Application generation method and device based on large language model, equipment and medium

Abstract

The invention discloses an application generation method and device based on a large language model, equipment and a medium, and relates to the technical field of computers. The method comprises the steps of obtaining at least one section of natural language demand text; according to the at least one section of natural language demand text, determining a target digital-analog structure corresponding to each section of natural language demand text; generating a structured query language according to the at least one section of natural language demand text, the target digital-analog structure corresponding to each section of natural language demand text and the target large language model; according to the structured query language and a database, a query result meeting the at least one natural language demand text is determined, and data meeting the corresponding demand of the at least one natural language demand text is stored in the database. According to the method, the application capable of processing the natural language requirement text input by the user is provided, the application is achieved based on the mode of calling the large language model, and research and development personnel do not need to conduct application development.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to a method, device, equipment and medium for generating an application based on a large language model. Background Art

[0002] At present, the conventional application development process is: customers put forward application requirements, R&D personnel design applications according to the application requirements, and further write codes according to the designed applications. If the customer's application requirements change, the aforementioned application development process needs to be repeated. Therefore, the existing application development process has the following problems: high labor costs, long development time, and low demand compatibility.

[0003] Therefore, how to provide a new way to build applications has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] One object of the present application is to provide a new technical solution for application generation.

[0005] According to a first aspect of the present application, a method for generating an application based on a large language model is provided, comprising:

[0006] Obtain at least one natural language requirement text;

[0007] Determine, according to the at least one natural language requirement text, a target digital model structure corresponding to each natural language requirement text;

[0008] Generate a structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model;

[0009] According to the structured query language and the database, a query result that meets the at least one natural language requirement text is determined, and the database stores data that meets the requirements corresponding to the at least one natural language requirement text.

[0010] Optionally, determining the target digital model structure corresponding to each section of the natural language requirement text according to the at least one section of the natural language requirement text includes:

[0011] For any section of the natural language requirement text, perform a natural language processing operation on the natural language requirement text to obtain a processing result;

[0012] A digital-analog structure matching the processing result is searched from the digital-analog structure set as the target digital-analog structure.

[0013] Optionally, the processing result includes master data, and searching the digital-analog structure set for a digital-analog structure matching the processing result as the target digital-analog structure includes:

[0014] According to a preset mapping relationship, searching for a digital-analog structure matching the processing result from the digital-analog structure set as a target digital-analog structure;

[0015] Among them, the preset mapping relationship is used to reflect the corresponding relationship between different master data and the target digital model structure.

[0016] Optionally, after determining the query result that meets the at least one natural language requirement text according to the structured query language and the database, the method further includes:

[0017] According to preset arrangement rules, the query results that meet the at least one natural language requirement text are arranged and output.

[0018] Optionally, before arranging and outputting the query results that meet the at least one natural language requirement text according to a preset arrangement rule, the method further includes:

[0019] Displaying an arrangement mode selection option for each of the query results;

[0020] receiving a first selection input for the arrangement mode selection item;

[0021] In response to the first selection input, the preset arrangement rule is generated.

[0022] Optionally, after determining the query result that meets the at least one natural language requirement text according to the structured query language and the database, the method further includes:

[0023] For any query result, if the query result is wrong, repeat the step of generating a structured query language based on the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model.

[0024] Optionally, before generating the structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model, the method further includes:

[0025] Output the identifier of the large language model to be selected;

[0026] receiving a second selection input for an identifier of the large language model to be selected;

[0027] In response to the second selection input, a target large language model is determined.

[0028] According to a second aspect of the present application, a device for generating an application based on a large language model is provided, the device comprising:

[0029] An acquisition module, used for acquiring at least one natural language requirement text;

[0030] A first determination module is used to determine a target digital model structure corresponding to each section of the natural language requirement text according to the at least one section of the natural language requirement text;

[0031] A generating module, configured to generate a structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model;

[0032] The second determination module is used to determine the query result that meets the at least one natural language requirement text according to the structured query language and the database, wherein the database stores data that meets the requirements corresponding to the at least one natural language requirement text.

[0033] According to a third aspect of the present application, an electronic device is provided, the electronic device comprising the application generating device based on a large language model as described in the second aspect;

[0034] Alternatively, it includes a memory and a processor, the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the application generation method based on a large language model as described in any one of the first aspects.

[0035] According to a fourth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for generating an application based on a large language model according to any one of the first aspects is implemented.

[0036] The present application provides an application generation method based on a large language model, including: obtaining at least one natural language requirement text; determining the target numerical model structure corresponding to each natural language requirement text according to at least one natural language requirement text; generating a structured query language according to at least one natural language requirement text, the target numerical model structure corresponding to each natural language requirement text, and the target large language model; determining the query result that meets the at least one natural language requirement text according to the structured query language and the database, wherein the database stores data that meets the requirements corresponding to at least one natural language requirement text. The method can be realized as follows: after the user inputs the natural language requirement text, the query result that meets the natural language requirement text can be determined. That is, the present application provides an application that can process the natural language requirement text input by the user, and the application is implemented based on calling the large language model, without the need for R&D personnel to develop the application.

[0037] Other features and advantages of the present application will become apparent from the following detailed description of exemplary embodiments of the present application with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the application and, together with the description, serve to explain the principles of the application.

[0039] Figure 1 A hardware configuration of an electronic device for implementing an application generation method based on a large language model according to an embodiment of the present application is provided. Figure 1 ;

[0040] Figure 2 It is a flowchart of a method for generating an application based on a large language model provided according to an embodiment of the present application;

[0041] Figure 3 It is a schematic diagram of the structure of a device for generating an application based on a large language model provided according to an embodiment of the present application;

[0042] Figure 4 A hardware configuration of an electronic device for implementing an application generation method based on a large language model according to an embodiment of the present application is provided. Figure 2 . DETAILED DESCRIPTION

[0043] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0044] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0046] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0047] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0048] Figure 1 A hardware configuration of an electronic device for implementing an application generation method based on a large language model according to an embodiment of the present application is provided. Figure 1 .

[0049] The electronic device 1000 may be a terminal or a server. Further, the terminal may be a smart phone, a portable computer, a tablet computer, a palm computer, etc. The server may be a cloud server, etc.

[0050] The electronic device 1000 may include a processor 1100, a memory 1200, an interface device 1300, a communication device 1400, a display device 1500, an input device 1600, a speaker 1700, a microphone 1800, and the like. The processor 1100 may be a central processing unit CPU, a microprocessor MCU, and the like. The memory 1200 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, and the like. The interface device 1300 may include, for example, a USB interface, an earphone interface, and the like. The communication device 1400 may, for example, be capable of wired or wireless communication. The display device 1500 may be, for example, a liquid crystal display screen, a touch display screen, and the like. The input device 1600 may include, for example, a touch screen, a keyboard, and the like. The user may input / output voice information through the speaker 1700 and the microphone 1800.

[0051] Despite Figure 1 Multiple devices are shown for the electronic device 1000, but the present application may only involve some of the devices, for example, the electronic device 1000 only involves the memory 1200 and the processor 1100.

[0052] In the embodiment of the present application, the memory 1200 of the electronic device 1000 is used to store instructions, and the instructions are used to control the processor 1100 to execute the application generation method based on the large language model provided in the embodiment of the present application.

[0053] In the above description, the technician can design instructions according to the scheme disclosed in this application. How instructions control the processor to operate is well known in the art, so it will not be described in detail here.

[0054] This application provides an application generation method based on a large language model, which is applied to Figure 1 Electronic equipment shown.

[0055] like Figure 2 As shown, the application generation method based on the large language model provided in the present application includes the following steps S2100 to S2400.

[0056] Step S2100, obtaining at least one natural language requirement text.

[0057] In this embodiment, the natural language demand text is a text in which the user describes his or her own needs in natural language, and this application does not limit the content of the natural language demand text.

[0058] In an example, a natural language requirement text is: Query employee A's income last year.

[0059] In one embodiment of the present application, the electronic device provides an input interface for the user to input natural language demand information, and the natural language demand information is a natural language demand text or a natural language demand voice. The user inputs the natural language demand information through the input interface, and the electronic device obtains at least one segment of natural language demand information based on the user's input on the input interface, and further parses the obtained natural language demand information to obtain a natural language demand text.

[0060] Step S2200, based on at least one segment of natural language requirement text, determine a target digital model structure corresponding to each segment of the natural language requirement text.

[0061] In this embodiment, a natural language requirement text corresponds to a target digital model structure, and the target digital model structure is used to describe the requirement parameters corresponding to the natural language requirement text.

[0062] Taking the natural language requirement text of "query employee A's income last year" as an example, the target digital model structure can be as shown in Table 1 below.

[0063] Table 1

[0064]

[0065] Of course, the target digital-analog structure may also be the description information in Table 1 above.

[0066] In one embodiment of the present application, the above step S2200 is specifically implemented by the following steps S2210 and S2211.

[0067] Step S2210: for any section of natural language requirement text, perform a natural language processing operation on the natural language requirement text to obtain a processing result.

[0068] In this embodiment, a natural language processing (NLP) operation is performed on the natural language demand text to segment the natural language demand text and obtain text components of the natural language demand text, for example, to obtain what the subject, predicate, and object are respectively. The text components of the natural language demand text are recorded as processing results.

[0069] Step S2211, searching the digital-analog structure set for a digital-analog structure that matches the processing result as the target digital-analog structure.

[0070] In the embodiment of the present application, a digital-analog structure set is pre-stored in the electronic device, and the digital-analog structure includes a large number of digital-analog structures. After the processing result of the natural language requirement text is obtained based on the above step S2210, the most matching digital-analog structure is obtained from the digital-analog structure set as the target digital-analog structure according to the processing result.

[0071] In one embodiment of the present application, the above-mentioned step S2211 is specifically implemented by providing the following step S2211-1.

[0072] Step S2211 - 1 , according to a preset mapping relationship, searching for a digital-analog structure that matches the processing result from the digital-analog structure set as the target digital-analog structure.

[0073] Among them, the preset mapping relationship is used to reflect the corresponding relationship between different master data and the target digital model structure.

[0074] In this embodiment, the master data is used to describe the core of the processing result corresponding to the natural language requirement text. Taking the natural language requirement text as "query employee A's income last year" as an example, the master data is: employee A, last year, income.

[0075] Furthermore, a preset mapping relationship is pre-stored in the electronic device, and the preset mapping relationship can be represented in a table.

[0076] Based on the above content, the specific implementation of the above step S2211-1 is: determine the master data of the processing results corresponding to the natural language requirement text, and search for digital model results matching the master data from the digital model structure set as the target digital model structure through keyword matching and other methods.

[0077] Step S2300, generating a structured query language according to at least one natural language requirement text, a target digital model structure corresponding to each natural language requirement text, and a target large language model.

[0078] The target large language model may be any large language model, and the target large language model may also be a large language model that meets user needs. For the latter, in one embodiment of the present application, the large language model-based application generation method provided by the present application further includes a step of determining the target large language model before the above step S2300, which is specifically implemented by the following steps S2310 to S2312.

[0079] Step S2310: output the identifier of the large language model to be selected.

[0080] The electronic device outputs an identifier of a callable large language model, such as a name, as an identifier of the large language model to be selected.

[0081] Step S2311: receiving a second selection input for an identifier of a large language model to be selected.

[0082] Step S2312: In response to the second selection input, determine the target large language model.

[0083] In this embodiment, the second selection input is input by the user. Specifically, the user selects the identifier of the large language model that meets his or her needs from the identifiers of the large language models to be selected by voice input or touch input. The electronic device recognizes the user's selection operation on the identifier of the large language model to be selected as the second selection input. Further, the large language model corresponding to the identifier of the large language model to be selected represented by the second selection input is recorded as the target large language model.

[0084] Based on the above steps S2310 to S2312, a large language model that meets the user's needs is called when executing the above step S2300. In this way, the application generation method based on the large language model provided by the present application can meet the personalized needs of users.

[0085] For the above step S2300, at least one natural language requirement text and the target digital model structure corresponding to each natural language requirement text are input into the target large language model, and the target large language model is instructed to generate a structured query language (SQL). On this basis, the target large language model outputs SQL.

[0086] After executing the above step S2300, the electronic device executes the following step S2400.

[0087] Step S2400: Determine, based on the structured query language and the database, a query result that meets at least one natural language requirement text.

[0088] The database stores data that meets the requirements corresponding to at least one natural language requirement text.

[0089] Taking the natural language demand text "query employee A's income last year" as an example, the database is a database that stores the historical income information of different employees.

[0090] For the above step S2400, through the structured query language, query results that meet at least one natural language requirement text can be queried from the database, for example, the income of employee A last year can be queried.

[0091] Based on the above content, it can be seen that the application generation method based on the large language model provided by this application can achieve: after the user enters the natural language demand text, the query results that meet the natural language demand text can be determined. That is, this application provides an application that can process the natural language demand text entered by the user, and the application is implemented based on calling the large language model, without the need for R&D personnel to develop the application.

[0092] The present application provides an application generation method based on a large language model, including: obtaining at least one natural language requirement text; determining the target numerical model structure corresponding to each natural language requirement text according to at least one natural language requirement text; generating a structured query language according to at least one natural language requirement text, the target numerical model structure corresponding to each natural language requirement text, and the target large language model; determining the query result that meets the at least one natural language requirement text according to the structured query language and the database, wherein the database stores data that meets the requirements corresponding to at least one natural language requirement text. The method can be realized as follows: after the user inputs the natural language requirement text, the query result that meets the natural language requirement text can be determined. That is, the present application provides an application that can process the natural language requirement text input by the user, and the application is implemented based on calling the large language model, without the need for R&D personnel to develop the application.

[0093] In one embodiment of the present application, the application generation method based on the large language model adopted in the present application further includes the following step S2500 after the above step S2400.

[0094] Step S2500: Arrange and output the query results that meet at least one natural language requirement text according to a preset arrangement rule.

[0095] In this embodiment, the preset slice arrangement rule is used to describe the arrangement method of the query results, such as the arrangement position and the occupied area.

[0096] In an example, the preset arrangement rule may be: arranging the corresponding query results horizontally according to the order of the acquired natural speech requirement texts, and representing the query results corresponding to the natural language requirement texts acquired in the first order according to a curve graph.

[0097] After the query results that meet at least one natural language requirement text are arranged according to the preset arrangement rules, the arranged query results are output.

[0098] In one embodiment of the present application, the large language model-based application generation method provided by the present application further includes the following steps S2510 to S2512 before the above step S2500.

[0099] Step S2510, displaying arrangement options for each query result.

[0100] In one example, the layout selection items may be exemplified as: layout position selection sub-items (such as left, right, center, etc.), occupied area selection sub-items (such as 1 / 4 of the page width and 1 / 4 of the page height, etc.), and chart selection sub-items (such as bar charts, pie charts, and curve charts, etc.).

[0101] Step S2511, receiving a first selection input for an arrangement mode selection item.

[0102] The user selects an arrangement mode option that meets his / her needs from the arrangement mode options according to his / her needs. In this application, the aforementioned selection operation of the aforementioned user is recorded as the first selection input.

[0103] Step S2512: generating a preset arrangement rule in response to the first selection input.

[0104] After receiving the first selection input, the arrangement mode selection item selected by the user is determined from the arrangement mode selection items for each query result, and further, the arrangement mode selection item selected by the user is used as a preset arrangement rule.

[0105] In this embodiment, through the above steps S2510 to S2512, the user can customize the preset arrangement rules. In this way, the application generation method based on the large language model provided by the present application can further meet the personalized needs of users.

[0106] In one embodiment of the present application, the large language model-based application generation method provided by the present application further includes the following step S2600 after the above step S2400.

[0107] Step S2600, for any query result, if the query result is wrong, repeat the step of generating a structured query language based on at least one natural speech demand text, the target numerical model result corresponding to each natural language demand text, and the target large language model.

[0108] In one embodiment of the present application, the electronic device may display a control. When the control is triggered by the user, the above step S2300 is repeated. On this basis, after viewing the query results, if the user believes that there is an error in the query results (for example, the data is obviously abnormal, the data is missing), the above control is triggered to indicate that the electronic device query result is wrong. When the electronic device detects that the above control is triggered, it repeats the above step S2300. When repeating step S2300, the target large language model will adjust the structured query language outputted last time to generate a new structured query language. Furthermore, based on the new structured query language and the database, a new query result that meets at least one natural language requirement text can be determined.

[0109] The present application also provides an application generation device 300 based on a large language model, such as Figure 3 As shown, including:

[0110] An acquisition module 310 is used to acquire at least one natural language requirement text;

[0111] A first determination module 320 is used to determine a target digital model structure corresponding to each section of the natural language requirement text according to the at least one section of the natural language requirement text;

[0112] A generating module 330, configured to generate a structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model;

[0113] The second determination module 340 is used to determine the query result that meets the at least one natural language requirement text according to the structured query language and the database, wherein the database stores data that meets the requirements corresponding to the at least one natural language requirement text.

[0114] In one embodiment of the present application, the first determining module 320 is specifically configured to:

[0115] For any section of the natural language requirement text, perform a natural language processing operation on the natural language requirement text to obtain a processing result;

[0116] A digital-analog structure matching the processing result is searched from the digital-analog structure set as the target digital-analog structure.

[0117] In one embodiment of the present application, the first determining module 320 is specifically configured to:

[0118] According to a preset mapping relationship, searching for a digital-analog structure matching the processing result from the digital-analog structure set as a target digital-analog structure;

[0119] Among them, the preset mapping relationship is used to reflect the corresponding relationship between different master data and the target digital model structure.

[0120] In one embodiment of the present application, the application generation device 300 based on the large language model provided by the present application further includes:

[0121] The arrangement output module is used to arrange and output the query results that meet the at least one natural language requirement text according to a preset arrangement rule.

[0122] In one embodiment of the present application, the generating module 330 is further used to:

[0123] Displaying an arrangement mode selection option for each of the query results;

[0124] receiving a first selection input for the arrangement mode selection item;

[0125] In response to the first selection input, the preset arrangement rule is generated.

[0126] In one embodiment of the present application, the application generation device 300 based on the large language model provided by the present application further includes:

[0127] A repeated execution module is used to repeat the step of generating a structured query language based on the at least one natural language requirement text, the target numerical model structure corresponding to each natural language requirement text, and the target large language model for any query result if the query result is wrong.

[0128] In one embodiment of the present application, the application generation device 300 based on the large language model provided by the present application further includes:

[0129] A third determination module is used to output an identifier of a large language model to be selected;

[0130] receiving a second selection input for an identifier of the large language model to be selected;

[0131] In response to the second selection input, a target large language model is determined.

[0132] The present application also provides an electronic device, the electronic device comprising any one of the large language model-based application generation devices 300 provided in the above device embodiments;

[0133] Or, if Figure 4 As shown, the electronic device 400 includes a memory 410 and a processor 420, wherein the memory 410 is used to store computer instructions, and the processor 420 is used to call the computer instructions from the memory 410 to execute the application generation method based on the large language model as described in any one of the above method embodiments.

[0134] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for generating an application based on a large language model according to any one of the above method embodiments is implemented.

[0135] The present application may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present application.

[0136] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0137] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0138] The computer program instructions for performing the operation of the present application can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions can be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). In some embodiments, by using the state information of a computer-readable program instruction to personalize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), the electronic circuit can execute a computer-readable program instruction, thereby realizing various aspects of the present application.

[0139] Various aspects of the present application are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0140] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0141] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0142] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a part of a module, program segment or instruction, and the part of the module, program segment or instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0143] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present application is defined by the appended claims.

Claims

1. A method for generating an application based on a large language model, characterized in that: include: Obtain at least one natural language requirement text; Determine, according to the at least one natural language requirement text, a target digital model structure corresponding to each natural language requirement text; Generate a structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model; According to the structured query language and the database, a query result that meets the at least one natural language requirement text is determined, and the database stores data that meets the requirements corresponding to the at least one natural language requirement text.

2. The method according to claim 1, characterized in that The step of determining, based on the at least one natural language requirement text, a target digital model structure corresponding to each natural language requirement text comprises: For any section of the natural language requirement text, perform a natural language processing operation on the natural language requirement text to obtain a processing result; A digital-analog structure matching the processing result is searched from the digital-analog structure set as the target digital-analog structure.

3. The method according to claim 2, characterized in that The processing result includes master data, and searching the digital-analog structure set for a digital-analog structure matching the processing result as a target digital-analog structure includes: According to a preset mapping relationship, searching for a digital-analog structure matching the processing result from the digital-analog structure set as a target digital-analog structure; Among them, the preset mapping relationship is used to reflect the corresponding relationship between different master data and the target digital model structure.

4. The method according to claim 1, characterized in that: After determining the query result that meets the at least one natural language requirement text according to the structured query language and the database, the method further includes: According to preset arrangement rules, the query results that meet the at least one natural language requirement text are arranged and output.

5. The method according to claim 4, characterized in that Before arranging and outputting the query results that meet the at least one natural language requirement text according to the preset arrangement rules, the method further includes: Displaying an arrangement mode selection option for each of the query results; receiving a first selection input for the arrangement mode selection item; In response to the first selection input, the preset arrangement rule is generated.

6. The method according to claim 1, characterized in that After determining the query result that meets the at least one natural language requirement text according to the structured query language and the database, the method further includes: For any query result, if the query result is wrong, repeat the step of generating a structured query language based on the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model.

7. The method according to claim 1, characterized in that Before generating the structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model, the method further includes: Output the identifier of the large language model to be selected; receiving a second selection input for an identifier of the large language model to be selected; In response to the second selection input, a target large language model is determined.

8. An application generation device based on a large language model, characterized in that: The device comprises: An acquisition module, used for acquiring at least one natural language requirement text; A first determination module is used to determine a target digital model structure corresponding to each section of the natural language requirement text according to the at least one section of the natural language requirement text; A generating module, configured to generate a structured query language according to the at least one natural language requirement text, the target digital model structure corresponding to each natural language requirement text, and the target large language model; The second determination module is used to determine the query result that meets the at least one natural language requirement text according to the structured query language and the database, wherein the database stores data that meets the requirements corresponding to the at least one natural language requirement text.

9. An electronic device, characterized in that: The electronic device comprises the application generation device based on the large language model as claimed in claim 8; Alternatively, it includes a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call the computer instructions from the memory to execute the application generation method based on a large language model as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for generating an application based on a large language model according to any one of claims 1 to 7 is implemented.

Images