CN117193745A - Application development method and device combining assembly and large language model - Google Patents
Application development method and device combining assembly and large language model Download PDFInfo
- Publication number
- CN117193745A CN117193745A CN202311154017.8A CN202311154017A CN117193745A CN 117193745 A CN117193745 A CN 117193745A CN 202311154017 A CN202311154017 A CN 202311154017A CN 117193745 A CN117193745 A CN 117193745A
- Authority
- CN
- China
- Prior art keywords
- component
- target
- components
- language model
- large language
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000011161 development Methods 0.000 title claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 230000015654 memory Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 9
- 230000002452 interceptive effect Effects 0.000 claims description 7
- 230000000712 assembly Effects 0.000 claims description 4
- 238000000429 assembly Methods 0.000 claims description 4
- 230000018109 developmental process Effects 0.000 description 25
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000009877 rendering Methods 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 7
- 230000007246 mechanism Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000015572 biosynthetic process Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000003786 synthesis reaction Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Stored Programmes (AREA)
Abstract
The specification relates to the technical field of application development, and provides an application development method and device combining component assembly and a large language model. The method comprises the following steps: developing a plurality of large language model components in advance, and adding the large language model components into a component database, wherein the purpose or output format of each large language model component is different; receiving a target component selected from a component database by service personnel according to service requirements, wherein the target component at least comprises a large language model component; receiving an arrangement relation among target components set by service personnel; and generating the application program according to the target component and the arrangement relation between the target components. According to the embodiment of the specification, the problems that a threshold required in software development is high and a result in various forms cannot be output can be solved.
Description
Technical Field
The present disclosure relates to the field of application development technologies, and in particular, to a method and an apparatus for application development by combining assembly and a large language model.
Background
With the development of digital transformation and blowout type of business requirements, the demand for software is increasing, while traditional software development has a certain requirement on code writing capability, so that it is extremely difficult for business personnel who do not understand code writing to develop software. However, IT personnel have low development efficiency due to the difficulty in understanding the business deeply, and business applications cannot be delivered quickly. The conflict of the urgent degree of business personnel on software and the inability of IT personnel to quickly and deeply understand business has been increased. The existing application development mode based on the low-code platform still needs a developer to modify codes and cannot output various types of results. Therefore, a low threshold mode is needed to enable the business personnel to develop software and generate output results with various display modes according to business requirements.
Disclosure of Invention
In view of the high threshold required for software development and the inability to output various forms of results, the present solution has been proposed to overcome or at least partially solve the above-described problems.
In one aspect, some embodiments of the present specification aim to provide an application development method based on a combination of component assembly and large language models, in which a plurality of large language model components are developed in advance and added to a component database, each large language model component having a different use or output format, the method comprising:
receiving a target component selected from a component database by service personnel according to service requirements, wherein the target component at least comprises a large language model component;
receiving the arrangement relation between the target components set by service personnel;
and generating an application program according to the target component and the arrangement relation between the target components.
Further, the pre-developed plurality of large language model components are developed using component development tools in a low code platform.
Further, the orchestration relationship between the target components is implemented by an application assembly workbench.
Further, after receiving the orchestration relationship between the target components set by the service personnel, the method further includes:
verifying the arrangement relation among the target components to determine whether the arrangement relation is abnormal;
if the verification result is abnormal, an automatic solution is given according to the target component at the abnormal position;
and if the verification result is not abnormal, determining the arrangement relation.
Further, the verifying the arrangement relation between the target components includes:
and checking whether the output parameters and the input parameters of the target components with the connected arrangement relation are consistent.
Further, the target component according to the abnormal position gives an automation solution, which comprises:
querying a component connection mode database to determine an alternative connection component of the target component at an abnormal position, wherein the component connection mode database stores association relations between each component and connectable components thereof;
matching target components contained in the alternative connection components from all target components;
and prompting the matched target component to a user as a suspected connection component.
Further, the application development method based on the combination of the component assembly and the large language model technology further comprises the following steps:
determining an input assembly and an output assembly according to the arrangement relation between the target assembly and the target assembly;
and generating an interactive interface by utilizing a preset interface template according to parameters required by the input assembly and output contents of the output assembly, wherein the interactive interface at least comprises an input control for inputting source data information.
Further, the application development method based on the combination of the component assembly and the large language model technology further comprises the following steps:
receiving a triggering request of a user to any target component;
and acquiring and displaying input and output information of the corresponding target component according to the trigger request, so that a user can set an arrangement relation according to the displayed input and output information.
In another aspect, some embodiments of the present specification further provide an application development apparatus based on a combination of component assembly and large language model technology, which pre-develops and adds a plurality of large language model components to a component database, each large language model component having a different use or output format, the apparatus comprising:
the component receiving module is used for receiving a target component selected from a component database by service personnel according to service requirements, wherein the target component at least comprises a large language model component;
the component arrangement relation receiving module is used for receiving arrangement relations among target components set by service personnel;
and the application program generating module is used for generating an application program according to the target assembly and the arrangement relation between the target assemblies.
In another aspect, some embodiments of the present description also provide a computer device including a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program executing instructions of the above method when executed by the processor.
In another aspect, some embodiments of the present description also provide a computer storage medium having stored thereon a computer program which, when executed by a processor of a computer device, performs instructions of the above method.
In another aspect, some embodiments of the present description also provide a computer program product comprising a computer program which, when executed by a processor of a computer device, performs instructions of the above method.
Some embodiments of the present disclosure provide one or more technical solutions, which at least have the following technical effects:
embodiments of the present description pre-develop and add a plurality of large language model components to a component database, each of which has a different use or output format, and can generate output results in a plurality of presentation forms through one input. The large language model interface is packaged into a visual component through the low code platform so that business personnel can use the component in a graphical manner. When the application is developed, service personnel only need to select corresponding target components according to service requirements through an application assembly workbench (used for displaying the components contained in the component database), drag and set the arrangement relation to generate a required application program.
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present description or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present description, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings of which there are shown,
FIG. 1 illustrates a schematic diagram of steps in an application development method of component assembly and large language model integration in some embodiments of the present description;
FIG. 2 illustrates an application component selection diagram that turns a web page into a mind map in some embodiments of the present description;
FIG. 3 illustrates an application component orchestration schematic that turns a web page into a mind map in some embodiments of the present description;
FIG. 4 illustrates a schematic diagram of an application development device combining component assembly and large language model techniques in some embodiments of the present description;
fig. 5 illustrates a schematic diagram of a computer device provided in some embodiments of the present description.
[ reference numerals description ]
401. A component receiving module;
402. a component orchestration relationship receiving module;
403. an application program generation module;
502. a computer device;
504. a processor;
506. a memory;
508. a driving mechanism;
510. an input/output module;
512. an input device;
514. an output device;
516. a presentation device;
518. a graphical user interface;
520. a network interface;
522. a communication link;
524. a communication bus.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and the claims, and in the foregoing figures, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the present description described herein may be capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or device.
In order to solve the above-mentioned problems, the embodiments of the present disclosure provide an application development method combining assembly and large language model, which can reduce the threshold of application development and can generate output results in various display forms. FIG. 1 is a schematic diagram of the steps of a method for application development of a combination of component assembly and large language models provided by embodiments of the present disclosure, which provide the method operational steps described in the examples or flowcharts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When a system or apparatus product in practice is executed, it may be executed sequentially or in parallel according to the method shown in the embodiments or the drawings.
The method of FIG. 1 is performed by pre-developing and adding a plurality of large language model components to a component database, each of the large language model components having a different use or output format, and in some embodiments, the output format of the large language model components includes, but is not limited to, forms such as forms, reports, and pages. The large language model actually supports only text-type output, where some hints may be preconfigured and input to the large language model to enable the large language model to output multiple forms of data according to the hints.
Specifically, as shown in fig. 1, the application development method combining the assembly of components and the large language model includes:
s101: receiving a target component selected by a business person from the component database according to business requirements, wherein the target component at least comprises a large language model component;
in particular, a low-code platform is a way of software development, generating applications by using descriptive, high-level programming abstraction languages, and also enabling software application development by means of component assembly. The components of the low-code platform package comprise an input type component, a layout type component, a selection component and a prompt component, wherein the components can be realized by adopting a JS framework, and configuration attributes of each component, such as color, size, theme, action event and the like, are exposed; the components are utilized to orchestrate large language model application input and output materials on a canvas that includes common component areas, orchestration areas, and attribute configuration areas. These orchestrated finished products may be trained to large language models as inputs and outputs to large language model components. Specific training procedures for large language models may be referred to the prior art and will not be described in detail herein.
The large language model refers to a deep learning and reasoning model trained by using a large amount of text data, can process various natural language tasks, such as text classification, question-answering, dialogue and the like, and belongs to the category of artificial intelligence. By combining the low-code assembly thought with the natural language processing logic of the large language model, a low-threshold research and development tool for large language model application is formed, so that business personnel are assisted to convert discrete and descriptive demands into highly structured, digitized and visualized expressions, and the business model is facilitated to be better converted. In some embodiments, a large language model component is pre-developed with a component development tool in a low code platform, and the large language model interface is packaged into a visualized component, which enables business personnel to use the component in a graphical manner.
FIG. 2 is a diagram of application component selection for converting a web page into a mind map. As shown in FIG. 2, according to business requirements, business personnel select components from a component database required for converting a web page into a mind map, including a text crawler component, a text synthesis component, a text segmentation component, a list rendering component, a text presentation component, a mind map component, and a large language model component, i.e., an OpenAI component. The text crawler component is used for crawling texts in the web pages, the text synthesis component is used for synthesizing a plurality of variables into a section of words, the text segmentation component is used for segmenting the texts into a plurality of texts according to a specified method, the list rendering component is used for rendering the list into the texts, the text rendering component is used for rendering the texts on a user using an interface, and the mind map component is used for generating a mind map. In addition, a button trigger component is included for triggering the workflow operation, and as a special node, no connection with other nodes is needed.
S102: receiving the arrangement relation between the target components set by service personnel;
in some embodiments, after a business person selects a suitable target component in the component database according to a business requirement, the selected target component needs to be arranged according to an input/output parameter of each component so as to determine an execution sequence of the target components connected in series. For each component, there are its determined input and output parameters, and business personnel need to assign values to the necessary parameters. As shown in fig. 3, in an application for converting a web page into a mind map, the input of the text crawler component is a web address, the output type can be selected according to service requirements, in the application, the output type is selected as text, and the output content comprises a web page title and web page text. The text synthesis component inputs the title and the text, outputs the template generated according to the title and the text, and displays the template in a natural language form. The text segmentation component inputs text and outputs text segmented according to segmentation methods, wherein the segmentation methods and the text segmentation lengths can be selected autonomously. The Open AI component inputs as natural language and outputs as content generated from natural language. The text presentation component inputs as text content and then outputs at the user interface. The mind map component inputs text in Markdown form and outputs as a mind map. After the input/output of each component is specified, it needs to be arranged according to the relationship between them and the processing logic of the service.
In the application of converting a webpage into a mind map, firstly, a text crawler component is utilized to crawl texts in the webpage, so that the texts are input into websites and output into webpage titles and webpage text, then, a text segmentation component is utilized to segment the webpage text into a plurality of texts according to a specified method, the segmented text and the webpage titles are input into a first text synthesis component, a plurality of variables are synthesized into a section of text according to a preset template, and the template content comprises: the title, text, please summarize the above articles into mind map, the template content is input to the first Open AI component, which performs integration extraction on the input content and returns the result. And then inputting the result into a list rendering component, rendering the list into a text, inputting the text into a second text synthesizing component, and outputting synthesized contents according to a preset template, wherein the template contents comprise: "article", please summarize the above article as a mind map, output in Markdown form. And inputting the template content into a second Open AI component, outputting a Markdown format text for generating a mind map from the text, and finally inputting the Markdown content into the mind map component to generate the mind map.
Further, after receiving the orchestration relationship between the target components set by the service personnel, the method may further include:
and checking the arrangement relation among the target components to determine whether the arrangement relation is abnormal. The verification is mainly performed by verifying whether the output parameters and the input parameters of the target components with the connected arrangement relation are consistent.
If the verification result is abnormal, an automatic solution is given according to the target component at the abnormal position. Wherein the automated solution may comprise the steps of:
step a: querying a component connection mode database to determine an alternative connection component of the target component at an abnormal position, wherein the component connection mode database stores association relations between each component and connectable components thereof;
step b: matching target components contained in the alternative connection components from all target components;
step c: and prompting the matched target component to a user as a suspected connection component.
And if the verification result is not abnormal, determining the arrangement relation.
For business personnel, errors can be avoided when the components are organized or parameters of the components are assigned, and at the moment, if the business personnel seek solutions, a great amount of time is consumed, and the errors are difficult to solve, so that the accuracy of the organization can be ensured through automatic verification of the organization relation, and the time and energy for the business personnel to develop software are saved. In addition, when the verification result is abnormal, an automatic solution can be given according to the target component at the abnormal position, so that the efficiency of software development is improved.
S103: and generating an application program according to the target component and the arrangement relation between the target components.
Specifically, receiving a trigger request of a user to any target component at an application assembly workbench; and acquiring and displaying input and output information of the corresponding target component according to the trigger request, so that a user can set an arrangement relation according to the displayed input and output information. Determining an input assembly and an output assembly according to the arrangement relation between the target assembly and the target assembly; and generating an interactive interface by utilizing a preset interface template according to parameters required by the input assembly and output contents of the output assembly, wherein the interactive interface at least comprises an input control for inputting source data information. And triggering an application programming interface of the large language model through a button of the interactive interface, and finally outputting according to an output format of service requirements.
The trigger request may be sent by means of a mouse movement (e.g. when a mouse pointer is located on the component), clicking, double clicking, etc.
It should be noted that although the operations of the method of the present application are described in a particular order in the above embodiments and the accompanying drawings, this does not require or imply that the operations must be performed in the particular order or that all of the illustrated operations be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform.
In response to the above-described application development method for combining assembly and large language models, some embodiments of the present disclosure further provide an application development apparatus for combining assembly and large language models, which pre-develops and adds a plurality of large language model assemblies to an assembly database, each of the large language model assemblies having a different use or output format, the apparatus comprising: referring to fig. 4, in some embodiments, the apparatus may include:
the component receiving module 401 is configured to receive a target component selected by a service person from a component database according to a service requirement, where the target component at least includes a large language model component;
a component arrangement relation receiving module 402, configured to receive an arrangement relation between target components set by service personnel;
an application generating module 403, configured to generate an application according to the target component and the arrangement relation between the target components.
The beneficial effects obtained by the device provided by the embodiment of the present disclosure are consistent with those obtained by the above method, and will not be described herein.
The user information (including but not limited to user equipment information, user personal information, etc.) related to the present application is information authorized by the user or sufficiently authorized by each party.
Embodiments of the present description also provide a computer device. As shown in FIG. 5, which is a schematic diagram of a computer device in an embodiment of the present description, the computer device 502 may include one or more processors 504, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The computer device 502 may also include any memory 506 for storing any kind of information, such as code, settings, data, etc. For example, and without limitation, memory 506 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may store information using any technique. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 502. In one case, when the processor 504 executes associated instructions stored in any memory or combination of memories, the computer device 502 can perform any of the operations of the associated instructions. The computer device 502 also includes one or more drive mechanisms 508, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like, for interacting with any memory.
The computer device 502 may also include an input/output module 510 (I/O) for receiving various inputs (via an input device 512) and for providing various outputs (via an output device 514). One particular output mechanism may include a presentation device 516 and an associated Graphical User Interface (GUI) 518. In other embodiments, input/output module 510 (I/O), input device 512, and output device 514 may not be included, but merely as a computer device in a network. Computer device 502 may also include one or more network interfaces 520 for exchanging data with other devices via one or more communication links 522. One or more communication buses 524 couple the above-described components together.
Communication link 522 may be implemented in any manner, for example, by a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. Communication link 522 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.
Corresponding to the method in fig. 1-3, the present description also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.
The present embodiments also provide a computer readable instruction wherein the program therein causes the processor to perform the method as shown in fig. 1 to 3 when the processor executes the instruction.
It should be understood that, in various embodiments of the present disclosure, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation of the embodiments of the present disclosure.
It should also be understood that, in the embodiments of the present specification, the term "and/or" is merely one association relationship describing the association object, meaning that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist together, and B exists alone. In the present specification, the character "/" generally indicates that the front and rear related objects are an or relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the various example components and steps have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present specification.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this specification, it should be understood that the disclosed systems, apparatuses, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purposes of the embodiments of the present description.
In addition, each functional unit in each embodiment of the present specification may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present specification is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present specification. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The principles and embodiments of the present specification are explained in this specification using specific examples, the above examples being provided only to assist in understanding the method of the present specification and its core ideas; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope based on the ideas of the present specification, the present description should not be construed as limiting the present specification in view of the above.
Claims (12)
1. An application development method combining assembly of components and large language models, characterized in that a plurality of large language model components are developed in advance and added to a component database, each large language model component having a different use or output format, the method comprising:
receiving a target component selected by a business person from the component database according to business requirements, wherein the target component at least comprises a large language model component;
receiving the arrangement relation between the target components set by service personnel;
and generating an application program according to the target component and the arrangement relation between the target components.
2. The method of claim 1, wherein the pre-developed plurality of large language model components are developed using component development tools in a low code platform.
3. The method of claim 1, wherein the orchestration relationship between the target components is implemented by an application assembly workbench.
4. The method of claim 1, wherein after receiving the orchestration relationship between the target components set by business personnel, further comprising:
verifying the arrangement relation among the target components to determine whether the arrangement relation is abnormal;
if the verification result is abnormal, an automatic solution is given according to the target component at the abnormal position;
and if the verification result is not abnormal, determining the arrangement relation.
5. The method of claim 4, wherein verifying the orchestration relationship between the target components comprises:
and checking whether the output parameters and the input parameters of the target components with the connected arrangement relation are consistent.
6. The method of claim 4, wherein the target component based on anomaly location gives an automation solution comprising:
querying a component connection mode database to determine an alternative connection component of the target component at an abnormal position, wherein the component connection mode database stores association relations between each component and connectable components thereof;
matching target components contained in the alternative connection components from all target components;
and prompting the matched target component to a user as a suspected connection component.
7. The method as recited in claim 1, further comprising:
determining an input assembly and an output assembly according to the arrangement relation between the target assembly and the target assembly;
and generating an interactive interface by utilizing a preset interface template according to parameters required by the input assembly and output contents of the output assembly, wherein the interactive interface at least comprises an input control for inputting source data information.
8. The method as recited in claim 1, further comprising:
receiving a triggering request of a user to any target component;
and acquiring and displaying input and output information of the corresponding target component according to the trigger request, so that a user can set an arrangement relation according to the displayed input and output information.
9. An application development apparatus combining assembly of components and large language models, characterized in that a plurality of large language model components are developed in advance and added to a component database, each large language model component having a different use or output format, the apparatus comprising:
the component receiving module is used for receiving a target component selected from a component database by service personnel according to service requirements, wherein the target component at least comprises a large language model component;
the component arrangement relation receiving module is used for receiving arrangement relations among target components set by service personnel;
and the application program generating module is used for generating an application program according to the target assembly and the arrangement relation between the target assemblies.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any one of claims 1 to 8 when executing the computer program.
11. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.
12. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor of a computer device, implements the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311154017.8A CN117193745A (en) | 2023-09-07 | 2023-09-07 | Application development method and device combining assembly and large language model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311154017.8A CN117193745A (en) | 2023-09-07 | 2023-09-07 | Application development method and device combining assembly and large language model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117193745A true CN117193745A (en) | 2023-12-08 |
Family
ID=88993677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311154017.8A Pending CN117193745A (en) | 2023-09-07 | 2023-09-07 | Application development method and device combining assembly and large language model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117193745A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118034661A (en) * | 2024-04-12 | 2024-05-14 | 清华大学 | Intelligent task application system of large language model |
-
2023
- 2023-09-07 CN CN202311154017.8A patent/CN117193745A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118034661A (en) * | 2024-04-12 | 2024-05-14 | 清华大学 | Intelligent task application system of large language model |
| CN118034661B (en) * | 2024-04-12 | 2024-06-11 | 清华大学 | Intelligent task application system of large language model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Szekely | Retrospective and challenges for model-based interface development | |
| US20130097583A1 (en) | Systems and Methods For Automating the Application of a Software Methodology | |
| Ahmed et al. | Model-based user interface engineering with design patterns | |
| EP1672537A2 (en) | Data semanticizer | |
| US20120221998A1 (en) | Screenflow designer with automatically changing view | |
| Kim et al. | A model-driven approach for describing semantic web services: From UML to OWL-S | |
| Gupta et al. | Creation of multiple conceptual models from user stories–a natural language processing approach | |
| Rosa et al. | A visual approach for identification and annotation of business process elements in process descriptions | |
| CN117390336A (en) | Webpage process automation method, device, equipment and storage medium | |
| Glinz et al. | Handbook for the CPRE Foundation Level according to the IREB Standard | |
| Houde et al. | Opportunities for generative ai in ux modernization | |
| CN117193745A (en) | Application development method and device combining assembly and large language model | |
| Arthur et al. | Investigating the use of software requirements engineering techniques in simulation modelling | |
| Bainey | AI-Driven Project Management: Harnessing the Power of Artificial Intelligence and ChatGPT to Achieve Peak Productivity and Success | |
| Rojas et al. | Bridging the gap between information architecture analysis and software engineering in interactive web application development | |
| Sadouski | Ontological approach to the building of semantic models of user interfaces | |
| Pontico et al. | Organizing user interface patterns for e-Government applications | |
| Gilson et al. | Recording Software Design Decisions on the Fly. | |
| Costabile et al. | Computer environments for improving end-user accessibility | |
| KR101632951B1 (en) | Computer readable medium recording program for converting to online learning data and method of converting to online learning data | |
| Babris et al. | From Models to Interfaces: Leveraging the Two-Hemisphere Model for Automated UI Generation | |
| Tilley | Documenting software systems with views VI: lessons learned from 15 years of research & practice | |
| Orni | Development and Usability Evaluation of a Domain-Specific Modeling Tool for Cybersecurity-related User Journeys | |
| CN119312783A (en) | Method, device and storage medium for generating demand document | |
| Lachaume et al. | Task model simulators: a review |
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 |