CN117111902A - AI intelligent software development method and device - Google Patents

AI intelligent software development method and device Download PDF

Info

Publication number
CN117111902A
CN117111902A CN202311385942.1A CN202311385942A CN117111902A CN 117111902 A CN117111902 A CN 117111902A CN 202311385942 A CN202311385942 A CN 202311385942A CN 117111902 A CN117111902 A CN 117111902A
Authority
CN
China
Prior art keywords
module
function
technical
determining
design
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202311385942.1A
Other languages
Chinese (zh)
Other versions
CN117111902B (en
Inventor
王福民
梁志强
冀单单
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Hengxin Qihua Information Technology Co ltd
Original Assignee
Beijing Hengxin Qihua Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Hengxin Qihua Information Technology Co ltd filed Critical Beijing Hengxin Qihua Information Technology Co ltd
Priority to CN202311385942.1A priority Critical patent/CN117111902B/en
Publication of CN117111902A publication Critical patent/CN117111902A/en
Application granted granted Critical
Publication of CN117111902B publication Critical patent/CN117111902B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/20—Software design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/3332—Query translation
    • G06F16/3334—Selection or weighting of terms from queries, including natural language queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F8/00—Arrangements for software engineering
    • G06F8/10—Requirements analysis; Specification techniques
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Databases & Information Systems (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Stored Programmes (AREA)

Abstract

The application discloses an AI intelligent software development method and a device, wherein the method can be applied to a server and comprises the following steps: acquiring voice input data of a user, identifying the voice input data, obtaining design text data, wherein the voice input data is used for designing an application module; analyzing the design text data, determining a module design scheme of the application module, and designing a module structure diagram according to the module design scheme; displaying a module architecture diagram to a user, acquiring a confirmation request of the user for the module architecture diagram, decomposing according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module; and determining the function provider corresponding to each function node diagram, and acquiring the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.

Description

AI intelligent software development method and device
Technical Field
The application relates to the technical field of computers, in particular to an AI intelligent software development method and device.
Background
In the existing software development method, a module architecture diagram of each application module of an application program is designed according to requirements, then the module architecture diagram is further disassembled into a plurality of small functional nodes, and a developer designs a corresponding function instance module (obtained by carrying out instantiation processing such as programming) to form a corresponding application module.
In the manner described above, however, it is common for a worker to develop from scratch, many existing functional instance modules have been developed and a great deal of repetitive work has been done by the staff.
Disclosure of Invention
The application provides an AI intelligent software development method and device, which can reduce the workload of staff.
In order to solve the technical problems, the application is realized as follows:
in a first aspect, the present application provides an AI intelligent software development method, applied to a server, the method comprising: acquiring voice input data of a user, and identifying the voice input data to obtain design text data, wherein the voice input data is used for designing an application module; analyzing the design text data, determining a module design scheme of the application module, and designing a module structure diagram according to the module design scheme; displaying a module architecture diagram to a user, acquiring a confirmation request of the user for the module architecture diagram, decomposing according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module; and determining the function provider corresponding to each function node diagram, and acquiring the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.
Further, the analyzing the design text data to determine a module design scheme includes: identifying technical keywords in the design text data according to a pre-trained identification model; acquiring a first interactive sentence related to a technical keyword, and outputting the first interactive sentence to a user; receiving first feedback information of a user for a first interactive sentence, determining a design scheme of a technical unit corresponding to a technical keyword according to the first feedback information, wherein the technical keyword corresponds to the technical unit, the technical unit is used for forming an application module, and the functional node is formed by at least one technical unit; according to the design scheme of each technical unit, determining the module design scheme.
Further, the pre-trained recognition model is further configured to recognize parameter related information corresponding to a technical keyword in the design text data, and the obtaining a first interaction sentence related to the technical keyword includes: determining given parameter information in the design text data according to the parameter related information; acquiring technical parameter information corresponding to technical keywords, and classifying the technical parameter information according to parameter related information identified by a pre-trained identification model to obtain first parameter information of given parameters and second parameter information without parameters; and acquiring a first interactive statement corresponding to the second parameter information.
Further, the method comprises the steps of, the method further includes the process of training the recognition model: acquiring names of technical keywords, alternative names of the technical keywords, definition information of the technical keywords and functional description information of the technical keywords as model input data, and the names of the technical keywords are used as labeling data; inputting the model input data into the recognition model for recognition to obtain a recognition result; and adjusting the recognition model according to the recognition result and the labeling data to determine a trained recognition model, wherein the trained recognition model is used for mapping the names of the recognized technical keywords, the alternative names of the technical keywords, the definition information of the technical keywords and the function description information of the technical keywords into the technical keywords.
Further, the method further comprises: acquiring related parameter information of the technical keywords, and storing the related parameter information into a parameter information base; the obtaining technical parameter information corresponding to the technical keywords comprises the following steps: technical parameter information of the technical keywords is extracted from the parameter information base.
Further, the determining a module design according to the design of each technical unit includes: acquiring connection parameter information among all the technical units, and generating a second interactive statement according to the connection parameter information; outputting a second interactive sentence to the user, and receiving second feedback information of the user for the second interactive sentence; and determining a connection scheme between the technical units according to the second feedback information so as to determine a module design scheme according to the design scheme of the technical units and the connection scheme between the technical units.
Further, the determining the function provider corresponding to each function node diagram, and obtaining the function instance module corresponding to the function node diagram from the function provider, so as to combine the function instance modules into an application module, includes: issuing a function node diagram to each function provider, and each function provider is matched with a module structure diagram of a local function module according to the function node diagram, and determining and uploading a matching result; receiving matching results of all the function providers, comparing the matching results, and determining the function provider corresponding to each function node diagram; and obtaining the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.
Further, the issuing the function node diagram to each function provider, each function provider matches the module architecture diagram of the local function module according to the function node diagram, determines a matching result, and uploads the matching result, including: carrying out hash processing on the functional node diagram to obtain first hash information; and issuing the first hash information to each function provider, and each function provider is matched with the second hash information of the module structure diagram of the local function module according to the first hash information, and determining and uploading a matching result.
In a second aspect, the present application provides an AI intelligent software development apparatus, applied to a server, the apparatus comprising: the voice data acquisition module is used for acquiring voice input data of a user, identifying the voice input data and obtaining design text data, wherein the voice input data is used for designing the application module; the module architecture design module is used for analyzing the design text data, determining a module design scheme of the application module and designing a module architecture diagram according to the module design scheme; the module architecture display module is used for displaying the module architecture diagram to a user, acquiring a confirmation request of the user for the module architecture diagram, decomposing according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module; and the module architecture combination module is used for determining the function provider corresponding to each function node diagram and acquiring the function instance module corresponding to the function node diagram from the function provider so as to be combined into an application module.
In a third aspect, the present application provides an electronic device, comprising: a memory and at least one processor; the memory is used for storing computer execution instructions; the at least one processor is configured to execute computer-executable instructions stored in the memory, such that the at least one processor performs the method according to the first aspect.
The application provides an AI intelligent software development method, which is applied to a server and comprises the following steps: acquiring voice input data of a user, and identifying the voice input data to obtain design text data, wherein the voice input data is used for designing an application module; analyzing the design text data, determining a module design scheme of the application module, and designing a module structure diagram according to the module design scheme; displaying a module architecture diagram to a user, acquiring a confirmation request of the user for the module architecture diagram, decomposing according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module; and determining the function provider corresponding to each function node diagram, and acquiring the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.
The embodiment of the application can be applied to a software development scene, a user can interact with a server, the user can send voice input data for designing an application module to the server, the server carries out artificial intelligence (Artificial Intelligence, AI) analysis according to the voice input data, determines a module design scheme of the application module to be designed, determines a function provider capable of providing each function node of the application module, and accordingly obtains a corresponding function instance module, the function instance module is data obtained by instantiating a function (such as data corresponding to the function after programming by adopting a corresponding programming language), and the server combines a plurality of function instance modules into the application module and feeds the application module back to the user. The scheme can utilize the existing function examples provided by the function provider to rapidly complete the development of the application model, and reduces the workload of staff. Moreover, the user can complete the development of the software in a voice input mode, so that the interactivity is stronger.
Specifically, the application can acquire the voice input data of the user for designing the application module, and identify the voice input data to obtain the design text data; then, the server can analyze the design text data, determine a module design scheme of the application module, design a module architecture diagram according to the module design scheme, and display the module architecture diagram to a user so as to acquire a confirmation request (the user can confirm or modify the operation and the like) of the user on the module architecture diagram, and after the user confirms the module architecture diagram, the server can decompose the module architecture diagram to determine a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into the application module; then, the server can determine the function provider corresponding to each function node diagram according to the function node diagram, and acquire the function instance module corresponding to the function node diagram from the function provider to be combined into an application module, and feed back the application module to the user. The voice input data may include a technical keyword, where the technical keyword corresponds to a technical unit, the technical unit is used to form an application module, and the functional node is formed by at least one technical unit. In addition, for the parameters which are not given in the voice input data, the scheme can communicate with the user in a voice interaction mode for guiding, and the corresponding parameter design scheme can be more conveniently determined.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a flow chart of an AI intelligent software development method of one embodiment of the application;
FIG. 2 is a schematic diagram of the steps of an AI intelligent software development method in accordance with one embodiment of the application;
fig. 3 is a schematic structural diagram of an AI intelligent software development apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application can be applied to a software development scene, as shown in fig. 1, a user can interact with a server, the user can send voice input data for designing an application module to the server, the server analyzes according to the voice input data, determines a module design scheme of the application module to be designed, determines a function provider capable of providing each function node of the application module, and accordingly obtains a corresponding function instance module, wherein the function instance module is data obtained by instantiating a function (such as data corresponding to the function after programming by adopting a corresponding programming language), and the server combines a plurality of function instance modules into the application module and feeds back the application module to the user. The scheme can utilize the existing function examples provided by the function provider to rapidly complete the development of the application model, and reduces the workload of staff. Moreover, the user can complete the development of the software in a voice input mode, so that the interactivity is stronger.
Specifically, the application can acquire the voice input data of the user for designing the application module, and identify the voice input data to obtain the design text data; then, the server can analyze the design text data, determine a module design scheme of the application module, design a module architecture diagram according to the module design scheme, and display the module architecture diagram to a user so as to acquire a confirmation request (the user can confirm or modify the operation and the like) of the user on the module architecture diagram, and after the user confirms the module architecture diagram, the server can decompose the module architecture diagram to determine a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into the application module; then, the server can determine the function provider corresponding to each function node diagram according to the function node diagram, and acquire the function instance module corresponding to the function node diagram from the function provider to be combined into an application module, and feed back the application module to the user. The voice input data may include a technical keyword, where the technical keyword corresponds to a technical unit, the technical unit is used to form an application module, and the functional node is formed by at least one technical unit. In addition, for the parameters which are not given in the voice input data, the scheme can communicate with the user in a voice interaction mode, so that the corresponding parameter design scheme can be more conveniently determined, and the design of an application module is facilitated.
Specifically, an embodiment of the present application provides an AI intelligent software development method, which may be applied to a server, as shown in fig. 2, and includes:
step 202, acquiring voice input data of a user, and identifying the voice input data to obtain design text data, wherein the voice input data is used for designing an application module;
204, analyzing the design text data, determining a module design scheme of the application module, and designing a module architecture diagram according to the module design scheme;
step 206, displaying the module architecture diagram to the user, and obtaining a confirmation request of the user for the module architecture diagram, so as to decompose according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module;
and step 208, determining the function provider corresponding to each function node diagram, and acquiring the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.
The embodiment of the application can be applied to a software development scene, a user can interact with a server, the user can send voice input data for designing an application module to the server, the server analyzes according to the voice input data, determines a module design scheme of the application module to be designed, determines a function provider capable of providing each function node of the application module, and accordingly obtains a corresponding function instance module, the function instance module is data obtained by instantiating a function (such as data corresponding to the function obtained after programming by adopting a corresponding programming language), and the server combines a plurality of function instance modules into the application module and feeds back the application module to the user. The scheme can utilize the existing function examples provided by the function provider to rapidly complete the development of the application model, and reduces the workload of staff. Moreover, the user can complete the development of the software in a voice input mode, so that the interactivity is stronger.
Specifically, the application can acquire the voice input data of the user for designing the application module, and identify the voice input data to obtain the design text data; then, the server can analyze the design text data, determine a module design scheme of the application module, design a module architecture diagram according to the module design scheme, and display the module architecture diagram to a user so as to acquire a confirmation request (the user can confirm or modify the operation and the like) of the user on the module architecture diagram, and after the user confirms the module architecture diagram, the server can decompose the module architecture diagram to determine a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into the application module; then, the server can determine the function provider corresponding to each function node diagram according to the function node diagram, and acquire the function instance module corresponding to the function node diagram from the function provider to be combined into an application module, and feed back the application module to the user. The voice input data may include a technical keyword, where the technical keyword corresponds to a technical unit, the technical unit is used to form an application module, and the functional node is formed by at least one technical unit.
In addition, for the parameters which are not given in the voice input data, the scheme can communicate with the user in a voice interaction mode for guiding, and the corresponding parameter design scheme can be more conveniently determined. Specifically, as an optional embodiment, the analyzing the design text data to determine the module design scheme includes: identifying technical keywords in the design text data according to a pre-trained identification model; acquiring a first interactive sentence related to a technical keyword, and outputting the first interactive sentence to a user; receiving first feedback information of a user for a first interactive sentence, determining a design scheme of a technical unit corresponding to a technical keyword according to the first feedback information, wherein the technical keyword corresponds to the technical unit, the technical unit is used for forming an application module, and the functional node is formed by at least one technical unit; according to the design scheme of each technical unit, determining the module design scheme. According to the technical key word recognition method and device, a recognition model for recognizing the technical key word can be preset, the technical key word is recognized, and an information base can be built in advance for the technical key word to store parameters corresponding to the technical key word and interactive sentences corresponding to the parameters. The interactive sentences can be output to the user in the form of voice or can be displayed in the form of text. The user can perform interactive feedback aiming at the first interactive sentence, so as to determine a corresponding design scheme.
The voice input data of the user may include a part of parameters corresponding to the technical keywords, so that before determining the first interactive sentence, the corresponding parameters may be classified, the undetermined parameters may be extracted, and then the first interactive sentence may be determined. Specifically, as an optional embodiment, the pre-trained recognition model is further configured to recognize parameter related information corresponding to a technical keyword in the design text data, and the obtaining a first interaction sentence related to the technical keyword includes: determining given parameter information in the design text data according to the parameter related information; acquiring technical parameter information corresponding to technical keywords, and classifying the technical parameter information according to parameter related information identified by a pre-trained identification model to obtain first parameter information of given parameters and second parameter information without parameters; and acquiring a first interactive statement corresponding to the second parameter information. The technical keywords in the voice input data may carry part of limiting information (technical parameter information), so that interaction can be performed on the non-mentioned parameter forming interaction statement, and corresponding parameter design is obtained.
For different understandings of the user on the technical keywords (corresponding to the technical units), the recognition model in the scheme can map names, alternative names, definitions, functional descriptions and the like of the technical keywords into the same technical keywords so as to conveniently convert multiple inputs into the same technical keywords and determine the corresponding technical units. Specifically, as an optional embodiment, the method further includes a process of training the recognition model: acquiring names of technical keywords, alternative names of the technical keywords, definition information of the technical keywords and functional description information of the technical keywords as model input data, and taking the names of the technical keywords as labeling data; inputting the model input data into the recognition model for recognition to obtain a recognition result; and adjusting the recognition model according to the recognition result and the labeling data to determine a trained recognition model, wherein the trained recognition model is used for mapping the names of the recognized technical keywords, the alternative names of the technical keywords, the definition information of the technical keywords and the function description information of the technical keywords into the technical keywords. The recognition model may build a mapping space to map names, functional descriptions, etc. to technical keywords.
According to the scheme, a parameter information base can be established, and each technical keyword corresponds to at least one parameter information so as to design parameters. Specifically, as an optional embodiment, the method further includes: acquiring related parameter information of the technical keywords, and storing the related parameter information into a parameter information base; the obtaining technical parameter information corresponding to the technical keywords comprises the following steps: technical parameter information of the technical keywords is extracted from the parameter information base.
The method can design the related parameters of one technical unit, design the connection scheme among the technical units, and acquire the connection scheme by outputting interactive sentences and acquiring feedback so as to establish the connection among the technical units according to the connection scheme. Specifically, as an optional embodiment, the determining a module design according to the design of each technical unit includes: acquiring connection parameter information among all the technical units, and generating a second interactive statement according to the connection parameter information; outputting a second interactive sentence to the user, and receiving second feedback information of the user for the second interactive sentence; and determining a connection scheme between the technical units according to the second feedback information so as to determine a module design scheme according to the design scheme of the technical units and the connection scheme between the technical units. The second interactive sentence may be output in the form of text or speech. Such as interfaces that may be designed according to the connection scheme.
For the module architecture diagram, one function provider may not include all module architectures, so the scheme may decompose a module architecture corresponding to the module architecture diagram into a plurality of function nodes (composed of at least one technology unit) to form a function node diagram so as to match corresponding function instance modules through the function node diagram. Specifically, as an optional embodiment, the determining the function provider corresponding to each function node diagram, and obtaining the function instance module corresponding to the function node diagram from the function provider, so as to combine the function instance modules into an application module, includes: issuing a function node diagram to each function provider, and each function provider is matched with a module structure diagram of a local function module according to the function node diagram, and determining and uploading a matching result; receiving matching results of all the function providers, comparing the matching results, and determining the function provider corresponding to each function node diagram; and obtaining the function instance module corresponding to the function node diagram from the function provider to be combined into an application module. Each function provider stores a module architecture diagram, the module architecture diagram is composed of a plurality of function node diagrams, and the scheme can be matched with whether the function node diagram issued by the server is consistent with the function node diagram in the module architecture diagram of the local function provider or not so as to select a corresponding function instance module, so that the module is an application module.
The problem of data leakage may occur when the function node diagram is directly issued, so that the hash information can be obtained after the information of the function node diagram is hashed, and matching is performed according to the hash information. The hash manner of the server is the same as that of the function provider to convert the same data into the same hash value. Specifically, as an optional embodiment, the issuing the function node diagram to each function provider, where each function provider matches the module architecture diagram of the local function module according to the function node diagram, determines a matching result, and uploads the matching result, including: carrying out hash processing on the functional node diagram to obtain first hash information; and issuing the first hash information to each function provider, and each function provider is matched with the second hash information of the module structure diagram of the local function module according to the first hash information, and determining and uploading a matching result.
On the basis of the above embodiment, the embodiment of the present application further provides an AI intelligent software development device, which is applicable to a server, as shown in fig. 3, and the device includes:
the voice data acquisition module 302 is configured to acquire voice input data of a user, and identify the voice input data to obtain design text data, where the voice input data is used for designing the application module;
the module architecture design module 304 is configured to analyze the design text data, determine a module design scheme of the application module, and design a module architecture diagram according to the module design scheme;
the module architecture display module 306 is configured to display a module architecture diagram to a user, and obtain a confirmation request of the user for the module architecture diagram, so as to decompose the module architecture diagram according to the module architecture diagram, and determine a plurality of function node diagrams, where the function node diagrams correspond to function nodes, and the function nodes are used to be combined into an application module;
the module architecture combining module 308 is configured to determine a function provider corresponding to each function node diagram, and obtain a function instance module corresponding to the function node diagram from the function provider, so as to combine the function instance modules into an application module.
The implementation manner of the embodiment of the present application is similar to that of the embodiment of the method, and the specific implementation manner may refer to the specific implementation manner of the embodiment of the method, which is not repeated herein.
The embodiment of the application can be applied to a software development scene, a user can interact with a server, the user can send voice input data for designing an application module to the server, the server analyzes according to the voice input data, determines a module design scheme of the application module to be designed, determines a function provider capable of providing each function node of the application module, and accordingly obtains a corresponding function instance module, the function instance module is data obtained by instantiating a function (such as data corresponding to the function obtained after programming by adopting a corresponding programming language), and the server combines a plurality of function instance modules into the application module and feeds back the application module to the user. The proposal can utilize the existing function examples provided by the function provider to rapidly complete the development of the application model, the workload of staff is reduced. Moreover, the user can complete the development of the software in a voice input mode, so that the interactivity is stronger.
Specifically, the application can acquire the voice input data of the user for designing the application module, and identify the voice input data to obtain the design text data; then, the server can analyze the design text data, determine a module design scheme of the application module, design a module architecture diagram according to the module design scheme, and display the module architecture diagram to a user so as to acquire a confirmation request (the user can confirm or modify the operation and the like) of the user on the module architecture diagram, and after the user confirms the module architecture diagram, the server can decompose the module architecture diagram to determine a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into the application module; then, the server can determine the function provider corresponding to each function node diagram according to the function node diagram, and acquire the function instance module corresponding to the function node diagram from the function provider to be combined into an application module, and feed back the application module to the user. Wherein, the voice input data can contain technical keywords which correspond to the technical units, the technical units are used for forming an application module, and the functional node is formed by at least one technical unit. In addition, for the parameters which are not given in the voice input data, the scheme can communicate with the user in a voice interaction mode for guiding, and the corresponding parameter design scheme can be more conveniently determined.
On the basis of the above embodiment, the present application further provides an electronic device, including: a memory and at least one processor; the memory is used for storing computer execution instructions; the at least one processor is configured to execute computer-executable instructions stored in the memory, such that the at least one processor performs the method as described in the above embodiments.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the data processing method embodiment, and can achieve the same technical effects, so that repetition is avoided and no further description is given here. Wherein the computer readable storage medium is selected from Read-Only Memory (ROM), random access Memory (Random ACGess Memory, RAM), magnetic disk or optical disk.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. According to the definitions herein, the computer-readable medium does not include a transitory computer-readable medium (transmission medium), such as a modulated data signal and carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims (10)

1. An AI intelligent software development method, characterized by being applied to a server, the method comprising:
acquiring voice input data of a user, and identifying the voice input data to obtain design text data, wherein the voice input data is used for designing an application module;
analyzing the design text data, determining a module design scheme of the application module, and designing a module structure diagram according to the module design scheme;
displaying a module architecture diagram to a user, acquiring a confirmation request of the user for the module architecture diagram, decomposing according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module;
and determining the function provider corresponding to each function node diagram, and acquiring the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.
2. The method of claim 1, wherein analyzing the design text data to determine a module design comprises:
identifying technical keywords in the design text data according to a pre-trained identification model;
acquiring a first interactive sentence related to a technical keyword, and outputting the first interactive sentence to a user;
receiving first feedback information of a user for a first interactive sentence, determining a design scheme of a technical unit corresponding to a technical keyword according to the first feedback information, wherein the technical keyword corresponds to the technical unit, the technical unit is used for forming an application module, and the functional node is formed by at least one technical unit;
according to the design scheme of each technical unit, determining the module design scheme.
3. The method according to claim 2, wherein the pre-trained recognition model is further used for recognizing parameter related information corresponding to a technical keyword in the design text data, and the obtaining the first interactive sentence related to the technical keyword includes:
determining given parameter information in the design text data according to the parameter related information;
acquiring technical parameter information corresponding to technical keywords, and classifying the technical parameter information according to parameter related information identified by a pre-trained identification model to obtain first parameter information of given parameters and second parameter information without parameters;
and acquiring a first interactive statement corresponding to the second parameter information.
4. A method according to claim 3, further comprising the process of training an identification model:
acquiring names of technical keywords, alternative names of the technical keywords, definition information of the technical keywords and functional description information of the technical keywords as model input data, and taking the names of the technical keywords as labeling data;
inputting the model input data into the recognition model for recognition to obtain a recognition result;
and adjusting the recognition model according to the recognition result and the labeling data to determine a trained recognition model, wherein the trained recognition model is used for mapping the names of the recognized technical keywords, the alternative names of the technical keywords, the definition information of the technical keywords and the function description information of the technical keywords into the technical keywords.
5. The method according to claim 4, wherein the method further comprises:
acquiring related parameter information of the technical keywords, and storing the related parameter information into a parameter information base;
the obtaining technical parameter information corresponding to the technical keywords comprises the following steps:
technical parameter information of the technical keywords is extracted from the parameter information base.
6. The method of claim 5, wherein determining the module design based on the design of each technology unit comprises:
acquiring connection parameter information among all the technical units, and generating a second interactive statement according to the connection parameter information;
outputting a second interactive sentence to the user, and receiving second feedback information of the user for the second interactive sentence;
and determining a connection scheme between the technical units according to the second feedback information so as to determine a module design scheme according to the design scheme of the technical units and the connection scheme between the technical units.
7. The method of claim 6, wherein determining the function provider corresponding to each function node graph and obtaining the function instance module corresponding to the function node graph from the function provider to be combined into the application module comprises:
issuing a function node diagram to each function provider, and each function provider is matched with a module structure diagram of a local function module according to the function node diagram, and determining and uploading a matching result;
receiving matching results of all the function providers, comparing the matching results, and determining the function provider corresponding to each function node diagram;
and obtaining the function instance module corresponding to the function node diagram from the function provider to be combined into an application module.
8. The method of claim 7, wherein issuing the function node map to each function provider, each function provider matching the function node map with a module architecture map of a local function module, determining and uploading a matching result, comprises:
the functional node map is hashed, obtaining first hash information;
and issuing the first hash information to each function provider, and each function provider is matched with the second hash information of the module structure diagram of the local function module according to the first hash information, and determining and uploading a matching result.
9. An AI intelligent software development apparatus, characterized by being applied to a server, comprising:
the voice data acquisition module is used for acquiring voice input data of a user, identifying the voice input data and obtaining design text data, wherein the voice input data is used for designing the application module;
the module architecture design module is used for analyzing the design text data, determining a module design scheme of the application module and designing a module architecture diagram according to the module design scheme;
the module architecture display module is used for displaying the module architecture diagram to a user, acquiring a confirmation request of the user for the module architecture diagram, decomposing according to the module architecture diagram, and determining a plurality of function node diagrams, wherein the function node diagrams correspond to the function nodes, and the function nodes are used for being combined into an application module;
and the module architecture combination module is used for determining the function provider corresponding to each function node diagram and acquiring the function instance module corresponding to the function node diagram from the function provider so as to be combined into an application module.
10. An electronic device, comprising: a memory and at least one processor;
the memory is used for storing computer execution instructions;
the at least one processor is configured to execute computer-executable instructions stored in the memory, such that the at least one processor performs the method of any one of claims 1-8.
CN202311385942.1A 2023-10-25 2023-10-25 AI intelligent software development method and device Active CN117111902B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311385942.1A CN117111902B (en) 2023-10-25 2023-10-25 AI intelligent software development method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311385942.1A CN117111902B (en) 2023-10-25 2023-10-25 AI intelligent software development method and device

Publications (2)

Publication Number Publication Date
CN117111902A true CN117111902A (en) 2023-11-24
CN117111902B CN117111902B (en) 2024-01-26

Family

ID=88813232

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311385942.1A Active CN117111902B (en) 2023-10-25 2023-10-25 AI intelligent software development method and device

Country Status (1)

Country Link
CN (1) CN117111902B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107632823A (en) * 2017-08-18 2018-01-26 深圳怡化电脑股份有限公司 A kind of software development methodology and device
US10191721B1 (en) * 2017-07-27 2019-01-29 Huma.Ai Systems and methods for generating functional application designs
CN109375904A (en) * 2018-09-26 2019-02-22 思朋网络科技(武汉)有限公司 A kind of computer software development approach based on model
CN113962666A (en) * 2021-11-02 2022-01-21 湛江芯承科技有限公司 Front-end software development testing method and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10191721B1 (en) * 2017-07-27 2019-01-29 Huma.Ai Systems and methods for generating functional application designs
CN107632823A (en) * 2017-08-18 2018-01-26 深圳怡化电脑股份有限公司 A kind of software development methodology and device
CN109375904A (en) * 2018-09-26 2019-02-22 思朋网络科技(武汉)有限公司 A kind of computer software development approach based on model
CN113962666A (en) * 2021-11-02 2022-01-21 湛江芯承科技有限公司 Front-end software development testing method and system

Also Published As

Publication number Publication date
CN117111902B (en) 2024-01-26

Similar Documents

Publication Publication Date Title
CN110377716B (en) Interaction method and device for conversation and computer readable storage medium
CN110502227B (en) Code complement method and device, storage medium and electronic equipment
CN107590123B (en) Vehicular middle-location context reference resolution method and device
CN109036424A (en) Audio recognition method, device, electronic equipment and computer readable storage medium
CN112966076A (en) Intelligent question and answer generating method and device, computer equipment and storage medium
CN110931002B (en) Man-machine interaction method, device, computer equipment and storage medium
CN117875292A (en) Financial knowledge intelligent question-answering method, system, terminal equipment and storage medium
CN117453885A (en) Question information processing method, device, equipment, storage medium and product
CN115148212A (en) Voice interaction method, intelligent device and system
CN114676705B (en) Dialogue relation processing method, computer and readable storage medium
CN116680368B (en) Water conservancy knowledge question-answering method, device and medium based on Bayesian classifier
CN118093625A (en) Financial data query method, equipment and medium for ERP system
CN114238807A (en) Processing method and device for data visualization page
CN116560631B (en) Method and device for generating machine learning model code
CN110347921B (en) Label extraction method and device for multi-mode data information
CN117111902B (en) AI intelligent software development method and device
CN111381935A (en) DSL configuration expression-based function implementation method and system
CN117194620A (en) Information processing method, device, equipment and storage medium
CN113360630B (en) Interactive information prompting method
CN111126066B (en) Method and device for determining Chinese congratulation technique based on neural network
CN114548314A (en) Text matching method and device, storage medium and electronic equipment
CN115114281A (en) Query statement generation method and device, storage medium and electronic equipment
Yuan et al. An approach of dynamically combining ontologies for interactive Requirements Elicitation
KR102665966B1 (en) Method and system for generating classification numbers using artificial intelligence to build book MARC DATA
CN116737964B (en) Artificial intelligence brain system

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant