is a schematic structural diagram of a function guidance program according to an embodiment of the present invention; [Figure 10] FIG. 2 is a schematic structural diagram of a function association program according to an embodiment of the present invention; [Figure 11A] 2 is a schematic diagram of the content presented by an interactive interface according to one embodiment of the present invention; [Figure 11B]2 is a schematic diagram of the content presented by an interactive interface according to one embodiment of the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0017]

[0023] Figure 1 is a block diagram of a functional map generation system according to one embodiment of the present invention. Please refer to Figure 1. The functional map generation system includes a processor 110, an interactive interface 120, and an artificial intelligence (AI) model 130. The processor 110 is coupled to the interactive interface 120 and the AI model 130.

[0018] The processor 110 may be, for example, a central processing unit (CPU), a physical processing unit (PPU), a programmable microprocessor, an embedded control chip, a digital signal processor (DSP), an application specific integrated circuit (ASIC), or other similar device.

[0019] The interactive interface 120 is a user interface (UI) that is a medium for interaction and information exchange between the processor 110 and a user. For example, the interactive interface 120 includes a human-computer interaction (HCI) and a graphical user interface (GUI). In one embodiment, the interactive interface 120 may be realized by a display and an input device, or may be realized by a touch screen.

[0020] The AI model 130 may be located in the same electronic device as the processor 110. Alternatively, the AI model 130 and the processor 110 may be located in different electronic devices and communicatively connected via wired or wireless means. The AI model 130 is, for example, a large-scale language model (LLM), which is composed of an artificial neural network with many parameters and is trained on a large amount of unlabeled text using self-supervised or semi-supervised learning. Examples of LLMs include ChatGPT, GPT4, LLaMA-65B, and PaLM-62B. All of these models have achieved very good results in various natural language processing (NLP) evaluations. Evaluation items include common sense reasoning, closed-book question-and-answering, reading comprehension, mathematical reasoning, program code generation, and massive multitask language understanding (MMLU). In recent years, major technology leaders have also been actively reducing LLMs while incorporating more powerful features.

[0021] In one embodiment, the UI / UX designer team collects past interview data, organizes three important pieces of information (such as difficulties, target users, and related data) and the type of website and its implementation functions to be finally realized, and constructs an input corpus and output results (including an output corpus). The inputs used to train the AI model 130 are the three important pieces of information. The outputs used to train the AI model 130 are the type of website and its implementation functions. The results obtained through subsequent analysis using the AI model 130 can be fed back to the AI model 130 to improve the accuracy of the AI model 130.

[0022] The AI model 130 employed in this embodiment has the following functions: sentence decomposition, which can decompose sentence structures such as nouns and verbs; semantic understanding, which can understand context, analyze meaning, and summarize; general expertise for learning knowledge through training using a large amount of teaching materials in a wide range of fields; topic modeling, which can analyze multiple keywords and induce corresponding topics into groups; association, which can associate things related to various levels according to the topic; word embedding, which can convert words and sentences into a semantic distance space; and highly anthropomorphic sentence generation, which can generate sentences according to situations, emotions, roles, etc.

[0023] The AI model 130 has strong generalization capabilities. When the AI model 130 is applied to a different task, retraining is not required; simply providing relevant prompts (including task descriptions, examples, output formats, etc.) is sufficient to output corresponding results. This method is called in-context learning, and the output results vary depending on the input prompts. Prompt design is also called prompt engineering. Prompt engineering is performed by the processor 110. Through design, one or more corresponding prompts are selected or generated according to the current status (such as the function guidance step S331, the function association step S332, the function comparison step S333, and the third query step S350). Finally, the AI model 130 can be driven through the prompts to obtain desired results.

[0024] Figure 2 is a schematic diagram of a robot structure according to one embodiment of the present invention. This embodiment includes three roles: a user, a robot 200, and an AI model 130 (see Figure 1). Based on professional knowledge and experience in UI / UX design, the robot 200 guides the user to answer questions and uses the functions of the AI model 130 to obtain important information required for website design, such as the data to be displayed, data sources, usage scenarios, and development functions. The key information is then organized into a feature map. Finally, after user confirmation, the final version of the feature map is generated.

[0025] See Figure 2. The robot 200 includes a question query module 210, a response analysis module 220, and a map construction module 230. The modules are, for example, software modules consisting of one or more program codes stored in a memory. The memory may be, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk, or other similar device, or a combination of these devices. The question query module 210, the response analysis module 220, and the map construction module 230 may also be realized by hardware chips or circuits.

[0026] The processor 110 drives the question query module 210, the response analysis module 220, and the map construction module 230 to perform corresponding functions. The question query module 210 is configured to call the AI model 130 to generate corresponding questions according to the key information. The response analysis module 220 is configured to call the AI model 130 to analyze the content of the response to the query. The map construction module 230 is configured to call the AI model 130 to find a feature list and construct a feature map based on the result obtained by the response analysis module 220.

[0027] For ease of understanding, FIGS. 3 to 11B are listed below and explained together with FIGS.

[0028] FIG. 3 is a flowchart of a method for generating a functional map according to an embodiment of the present invention. FIG. 4 is a schematic structural diagram of generating a functional map according to an embodiment of the present invention. FIGS. 5A to 5C are schematic diagrams of a plurality of prompt templates according to an embodiment of the present invention. FIG. 6 is a schematic structural diagram of a question generation program according to an embodiment of the present invention. FIG. 7 is a schematic structural diagram of a noun capture program according to an embodiment of the present invention. FIG. 8 is a schematic structural diagram of a meaning capture program according to an embodiment of the present invention. FIG. 9 is a schematic structural diagram of a function guidance program according to an embodiment of the present invention. FIG. 10 is a schematic structural diagram of a function association program according to an embodiment of the present invention. FIGS. 11A and 11B are schematic diagrams of content presented by an interactive interface according to an embodiment of the present invention.

[0029] First, please refer to FIG. 3. The function map generation method includes a first query step S310, a second query step S320, a completeness determination step S330, and a function map generation step S340. The completeness determination step S330 includes a function deriving step S331, a function association step S332, and a function comparison step S333. The function map generation method may further include a third query step S350. The third query step S350 is not a required step and may or may not be added depending on the situation.

[0030] See FIG. 4. The first query Q1, the second query Q2, and the third query Q3 used in the first query step S310, the second query step S320, and the third query step S350 are generated by the question query module 210. The question type of the first query Q1 is a difficulty, the question type of the second query Q2 is a target (including the purpose of use and the target user), and the question type of the third query Q3 is a data source. Specifically, the question query module 210 selects a corresponding prompt template according to the question type. Then, the AI model 130 generates the corresponding first query Q1, the second query Q2, or the third query Q3. The questions generated by the AI model 130 may be personified, including a dynamic, informal, polite, and service-oriented tone.

[0031] See FIG. 6. Taking the first query Q1, which corresponds to a difficulty, as an example, the query module 210 employs a prompt template 510 according to the question type "Difficulties the website needs to solve" and introduces key information corresponding to the "difficulty." At the same time, previously collected information, such as proper nouns and fields, can be supplemented in context to generate the final prompt. After deciding to employ the prompt template 510, the content of the question type "Difficulties the website needs to solve" is entered in the field 511 of the prompt template 510 to obtain a prompt. Then, the AI model 130 executes the question generation program P0 to generate the corresponding first query Q1 based on the prompt. For example, as shown in FIG. 11A, the first query Q1 may read, "To better assist you in website development, we need to understand the difficulties you are facing so that we can provide you with the most effective support. Please share some specific challenges the website needs to solve so that we can provide more specific advice and assistance." The second query Q2 and the third query Q3 can be derived analogously.

[0032] After generating the query, the question query module 210 submits the query (first query Q1, second query Q2, or third query Q3) on the interactive interface 120 and receives a corresponding response content (first response content R1, second response content R2, or third response content R3) through the interactive interface 120. Taking FIG. 11A as an example, after the interactive interface 120 submits the first query Q1, the first response content R1 is received through the interactive interface 120.

[0033] Referring to Figures 3 and 4, in the first query step S310, the processor 110 uses the AI model 130 to obtain the difficulty point and first data related to the difficulty point from the first response content R1 of the first query Q1 corresponding to the difficulty point, and stores the first data in the data and source database D1.

[0034] 7, the response analysis module 220 selects a prompt template 520 based on a first response content R1, then embeds the first response content R1 into an area 521 of the prompt template 520 to generate a prompt corresponding to the first response content R1, and then executes a noun capture program P1 based on the prompt corresponding to the first response content R1 through the AI model 130 to obtain a first noun response result.

[0035] The noun capture program P1 invokes the AI model 130 via a prompt, captures proper nouns, odd nouns, and branch nouns that appear in the first response content R1, and explains their meanings. Next, in the "parsing" process, the response analysis module 220 determines whether the noun list included in the first noun response result contains known nouns (nouns that the AI model 130 knows and can interpret) or unknown nouns. For example, whether a noun is an unknown noun can be determined by searching for the presence of strings such as "online search" or "search online" in the first noun response result (as shown in Example 1-1 below). If the noun is an unknown noun, a search engine may be further used to obtain a corresponding explanation. The meaning of the noun and its corresponding explanation are then confirmed. For example, the noun and its explanation are presented in the interactive interface 120 for the user to confirm. Finally, the results are stored in the noun database D2. If no relevant explanation is found, a user-provided explanation may also be received through the interactive interface 120 .

[0036] Example 1-1

[0037] [Table 1]

[0038] That is, if there is an unknown noun that the AI model 130 cannot understand, it searches for the corresponding meaning through a search engine, confirms the meaning, and provides it to the user for reconfirmation. Regardless of whether the finally obtained noun is a known noun or an unknown noun, the meaning, including corrections, is displayed to the user for confirmation.

[0039] Furthermore, during the "analysis" process, if the response analysis module 220 determines that there are currently no proper nouns, unambiguous nouns, or strange nouns by searching for default strings such as "does not appear," "cannot be found," "did not appear," or "could not be found," the process ends without proceeding to the next step. This means that the meaning confirmation step is not entered, and the list in the noun database D2 is not updated. For example, referring to Example 2-1, the first noun response result indicates "does not appear," so it is determined that there are no proper nouns, unambiguous nouns, or strange nouns.

[0040] Example 2-1

[0041] [Table 2]

[0042] Next, referring to FIG. 8, the response analysis module 220 executes the meaning capture program P2 via the AI model 130 to obtain the difficulty points and first data related to the difficulty points based on the first response content R1 and the first noun response result. The meaning capture program P2 aims to capture key information through semantic understanding by the AI model 130. The "prompt generation" and the meaning capture program P2 can obtain different results based on the "information type" input. For example, a prompt template is selected according to the "information type," and the AI model 130 analyzes the output semantic response result according to the "information type."

[0043] For example, referring to Example 2-2 below, the response analysis module 220 selects a prompt template 530 based on the information type. Then, it enters a first response content R1 in the prompt template 530's field 531, enters the question type (e.g., "What are the difficulties the website needs to solve?") in the field 532, and generates a prompt for semantic capture. Then, it executes the noun capture program P1 based on the generated prompt via the AI model 130 to obtain a first semantic response result (including, for example, "Difficulty: ..." and "Data: ..."). Then, it confirms the meaning of the first semantic response result. For example, the first semantic response result is presented to the interactive interface 120 for the user to confirm.

[0044] Example 2-2

[0045] [Table 3]

[0046] In another embodiment, referring to Example 1-2 below, a first response content R1 is entered in area 551 of a prompt template 550, a question type (e.g., "the difficulty the website needs to solve") is entered in area 553, and a proper noun and its description (e.g., "aaaaaa: refers to the cyclical growth rate of a tumor, and its size is calculated once a month") is entered in area 552, thereby generating a prompt for semantic capture. Then, a noun capture program P1 is executed based on the generated prompt via the AI model 130 to obtain a first semantic response result (including "Difficulty: ...," "Data: ...," etc.). The purpose of adding the collected proper nouns to the prompt is to avoid erroneous capture or missing capture.

[0047] Example 1-2

[0048] [Table 4]

[0049] Next, referring to Figures 3 and 4, in the second query step S320, the processor 110 uses the AI model 130 to obtain the target of use and second data related to the target of use from the second response content R2 of the second query Q2 corresponding to the target of use, and stores the second data in the data and source database D1.

[0050] The response analysis module 220 generates a prompt corresponding to the second response content R2, and then executes the noun capture program P1 via the AI model 130 based on the prompt corresponding to the second response content R2 to obtain a second noun response result. The response analysis module 220 then executes the meaning capture program P2 via the AI model 130 to obtain a target of use and second data related to the target of use based on the second response content R2 and the second noun response result. Here, the target of use includes a target user and a purpose of use.

[0051] The processes of the noun capture program P1 and the meaning capture program P2 executed in the second query step S320 are similar to those in the first query step S310. First, the noun capture program P1 determines whether a proper noun is present in the second response content R2. For example, as shown in Example 3 below, assume that the second response content R2 is "This website is for internal monitoring purposes only and is not publicly accessible." The noun capture program P1 determines that the provided content does not contain a proper noun, an unusual noun, or an unambiguous noun. The response analysis module 220 employs a prompt template 540, enters the second response content R2 in field 541 of the prompt template 540, and enters the type of question (e.g., "Who uses the website? What is the purpose?") in field 542 to generate a corresponding prompt. Then, the meaning capture program P2 is executed via the AI model 130 to acquire the target of use and the second data.

[0052] Example 3

[0053] [Table 5]

[0054] In a third query step S350, the processor 110 uses the AI model 130 to obtain a data source from the third response content R3 of the third query Q3 corresponding to the data source. After receiving the third response content R3 of the third query Q3 corresponding to the data source, the processor 110 generates a prompt corresponding to the third response content R3. The processor 110 executes the noun capture program P1 based on the corresponding prompt via the AI model 130 to obtain a third noun response result from the third response content R3. The processor 110 executes the meaning capture program P2 via the AI model 130 to obtain source information based on the third response content R3 and the third noun response result, and stores the source information in the data and source database D1.

[0055] In a third query step S350, processor 110 queries the user for data sources according to the first data obtained in the first query step S310 and the second data obtained in the second query step S320. A response from the user is obtained to determine whether the acquisition of sources is complete. If the acquisition is not complete, the information is first stored in a database, and another query is generated using question query module 210, as shown in Examples 4 and 5 below, and the cycle continues in this order until acquisition of all data sources is complete.

[0056] Example 4

[0057] [Table 6]

[0058] Example 5

[0059] [Table 7]

[0060] The processes of the noun capture program P1 and the meaning capture program P2 executed in the third query step S350 are similar to those of the first query step S310. First, the noun capture program P1 determines whether a proper noun is present in the second response content R2. Then, in the meaning capture program P2, the response analysis module 220 employs the prompt template 550, enters the third response content R3 into the field 561 in the prompt template 560, and enters the first data and the second data into the field 562 to generate a corresponding prompt. Then, based on the prompt, the noun capture program P1 is executed via the AI model 130 to obtain source information.

[0061] Next, the process enters the completeness determination step S330. In the function guidance step S331, the processor 110 uses the AI model 130 to obtain the performed function and object type based on the difficulty points and the use object. The map construction module 230 generates a prompt corresponding to the difficulty points and the use object, and then uses the AI model 130 to execute the function guidance program P3 based on the prompt to obtain the performed function and object type.

[0062] 9, the map construction module 230 selects a prompt template 570, enters the difficulty in area 571, and enters the usage object (purpose and object) in area 572 to generate a corresponding prompt. Then, the AI model 130 executes the function guidance program P3 based on the prompt to obtain the performed function and the object type. The AI model 130 can effectively guide the performed function and analyze the object type (e.g., website type). The AI model 130 analyzes and outputs the performed function and website type using "functional requirements: ..." and "website type," as shown in Example 6.

[0063] Example 6

[0064] [Table 8]

[0065] In a function associating step S332, the processor 110 obtains a required function based on the object type using the AI model 130. The map construction module 230 generates a prompt corresponding to the object type, and uses the AI model 130 to execute the function associating program P4 based on the prompt to obtain the required function.

[0066] 10 and Example 7, the map construction module 230 selects a prompt template 580, fills in the object type in the field 581, and generates a corresponding prompt. It then utilizes the general domain knowledge capabilities of the AI model 130 to associate other request functions based on the object type to complement the expertise the user does not possess.

[0067] Example 7

[0068] [Table 9]

[0069] The AI model 130 uses professional associations to acquire required functions related to the implementation. Because the AI model 130 has strong associative ability, the acquired prompt states that the acquired required functions are classified according to importance and only the required functions with high importance are output. However, this is not limited to this and can be determined according to requirements.

[0070] Then, in a function comparison step S333, the processor 110 executes the function comparison program P5 using the AI model 130 to perform a semantic comparison between the implemented functions and the requested functions, and obtains the contents of the difference set. For example, after obtaining the "requested functions" and "implemented functions," the AI model 130's word embedding capability is used to perform the semantic comparison. The main purpose of this process is to find common parts by adding the "requested functions" actually used in implementation to the "implemented functions" proposed by the user. To prevent overlap between the "requested functions" and the "implemented functions," the function comparison step S333 deletes overlapping items between the "requested functions" and the "implemented functions," and obtains and outputs the contents of the difference set.

[0071] For example, as shown in Example 6, the requested functions based on the user's response include integrating park information from various departments and tracking total number of visitors, total number of occupants, and average length of stay. The requested functions obtained by association with AI model 130 are shown in Example 7 and include user authentication and authorization management, visualization of real-time monitoring data, an alarm and notification system, and logging and auditing functions. After comparison, the contents of the difference set include user authentication and authorization management, visualization of real-time monitoring data, an alarm and notification system, and logging and auditing functions.

[0072] Then, in step S340, the processor 110 generates a function map based on the object type, the implemented function, and the content of the difference set. Furthermore, after obtaining the object type and the implemented function, the processor 110 may pre-construct the function map FM. After obtaining the content of the difference set, the processor 110 adds the content of the difference set to update the function map FM. Furthermore, after obtaining source information, the processor 110 updates the function map FM based on the source information.

[0073] The Functionality Map FM consists of four parts: website type, functions, data, and existing systems and processes. The Functionality Map FM is presented in the form of a Mind Map, organized from abstract to concrete. The website type is the core and top layer of the Functionality Map FM, determining the overall direction of the website. The second layer contains the functional items required to build the website based on the Functionality Implementation Program P3 and Functionality Association Program P4.

[0074] 11A and 11B, this embodiment illustrates the content presented by the interactive interface 120 with a website design. First, the processor 110 uses the question query module 210 to call the AI model 130 to generate a first query Q1 to inquire about pain points that the website needs to solve, and submits the first query Q1 to the interactive interface 120. Then, the processor 110 receives a first response R1 corresponding to the first query Q1 through the interactive interface 120. Then, the processor 110 uses the response analysis module 220 to call the AI model 130 to obtain the pain points and first data, and generates corresponding confirmation information A1 based on the pain points and the first data presented in the interactive interface 120 for user confirmation.

[0075] Next, the processor 110 uses the question query module 210 to invoke the AI model 130 to generate a second query Q2 to inquire about the use object (purpose and target) of the website, which is presented on the interactive interface 120. Then, the processor 110 receives a second response content R2 corresponding to the second query Q2 via the interactive interface 120. Thereafter, the processor 110 uses the response analysis module 220 to invoke the AI model 130 to obtain the use object (purpose and target) and second data, and generate corresponding confirmation information A2 based on the use object and the second data, which is presented on the interactive interface 120 for user confirmation.

[0076] Then, the processor 110 uses the question query module 210 to invoke the AI model 130 to generate a third query Q3-1 to query the data source, and submits the third query Q3-1 to the interactive interface 120. Then, the processor 110 receives corresponding response content R3-1 via the interactive interface 120. Then, the processor 110 uses the response analysis module 220 to invoke the AI model 130 to obtain source information, and generates corresponding confirmation information A3-1 based on the source information, which is presented to the interactive interface 120 for user confirmation.

[0077] In addition, because the response content R3-1 does not completely answer the source of all the data, the processor 110 uses the question query module 210 to invoke the AI model 130 to generate a fourth query Q3-2 that queries the data sources, and submits the fourth query Q3-2 to the interactive interface 120. Then, the processor 110 receives the corresponding reply content R3-2 via the interactive interface 120. Thereafter, the processor 110 uses the response analysis module 220 to invoke the AI model 130 to obtain source information, and generates corresponding confirmation information A3-2 based on the source information, which is presented to the interactive interface 120 for user confirmation.

[0078] The processor 110 then uses the map construction module 230 to invoke the AI model 130 to generate functional map information A4 corresponding to the functional map, and presents the functional map information A4 on the interactive interface 120 for user confirmation.

[0079] The above embodiment can be divided into the following four stages.

[0080] In the first stage, in a first query step S310, the robot 200 queries and captures the difficulties that the website needs to solve and captures keywords of data and files mentioned in the response content. In a second query step S320, the robot 200 queries and captures the target and purpose of using the website. Then, in a function guidance step S331, the robot 200 analyzes the type of website (target type) through the AI model 130 based on the information captured in the first query step S310 and the second query step S320, obtains the implemented functions corresponding to the website type, and constructs a preliminary function map FM.

[0081] In the second stage, in the function association step S332, the robot 200 calls the AI model 130 based on the type of website to associate common required functions with that type of website, divides them according to importance, obtains the most important functions, and compares the completeness of the required functions with the previously obtained performed functions. If it is found that the performed functions obtained in the function induction step S331 are missing, the function map FM is updated. At this point, the data capture of the functions and the function map FM is complete.

[0082] In the third stage, in addition to the key information captured in the second query step S320 of the first stage, in order to further capture source information and update the function map FM, the robot 200 captures keywords of data and files and sends them to the third query step S350 to query the source information of the data and files.

[0083] In the fourth stage, the generated functional map FM is presented to the user for confirmation. If there are no problems, the functional map FM becomes the final version. The UI / UX designer will then receive the functional map FM for website design.

[0084] In one embodiment, the function map FM generated by the processor 110 may be imported into a prototype website development platform with AI capabilities to generate a prototype website program code. The processor 110 then packages the website program code, deploys it to a cloud environment through a compilation engine, and records the browsing URL. The processor 110 then returns the browsing URL to the user via the robot 200 so that the user can further browse the web page. For example, after the robot 200 records the browsing URL, it packages the browsing URL (digital signal) into a logical set of transmission data (i.e., a data frame), drives a communication chip or communication circuit, and transmits the transmission data to a pre-designated electronic device associated with the user via email, short message service (SMS), push technology, etc.

[0085] In summary, the system of the present invention can operate 24 hours a day, improving designers' work efficiency. Furthermore, the present invention uses an AI model with deep conversational capabilities and a humanized speech pattern, providing a better customer experience than traditional robots. Based on the designer's expertise, the AI model can effectively capture important information. The proper noun understanding mechanism quickly resolves misunderstandings between the two parties and improves the efficiency of identifying needs. Directly generating a feature map allows designers to bypass the initial needs research period and directly address clear needs, accelerating the entire design and development process. [Industrial Applicability]

[0086] The method and system for generating functional maps based on artificial intelligence models can be applied to UI / UX design and development procedures to create mockups and prototypes. [Explanation of symbols]

[0087] 110: Processor 120: Interactive Interface 130: AI model 200:Robot 210: Question Query Module 220: Response analysis module 230: Map Building Module 510~580: Prompt template 511, 521, 531, 532, 541, 542, 551, 552, 553, 561, 562, 571, 572, 581: Area A1, A2, A3-1, A3-2: Confirmation information A4: Functional map information D1: Data and source databases D2: Noun database FM: Functional Map Q1: First query Q2: Second query Q3: Third query P0: Question generator P1: Noun capture program P2: Semantic Capture Program P3: Functional induction program P4: Function Association Program P5: Functional comparison program R1: First response R2: Second response R3: Third response S310: First query step S320: Second query step S330: Completeness determination step S331: Function induction step S332: Function association step S333: Function comparison step S340: Functional map generation step S350: Third query step

Claims

1. 1. A method for generating a functional map based on an artificial intelligence model, comprising the steps of: a first query step of acquiring the difficulty points and first data related to the difficulty points from a first response content of a first query corresponding to the difficulty points using the artificial intelligence model; a second query step of acquiring the target of use and second data related to the target of use from a second response content of a second query corresponding to the target of use using the artificial intelligence model; An integrity determination step, a function guiding step of using the artificial intelligence model to obtain an implementation function and an object type according to the difficulty and the use object; a function association step of obtaining a required function based on the object type using the artificial intelligence model; a function comparison step of performing a semantic comparison between the implemented function and the requested function using the artificial intelligence model to obtain the contents of a difference set; and generating a functional map based on the object type, the performed function, and the content of the difference set. the completeness determination step; A method for generating a feature map, comprising:

2. The first query step comprises: generating a prompt corresponding to the first response; Executing a noun capture program through the artificial intelligence model based on the prompt corresponding to the first response content to obtain a first noun response result; Executing a meaning capture program through the artificial intelligence model, and obtaining the difficulty points and first data related to the difficulty points based on the first response content and the first noun response result; Including, The second query step comprises: generating a prompt corresponding to the second response; Executing the noun capture program through the artificial intelligence model based on the prompt corresponding to the second response content to obtain a second noun response result from the second response content; Executing the semantic capture program through the artificial intelligence model, and acquiring the target of use and second data related to the target of use based on the second response content and the second noun response result; Including, The method of claim 1 .

3. a third query step, The first query step comprises: receiving a third response content of a third query corresponding to the data source; generating a prompt corresponding to the third response; Executing the noun capture program through the artificial intelligence model based on the prompt corresponding to the third response content to obtain a third noun response result from the third response content; Executing the semantic capture program through the artificial intelligence model to obtain source information based on the third response content and the third noun response result; Including, The functional map generating step includes: further comprising updating the functional map based on the source information. The method of generating a functional map according to claim 2 .

4. The function induction step includes: generating prompts corresponding to the difficulty and the intended use; Using the artificial intelligence model, execute a function guidance program based on the prompt to obtain the performed function and the object type; Including, The function associating step includes: generating a prompt corresponding to the type of object; Executing a function association program using the artificial intelligence model based on the prompt to obtain a requested function; Including, The functional map generating step includes: After the function induction step, generating the function map based on the performed function and the type of the object; updating the functional map after the functional comparison step based on the contents of the difference set; Including, The method of claim 1 .

5. Artificial intelligence models and An interactive interface; a processor coupled to the artificial intelligence model and the interactive interface; Including, In response to the interactive interface receiving a first response content to a first query corresponding to a difficulty point, the processor is configured to use the artificial intelligence model to obtain the difficulty point and first data related to the difficulty point from the first response content; In response to the interactive interface receiving a second response content of a second query corresponding to a target use, the processor is configured to use the artificial intelligence model to obtain second data representing the target use and related to the target use from the second response content; The processor further comprises: Using the artificial intelligence model, obtain the implementation function and object type according to the difficulty and the application object; Using the artificial intelligence model, obtain a required function based on the object type; Using the artificial intelligence model, a semantic comparison is made between the implemented function and the requested function to obtain the content of the difference set; configured to generate a functional map based on the object type, the performed function, and the content of the difference set; A functional map generation system based on an artificial intelligence model.

Images