Zero-code application development method, first server and second server

Abstract

The invention provides a zero-code application development method, a first server and a second server. The method is used for improving the development efficiency of zero-code applications. The method comprises the following steps: in response to an application development instruction sent by a user, determining the type of the application development instruction based on the application development instruction; filling a preset instruction template corresponding to the type of the application development instruction by utilizing the application development instruction to obtain a target instruction; sending the target instruction to a second server, so that the second server obtains a target JSON result according to the target instruction by using a plurality of artificial intelligence AI models; after the target ISON result sent by the second server is received, analyzing the target JSON result by using a preset algorithm to obtain a target code; and according to the target code, generating a target application corresponding to the application development instruction.

Description

Background Art

[0002] In recent years, with the increasing maturity of software engineering technology, a "zero-code" technology that does not require programming has emerged, allowing end users who do not understand computer programming technology to use this technology to develop applications that meet specific business needs without writing any computer programming language code. They only need to use a "drag and drop" method (such as "drag and drop" to build the application's form model, process model, printing model, and report model, etc.) to complete the development of applications. This application development process is called "zero-code" development or "codeless" development, and the developed applications are usually called "zero-code" applications or "codeless" applications.

[0003] However, in the prior art, only some simple application models can be constructed by dragging and dropping. Some slightly complex applications still need to be developed manually, resulting in low development efficiency of zero-code applications. Summary of the invention

[0004] In an exemplary embodiment of the present disclosure, a method for developing a zero-code application is provided to improve the development efficiency of the zero-code application.

[0005] A first aspect of the present disclosure provides a method for developing a zero-code application, which is applied to a first server, and the method includes:

[0006] In response to an application development instruction sent by a user, determining a type of the application development instruction based on the application development instruction;

[0007] Filling a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction;

[0008] Sending the target instruction to the second server, so that the second server uses multiple artificial intelligence AI models to obtain the target JSON result according to the target instruction;

[0009] After receiving the target ISON result sent by the second server, the target JSON result is parsed using a preset algorithm to obtain a target code;

[0010] The target application corresponding to the application development instruction is generated according to the target code.

[0011] In this embodiment, the target instruction is obtained by filling the template of the preset instruction corresponding to the type of application development instruction sent by the user, and the target instruction is sent to the second server, so that the second server uses multiple artificial intelligence AI models to obtain the target JSON result according to the target instruction. After receiving the target ISON result sent by the second server, the target JSON result is parsed by a preset algorithm to obtain the target code; according to the target code, the target application corresponding to the application development instruction is generated. Therefore, in the embodiment of the present application, not only can the application be generated by dragging and dropping, but also in the embodiment of the present application, the JSON result corresponding to the application generation instruction is determined by using an AI model, and the generated JSON result is parsed to generate the target code to obtain the target application. Therefore, in the embodiment of the present application, manual development is not required. The embodiment of the present application combines the existing AI model to automatically generate the corresponding application, which improves the development efficiency of zero-code applications.

[0012] In one embodiment, using the application development instruction to fill a preset instruction template corresponding to the type of the application development instruction to obtain a target instruction includes:

[0013] For any field in the instruction template, obtaining target data corresponding to the field in the development instruction, and filling the field with the target data to obtain a target field;

[0014] The target instruction is obtained based on the target fields respectively corresponding to the fields in the instruction template.

[0015] This embodiment obtains the target instruction by acquiring the target data corresponding to each field in the instruction template in the development instruction and filling each field respectively, thereby ensuring the accuracy of the zero-code application development.

[0016] In one embodiment, determining the type of the application development instruction based on the application development instruction includes:

[0017] Obtaining a type identifier in the application development instruction;

[0018] The type of the application development instruction corresponding to the type identifier is determined by using the preset corresponding relationship between the type identifier and the type of the application development instruction.

[0019] In this embodiment, the type of the application development instruction corresponding to the type identifier is determined by using the preset corresponding relationship between the type identifier and the type of the application development instruction, so that the determined type of the application development instruction is more accurate.

[0020] In one embodiment, the types of application development instructions include data modeling instruction types, process design instruction types, and page building instruction types; wherein:

[0021] The data modeling instruction type is used to instruct the creation of a new entity application model with a specified business function;

[0022] The process design instruction type is used to instruct the creation of a new entity application model with multiple process nodes;

[0023] The page construction instruction type is used to instruct to rebuild a page of a specified entity application model to obtain a new entity application model.

[0024] In this embodiment, different types of applications can be developed through different types of application development instructions to meet the needs of multiple scenarios.

[0025] A second aspect of the present disclosure provides a method for developing a zero-code application, which is applied to a second server, and the method includes:

[0026] Receiving a target instruction sent by the first server, and generating multiple JSON results based on the target instruction using multiple artificial intelligence AI models, wherein the target instruction is obtained by the first server filling a preset instruction template corresponding to the type of the application development instruction using the application development instruction sent by the user;

[0027] According to the multiple JSON results, a target JSON result is obtained;

[0028] The target JSON result is sent to the first server, so that the first server uses a preset algorithm to parse the JSON result to obtain a target code, and obtains a target application corresponding to the application development instruction based on the target code.

[0029] In the embodiment of the present application, multiple artificial intelligence AI models are used to generate multiple JSON results based on the received target instructions, and the target JSON result is obtained according to the multiple JSON results; then the target JSON result is sent to the first server, so that the first server uses a preset algorithm to parse the JSON result to obtain the target code, and according to the target code, the target application corresponding to the application development instruction is obtained. Therefore, in the implementation of the present application, not only can the application be generated by dragging and dropping, but also in the embodiment of the present application, the AI ​​model is used to determine the JSON result corresponding to the application generation instruction, and the generated JSON result is parsed to generate the target code to obtain the target application. Therefore, in the embodiment of the present application, manual development is not required. The embodiment of the present application combines the existing AI model to automatically generate the corresponding application, which improves the development efficiency of zero-code applications.

[0030] In one embodiment, any JSON result of the multiple JSON results includes multiple fields and sub-results corresponding to the multiple fields;

[0031] The step of obtaining a target JSON result according to the multiple JSON results includes:

[0032] For any field, counting the sub-results corresponding to the field in the multiple JSON results and the number of the sub-results; and,

[0033] Based on the number of the sub-results and the preset weights of the multiple AI models, obtaining a target sub-result corresponding to the field;

[0034] According to the target sub-results corresponding to each field, the target JSON result is obtained.

[0035] In the embodiment of the present application, the target sub-result corresponding to each field is determined by the number of sub-results corresponding to each field and the preset weight of the AI ​​model corresponding to each field, and the target JSON result is obtained according to the target sub-result corresponding to each field. Thus, the accuracy of the target JSON result is improved.

[0036] In one embodiment, obtaining a target sub-result corresponding to the field based on the number of the sub-results and the preset weights of the multiple AI models includes:

[0037] For any sub-result, if the number of the sub-results is greater than the specified number, the preset weights of the AI ​​models corresponding to the sub-results are added together to obtain the score of the sub-result; or,

[0038] If the number of the sub-results is not greater than the specified number, the preset weight of the AI ​​model corresponding to the sub-result is determined as the sub-result score;

[0039] The target sub-result is obtained according to the scores of the sub-results.

[0040] In the embodiment of the present application, the scores of the respective sub-results are obtained by the number of the sub-results and the preset weights of the multiple AI models, and the target sub-result is obtained according to the scores of the sub-results. Thus, the accuracy of the target sub-result is guaranteed.

[0041] In one embodiment, obtaining the target sub-result according to the scores of the sub-results includes:

[0042] The sub-result with the highest score among the sub-results is determined as the target sub-result corresponding to the field.

[0043] In the embodiment of the present application, the sub-result with the highest score among the sub-results is determined as the target sub-result corresponding to the field, thereby ensuring the accuracy of the target sub-result.

[0044] A third aspect of the present disclosure provides a first server, comprising a processor and a memory, wherein the processor and the memory are connected via a bus;

[0045] The memory stores a computer program, and the processor is configured to perform the following operations based on the computer program:

[0046] In response to an application development instruction sent by a user, determining a type of the application development instruction based on the application development instruction;

[0047] Filling a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction;

[0048] Sending the target instruction to the second server, so that the second server uses multiple artificial intelligence AI models to obtain the target JSON result according to the target instruction;

[0049] After receiving the target ISON result sent by the second server, the target JSON result is parsed using a preset algorithm to obtain a target code;

[0050] The target application corresponding to the application development instruction is generated according to the target code.

[0051] In one embodiment, the processor executes the step of filling a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction, which is specifically configured as follows:

[0052] For any field in the instruction template, obtaining target data corresponding to the field in the development instruction, and filling the field with the target data to obtain a target field;

[0053] The target instruction is obtained based on the target fields respectively corresponding to the fields in the instruction template.

[0054] In one embodiment, the processor executes the step of determining the type of the application development instruction based on the application development instruction, and is specifically configured to:

[0055] Obtaining a type identifier in the application development instruction;

[0056] The type of the application development instruction corresponding to the type identifier is determined by using the preset corresponding relationship between the type identifier and the type of the application development instruction.

[0057] In one embodiment, the types of application development instructions include data modeling instruction types, process design instruction types, and page building instruction types; wherein:

[0058] The data modeling instruction type is used to instruct the creation of a new entity application model with a specified business function;

[0059] The process design instruction type is used to instruct the creation of a new entity application model with multiple process nodes;

[0060] The page construction instruction type is used to instruct to rebuild a page of a specified entity application model to obtain a new entity application model.

[0061] A fourth aspect of the present disclosure provides a second server, comprising a processor and a memory, wherein the processor and the memory are connected via a bus;

[0062] The memory stores a computer program, and the processor is configured to perform the following operations based on the computer program:

[0063] Receiving a target instruction sent by the first server, and generating multiple JSON results based on the target instruction using multiple artificial intelligence AI models, wherein the target instruction is obtained by the first server filling a preset instruction template corresponding to the type of the application development instruction using the application development instruction sent by the user;

[0064] According to the multiple JSON results, a target JSON result is obtained;

[0065] The target JSON result is sent to the first server, so that the first server uses a preset algorithm to parse the JSON result to obtain a target code, and obtains a target application corresponding to the application development instruction based on the target code.

[0066] In one embodiment, any JSON result of the multiple JSON results includes multiple fields and sub-results corresponding to the multiple fields;

[0067] The processor executes the step of obtaining a target JSON result according to the multiple JSON results, and is specifically configured as follows:

[0068] For any field, counting the sub-results corresponding to the field in the multiple JSON results and the number of the sub-results; and,

[0069] Based on the number of the sub-results and the preset weights of the multiple AI models, obtaining a target sub-result corresponding to the field;

[0070] According to the target sub-results corresponding to each field, the target JSON result is obtained.

[0071] In one embodiment, the processor executes the method based on the number of each sub-result and the preset weights of the multiple AI models to obtain the target sub-result corresponding to the field, which is specifically configured as follows:

[0072] For any sub-result, if the number of the sub-results is greater than the specified number, the preset weights of the AI ​​models corresponding to the sub-results are added together to obtain the score of the sub-result; or,

[0073] If the number of the sub-results is not greater than the specified number, the preset weight of the AI ​​model corresponding to the sub-result is determined as the sub-result score;

[0074] The target sub-result is obtained according to the scores of the sub-results.

[0075] In one embodiment, the processor performs the step of obtaining the target sub-result according to the scores of the sub-results, and is specifically configured as follows:

[0076] The sub-result with the highest score among the sub-results is determined as the target sub-result corresponding to the field.

[0077] According to a fifth aspect provided by an embodiment of the present disclosure, a computer storage medium is provided, wherein the computer storage medium stores a computer program, and the computer program is used to execute the method described in the first aspect and / or the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0079] Figure 1 This is one of the schematic diagrams of applicable scenarios in one embodiment of the present disclosure;

[0080] Figure 2 This is a second schematic diagram of an applicable scenario in an embodiment of the present disclosure;

[0081] Figure 3 This is one of the flowcharts of a method for developing a zero-code application according to an embodiment of the present disclosure;

[0082] Figure 4 A schematic diagram of a process for determining a target JSON result according to an embodiment of the present disclosure;

[0083] Figure 5 A schematic diagram of a process for determining a target sub-result according to an embodiment of the present disclosure;

[0084] Figure 6 A schematic diagram of a platform framework of a method for developing a zero-code application according to an embodiment of the present disclosure;

[0085] Figure 7 A schematic diagram of the structure of an AI model API according to an embodiment of the present disclosure;

[0086] Figure 8 The second flowchart of the method for developing a zero-code application according to an embodiment of the present disclosure is as follows;

[0087] Fig. 9 This is one of the schematic diagrams of a zero-code application development device according to an embodiment of the present disclosure;

[0088] Fig.10 This is a second schematic diagram of a zero-code application development device according to an embodiment of the present disclosure;

[0089] Fig.11 The figure is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0090] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0091] In the embodiments of the present disclosure, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0092] The application scenarios described in the embodiments of the present disclosure are intended to more clearly illustrate the technical solutions of the embodiments of the present disclosure, and do not constitute a limitation on the technical solutions provided by the embodiments of the present disclosure. It is known to those skilled in the art that with the emergence of new application scenarios, the technical solutions provided by the embodiments of the present disclosure are also applicable to similar technical problems. In the description of the present disclosure, unless otherwise specified, the meaning of "multiple" is two or more.

[0093] In the prior art, only some simple application models can be constructed by dragging and dropping. Some slightly complex applications still need to be developed manually, which results in low development efficiency of zero-code applications.

[0094] Therefore, the present disclosure provides a method for developing a zero-code application, by filling the template of the preset instruction corresponding to the type of the application development instruction based on the type of the application development instruction sent by the user to obtain the target instruction, and sending the target instruction to the second server, so that the second server uses multiple artificial intelligence AI (Artificial Intelligence) models according to the target instruction to obtain the target JSON (JavaScript Object Notation, JS object notation) result. After receiving the target ISON result sent by the second server, the target JSON result is parsed by a preset algorithm to obtain the target code; according to the target code, the target application corresponding to the application development instruction is generated. Therefore, in the embodiment of the present application, not only can the application be generated by dragging and dropping, but also in the embodiment of the present application, the JSON result corresponding to the application generation instruction is determined by using the AI ​​model, and the generated JSON result is parsed to generate the target code to obtain the target application. Therefore, in the embodiment of the present application, manual development is not required. The embodiment of the present application combines the existing AI model to automatically generate the corresponding application, which improves the development efficiency of zero-code applications. Below, the scheme of the present disclosure is described in detail in conjunction with the accompanying drawings.

[0095] like Figure 1 As shown, an application scenario of a zero-code application development method includes a first server 110 and a second server 120.

[0096] In a possible application scenario, the first server 110 responds to an application development instruction sent by a user, and determines the type of the application development instruction based on the application development instruction; then uses the application development instruction to fill in a preset instruction template corresponding to the type of the application development instruction to obtain a target instruction; the first server 110 sends the target instruction to the second server 120, and after the second server 120 receives the target instruction, it uses multiple artificial intelligence AI models to obtain a target JSON result according to the target instruction, and sends the target JSON result to the first server 110. After the first server 110 receives the target ISON result sent by the second server, it uses a preset algorithm to parse the target JSON result to obtain a target code, and generates the target application corresponding to the application development instruction based on the target code.

[0097] In a possible application scenario, Figure 2 As shown, the application scenario includes a first server 110, a second server 120 and a terminal device 130. Among them:

[0098] The user sends an application development instruction through the terminal device 130. After receiving the application development instruction, the first server 110, in response to the application development instruction sent by the user, determines the type of the application development instruction based on the application development instruction; then fills a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction; the first server 110 sends the target instruction to the second server 120. After receiving the target instruction, the second server 120 uses multiple artificial intelligence AI models to obtain a target JSON result according to the target instruction and sends the target JSON result to the first server 110. After receiving the target ISON result sent by the second server, the first server 110 parses the target JSON result using a preset algorithm to obtain a target code, and generates a target application corresponding to the application development instruction according to the target code, and displays it through the terminal device 130.

[0099] Among them, Figure 1 Information interaction can be carried out between the first server 110, the second server 120 and the terminal device 130 through a communication network. Among them, the communication method adopted by the communication network can be divided into a wireless communication method or a wired communication method.

[0100] Exemplarily, the first server 110 can access the network through cellular mobile communication technology and communicate with the second server 120 and the terminal device 130. Among them, the cellular mobile communication technology, for example, includes the fifth-generation mobile communication (5th Generation Mobile Networks, 5G) technology.

[0101] Optionally, the first server 110 can access the network through a short-range wireless communication method and communicate with the second server 120 and the terminal device 130. Among them, the short-range wireless communication method, for example, includes wireless fidelity (Wireless Fidelity, Wi-Fi) technology.

[0102] Among them, in the description of this application, only a single first server 110, a single second server 120 and a single terminal device 130 are described in detail. However, those skilled in the art should understand that the shown first server 110, second server 120 and terminal device 130 are intended to represent the operations of the first server 110, second server 120 and terminal device 130 involved in the technical solution of this application. It does not imply any limitation on the number, type or location of the first server 110, second server 120 and terminal device 130. It should be noted that if additional modules are added to or individual modules are removed from the illustrated environment, the underlying concept of the exemplary embodiments of this application will not be changed.

[0103] It should be noted that the zero-code application development method proposed in this application is not only applicable to Figure 1 as well as Figure 2 The application scenarios shown are also applicable to any development device with zero-code applications.

[0104] The following describes the method for developing a zero-code application in an exemplary embodiment of the present application in combination with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the methods and principles of the present application, and the implementation methods of the present application are not subject to any limitations in this regard.

[0105] like Figure 3 FIG. 1 is a flow chart of the method for developing a zero-code application of the present disclosure, which may include the following steps:

[0106] Step 301: The first server responds to the application development instruction sent by the user and determines the type of the application development instruction based on the application development instruction;

[0107] In one embodiment, step 301 can be specifically implemented as follows: obtaining the type identifier in the application development instruction; using the pre-set type identifier and the type correspondence between the application development instruction, determining the type of the application development instruction corresponding to the type identifier. Table 1 shows the type correspondence between the type identifier and the type of the application development instruction:

[0108] Table 1:

[0109]

[0110]

[0111] As shown in Table 1, if the type identifier is a, it is determined that the type of the corresponding application development instruction is type 1.

[0112] Step 302: The first server uses the application development instruction to fill in a preset instruction template corresponding to the type of the application development instruction to obtain a target instruction;

[0113] In one embodiment, step 302 can be specifically implemented as follows: for any field in the instruction template, obtaining the target data corresponding to the field in the development instruction, filling the field with the target data to obtain the target field; and obtaining the target instruction based on the target fields corresponding to each field in the instruction template.

[0114] The fields of the instruction template in the embodiment of the present application include instructions, background information, input data, output indicators, etc. Among them, instructions are used to instruct the AI ​​model to perform specific tasks. Background information is contextual information that guides the AI ​​model to better specify tasks. Input data is used to inform the AI ​​model of the data that needs to be processed. The output indicator is used to inform the AI ​​model of the type or format of the data output.

[0115] The instruction template in the embodiment of the present application is a prompt template, but the specific format of the instruction template is not limited in the embodiment of the present application, and can be set according to the actual situation. In addition, the prompt template is a template in the prior art, and the embodiment of the present application will not be repeated here. In addition, the fields of the instruction template in the embodiment of the present application can be set according to the actual situation, and the embodiment of the present application does not limit the fields included in the instruction template.

[0116] The types of application development instructions in the embodiment of the present application include data modeling instruction type, process design instruction type and page building instruction type. Among them:

[0117] (1) The data modeling instruction type is used to instruct the creation of a new entity application model with specified business functions;

[0118] For example, the data modeling instruction type instruction may be: building a student management model, building a user management model, etc. The specified business function may also be a function such as data calculation and data query.

[0119] The designated spy function in the embodiment of the present application can be set according to actual conditions, and the embodiment of the present application does not limit the designated business function.

[0120] (2) The process design instruction type is used to instruct the creation of a new entity application model with multiple process nodes;

[0121] The instructions of the process design instruction type may be: "Generate a leave process, including initiator and approver nodes. The approver node is approved by the superior of the initiator."

[0122] (3) The page construction instruction type is used to instruct the page of the specified entity application model to be rebuilt to obtain a new entity application model.

[0123] The instructions of the page building instruction type can be: "Generate a form page based on the student management model, and use gray and white color for the page background."

[0124] Step 303: The first server sends the target instruction to the second server;

[0125] Step 304: The second server receives the target instruction sent by the first server, and generates multiple JSON results based on the target instruction using multiple artificial intelligence AI models;

[0126] The AI ​​model in the embodiments of the present application may be a ChatGLM (Chat Generalize Linear Model), a Llama model, a ChatGPT (Chat Generative Pre-trained Transformer) model, etc. The embodiments of the present application do not limit the AI ​​model here, and the specific AI model may be limited according to actual conditions.

[0127] Wherein, any JSON result among the multiple JSON results includes multiple fields and sub-results corresponding to the multiple fields;

[0128] In the embodiment of the present application, each AI model generates a JSON result including the same fields, but the sub-results corresponding to each field may be the same or different. For example, the sub-result corresponding to the age field may be varchar or int.

[0129] Secondly, the generation of multiple JSON results based on target instructions in the embodiment of the present application belongs to the prior art, and the embodiment of the present application will not be repeated here.

[0130] Step 305: The second server obtains a target JSON result according to the multiple JSON results;

[0131] Next, the method of determining the target JSON result in step 305 is described in detail. Figure 4 As shown, a flowchart for determining a target JSON result may include the following steps:

[0132] Step 401: for any field, counting the sub-results corresponding to the field in the multiple JSON results and the number of the sub-results;

[0133] For example, taking the field age as an example, if the sub-result corresponding to the field age generated by AI model 1 is int, the sub-result corresponding to the field ang generated by AI model 2 is int, and the sub-result corresponding to the field and generated by AI model 3 is varchar, then the number of sub-results int for the field age is determined to be 2. The number of sub-results varchar for the field age is determined to be 1.

[0134] Step 402: Based on the number of each sub-result and the preset weights of the multiple AI models, obtain a target sub-result corresponding to the field;

[0135] like Figure 5 As shown, it is a schematic diagram of a process for determining a target sub-result, which may include the following steps:

[0136] Step 501: for any sub-result, determine whether the number of the sub-results is greater than a specified number, if so, execute step 502, if not, execute step 503;

[0137] The specified number in the embodiment of the present application is 1, but the embodiment of the present application does not limit the specified number here. The specified number in the embodiment of the present application can be set according to actual conditions.

[0138] Step 502: Add the preset weights of the AI ​​models corresponding to the sub-results to obtain the scores of the sub-results;

[0139] Step 503: Determine the preset weight of the AI ​​model corresponding to the sub-result as the sub-result score;

[0140] The preset weights corresponding to each AI model in the embodiment of the present application are pre-configured. The embodiment of the present application does not limit the weights of the AI ​​models, which can be set according to actual conditions. The embodiment of the present application does not limit the number of AI models.

[0141] Step 504: Obtain the target sub-result according to the scores of the sub-results.

[0142] In one embodiment, step 504 may be specifically implemented as: determining the sub-result with the highest score among the sub-results as the target sub-result corresponding to the field.

[0143] Step 403: Obtain the target JSON result according to the target sub-result corresponding to each field.

[0144] The target sub-results corresponding to the fields are used to fill in the positions corresponding to the fields to obtain the target JSON result.

[0145] Step 306: The second server sends the target JSON result to the first server;

[0146] Step 307: After receiving the target ISON result sent by the second server, the first server parses the target JSON result using a preset algorithm to obtain a target code;

[0147] In the embodiment of the present application, the preset algorithm for parsing the target JSON result can be set according to the actual situation, and the embodiment of the present application does not limit the preset algorithm.

[0148] Step 308: The first server generates the target application corresponding to the application development instruction according to the target code.

[0149] In one embodiment, step 308 may be specifically implemented as follows: the first server executes the target code to generate a target application corresponding to the application development instruction.

[0150] Below, the platform framework of the zero-code application development method in this application is briefly introduced. Figure 6 As shown, it is a schematic diagram of the platform framework for zero-code application development in the embodiment of the present application. It can be seen from the figure that it includes a development layer, a technical layer and a data layer. Among them, the data layer includes a variety of databases, including but not limited to redis (Remote Dictionary Server, remote dictionary service) database, mysql (My Structured Query Language. My Structured Query Language) database, kafka database and minio database. The technical layer includes pre-configured services such as container encoding, message service, service gateway and log server. The development layer mainly includes functions used for zero-code application development. Among them, the AI ​​model API (Application Programming Interface) is used to call the AI ​​model to generate the corresponding target JSON result. The data modeling function is used to create a new entity application model with specified business functions. The process design function is used to create a new entity application model with multiple process nodes. The page building function is used to rebuild the page of the specified entity application model to obtain a new entity application model.

[0151] like Figure 7 As shown in the figure, it is a structural diagram of the AI ​​model API. It can be seen from the figure that the AI ​​model API consists of two aspects. One is the LangChain connector, that is, through the open source LangChain architecture, multiple AI models in the AI ​​model resource pool are connected to realize the call of each AI model. After each AI model is called, the corresponding JSON result is obtained, and then the most credible target JSON result is calculated according to the scoring method. Among them, the application builds a proprietary knowledge base including a variety of data, which may be used when calling the model. The other is the instruction template (Prompt) built for the specified application. The corresponding instruction template is given in combination with the different functions of the platform. The target instruction corresponding to the instruction template is combined with LangChain to realize the call of the AI ​​model, and the corresponding call result is generated in combination with the AI ​​model. The result needs to be defined as a JSON structure, that is, the target JSON result.

[0152] In order to further understand the technical solution of the present disclosure, Figure 8 A detailed description may include the following steps:

[0153] Step 801: The first server responds to the application development instruction sent by the user and determines the type of the application development instruction based on the application development instruction;

[0154] Step 802: the first server obtains target data corresponding to any field in the instruction template in the development instruction, and fills the field with the target data to obtain a target field;

[0155] Step 803: The first server obtains the target instruction based on the target fields corresponding to the fields in the instruction template;

[0156] Step 804: the first server sends the target instruction to the second server;

[0157] Step 805: After receiving the target instruction sent by the first server, the second server generates multiple JSON results based on the target instruction using multiple artificial intelligence AI models;

[0158] Wherein, any JSON result among the multiple JSON results includes multiple fields and sub-results corresponding to the multiple fields;

[0159] Step 806: the second server counts, for any field, sub-results corresponding to the field in the multiple JSON results and the number of the sub-results;

[0160] Step 807: The second server obtains a target sub-result corresponding to the field based on the number of the sub-results and the preset weights of the multiple AI models;

[0161] Step 808: The second server obtains the target JSON result according to the target sub-result corresponding to each field;

[0162] Step 809: The second server sends the target JSON result to the first server;

[0163] Step 810: After receiving the target ISON result sent by the second server, the first server parses the target JSON result using a preset algorithm to obtain a target code;

[0164] Step 811: The first server generates the target application corresponding to the application development instruction according to the target code.

[0165] Based on the same disclosed concept, the zero-code application development method described above in the present disclosure can also be implemented by a zero-code application development device. The effect of the zero-code application development device is similar to that of the aforementioned method, and will not be repeated here.

[0166] Fig. 9 The present invention is a schematic diagram of the structure of a zero-code application development device according to an embodiment of the present invention.

[0167] like Fig. 9 As shown, the zero-code application development device 900 of the present disclosure may include an instruction type determination module 910, a target instruction determination module 920, a first target JSON result determination module 930, a target code generation module 940 and a target application generation module 950.

[0168] An instruction type determination module 910, configured to respond to an application development instruction sent by a user and determine the type of the application development instruction based on the application development instruction;

[0169] A target instruction determination module 920, configured to fill a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction;

[0170] A first target JSON result determination module 930 is used to send the target instruction to the second server, so that the second server uses multiple artificial intelligence AI models to obtain a target JSON result according to the target instruction;

[0171] A target code generation module 940 is configured to parse the target JSON result using a preset algorithm to obtain a target code after receiving the target ISON result sent by the second server;

[0172] The target application generating module 950 is used to generate the target application corresponding to the application development instruction according to the target code.

[0173] In one embodiment, the target instruction determination module 920 is specifically configured to:

[0174] For any field in the instruction template, obtaining target data corresponding to the field in the development instruction, and filling the field with the target data to obtain a target field;

[0175] The target instruction is obtained based on the target fields respectively corresponding to the fields in the instruction template.

[0176] In one embodiment, the instruction type determination module 910 is specifically configured to:

[0177] Obtaining a type identifier in the application development instruction;

[0178] The type of the application development instruction corresponding to the type identifier is determined by using the preset corresponding relationship between the type identifier and the type of the application development instruction.

[0179] In one embodiment, the types of application development instructions include data modeling instruction types, process design instruction types, and page building instruction types; wherein:

[0180] The data modeling instruction type is used to instruct the creation of a new entity application model with a specified business function;

[0181] The process design instruction type is used to instruct the creation of a new entity application model with multiple process nodes;

[0182] The page construction instruction type is used to instruct to rebuild a page of a specified entity application model to obtain a new entity application model.

[0183] Based on the same inventive concept, the embodiment of the present application also provides another zero-code application development device, the effect of which is similar to that of the aforementioned method, and will not be repeated here.

[0184] Fig.10 The present invention is a schematic diagram of the structure of a zero-code application development device according to an embodiment of the present invention.

[0185] like Fig.10 As shown, the zero-code application development device 1000 of the present disclosure may include a JSON result determination module 1010 , a second target JSON result determination module 1020 , and a sending module 1030 .

[0186] The JSON result determination module 1010 is used to receive a target instruction sent by the first server, and generate multiple JSON results based on the target instruction using multiple artificial intelligence AI models, wherein the target instruction is obtained by the first server filling a preset instruction template corresponding to the type of the application development instruction using the application development instruction sent by the user;

[0187] A second target JSON result determination module 1020, configured to obtain a target JSON result according to the multiple JSON results;

[0188] The sending module 1030 is used to send the target JSON result to the first server, so that the first server uses a preset algorithm to parse the JSON result to obtain a target code, and obtains a target application corresponding to the application development instruction based on the target code.

[0189] In one embodiment, any JSON result of the multiple JSON results includes multiple fields and sub-results corresponding to the multiple fields; the second target JSON result determination module 1020 is specifically used to:

[0190] For any field, counting the sub-results corresponding to the field in the multiple JSON results and the number of the sub-results; and,

[0191] Based on the number of the sub-results and the preset weights of the multiple AI models, obtaining a target sub-result corresponding to the field;

[0192] According to the target sub-results corresponding to each field, the target JSON result is obtained.

[0193] In one embodiment, the second target JSON result determination module 1020 is further configured to:

[0194] For any sub-result, if the number of the sub-results is greater than the specified number, the preset weights of the AI ​​models corresponding to the sub-results are added together to obtain the score of the sub-result; or,

[0195] If the number of the sub-results is not greater than the specified number, the preset weight of the AI ​​model corresponding to the sub-result is determined as the sub-result score;

[0196] The target sub-result is obtained according to the scores of the sub-results.

[0197] In one embodiment, the second target JSON result determination module 1020 is further configured to:

[0198] The sub-result with the highest score among the sub-results is determined as the target sub-result corresponding to the field.

[0199] After introducing a method and apparatus for developing a zero-code application according to an exemplary embodiment of the present disclosure, next, an electronic device according to another exemplary embodiment of the present disclosure is introduced. The electronic device in the embodiment of the present application is a first server and / or a second server.

[0200] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0201] In some possible implementations, the electronic device according to the present disclosure may include at least one processor and at least one computer storage medium. The computer storage medium stores program code, and when the program code is executed by the processor, the processor executes the steps in the method for developing a zero-code application according to various exemplary implementations of the present disclosure described above in this specification. For example, the processor may execute the following steps: Figure 3 Steps 301-308 shown in .

[0202] Refer to the following Fig.11 1100 according to this embodiment of the present disclosure is described. Fig.11 The electronic device 1100 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0203] like Fig.11 As shown, the electronic device 1100 is in the form of a general electronic device. The components of the electronic device 1100 may include but are not limited to: the at least one processor 1101, the at least one computer storage medium 1102, and a bus 1103 connecting different system components (including the computer storage medium 1102 and the processor 1101).

[0204] Bus 1103 represents one or more of several types of bus structures, including a computer storage media bus or computer storage media controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0205] Computer storage media 1102 may include readable media in the form of volatile computer storage media, such as random access computer storage media (RAM) 1121 and / or cache storage media 1122 , and may further include read-only computer storage media (ROM) 1123 .

[0206] The computer storage medium 1102 may also include a program / utility 1125 having a set (at least one) of program modules 1124, such program modules 1124 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0207] The electronic device 1100 may also communicate with one or more external devices 1104 (e.g., keyboards, pointing devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1100, and / or communicate with any device that enables the electronic device 1100 to communicate with one or more other electronic devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1105. Furthermore, the electronic device 1100 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 1106. As shown, the network adapter 1106 communicates with other modules for the electronic device 1100 via a bus 1103. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1100, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0208] In some possible implementations, various aspects of a method for developing a zero-code application provided by the present disclosure may also be implemented in the form of a program product, which includes a program code. When the program product is run on a computer device, the program code is used to enable the computer device to execute the steps of the method for developing a zero-code application according to various exemplary implementations of the present disclosure described above in this specification.

[0209] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access computer storage medium (RAM), a read-only computer storage medium (ROM), an erasable programmable read-only computer storage medium (EPROM or flash memory), an optical fiber, a portable compact disk read-only computer storage medium (CD-ROM), an optical computer storage medium, a magnetic computer storage medium, or any suitable combination of the above.

[0210] The program product of the zero-code application development of the embodiment of the present disclosure can adopt a portable compact disk read-only computer storage medium (CD-ROM) and include program code, and can be run on an electronic device. However, the program product of the present disclosure is not limited to this. In this document, the readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or device.

[0211] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0212] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0213] Program code for performing the disclosed operations may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user electronic device, partially on the user device, as a separate software package, partially on the user electronic device and partially on a remote electronic device, or entirely on a remote electronic device or server. In the case of a remote electronic device, the remote electronic device may be connected to the user electronic device via any type of network including a local area network (LAN) or a wide area network (WAN), or may be connected to an external electronic device (e.g., via the Internet using an Internet service provider).

[0214] It should be noted that although several modules of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into multiple modules to be embodied.

[0215] In addition, although the operations of the disclosed method are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0216] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk computer storage media, CD-ROM, optical computer storage media, etc.) containing computer-usable program codes.

[0217] The present disclosure is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0218] These computer program instructions may also be stored in a computer-readable computer storage medium that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable computer storage medium produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0219] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0220] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A zero-code application development method, It is characterized in that Applied in a first server, the method includes: In response to an application development instruction sent by a user, determining a type of the application development instruction based on the application development instruction; Filling a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction; Sending the target instruction to the second server, so that the second server uses multiple artificial intelligence AI models to obtain the target JSON result according to the target instruction; After receiving the target ISON result sent by the second server, the target JSON result is parsed using a preset algorithm to obtain a target code; The target application corresponding to the application development instruction is generated according to the target code.

2. The method according to claim 1, It is characterized in that The using the application development instruction to fill a preset instruction template corresponding to the type of the application development instruction to obtain a target instruction includes: For any field in the instruction template, obtaining target data corresponding to the field in the development instruction, and filling the field with the target data to obtain a target field; The target instruction is obtained based on the target fields respectively corresponding to the fields in the instruction template.

3. The method according to claim 1, It is characterized in that The determining, based on the application development instruction, the type of the application development instruction comprises: Obtaining a type identifier in the application development instruction; The type of the application development instruction corresponding to the type identifier is determined by using the preset corresponding relationship between the type identifier and the type of the application development instruction.

4. The method according to any one of claims 1 to 3, It is characterized in that The types of application development instructions include data modeling instruction type, process design instruction type and page building instruction type; wherein: The data modeling instruction type is used to instruct the creation of a new entity application model with a specified business function; The process design instruction type is used to instruct the creation of a new entity application model with multiple process nodes; The page construction instruction type is used to instruct to rebuild a page of a specified entity application model to obtain a new entity application model.

5. A zero-code application development method, It is characterized in that Applied in the second server, the method includes: Receiving a target instruction sent by the first server, and generating multiple JSON results based on the target instruction using multiple artificial intelligence AI models, wherein the target instruction is obtained by the first server filling a preset instruction template corresponding to the type of the application development instruction using the application development instruction sent by the user; According to the multiple JSON results, a target JSON result is obtained; The target JSON result is sent to the first server, so that the first server parses the JSON result using a preset algorithm to obtain a target code, and obtains a target application corresponding to the application development instruction based on the target code.

6. The method according to claim 5, It is characterized in that Any JSON result among the multiple JSON results includes multiple fields and sub-results corresponding to the multiple fields; The step of obtaining a target JSON result according to the multiple JSON results includes: For any field, count the sub-results corresponding to the field in the multiple JSON results and the number of the sub-results; and, Based on the number of the sub-results and the preset weights of the multiple AI models, obtaining a target sub-result corresponding to the field; According to the target sub-results corresponding to each field, the target JSON result is obtained.

7. The method according to claim 6, It is characterized in that The obtaining, based on the number of each sub-result and the preset weights of the multiple AI models, a target sub-result corresponding to the field includes: For any sub-result, if the number of the sub-results is greater than the specified number, the preset weights of the AI ​​models corresponding to the sub-results are added together to obtain the score of the sub-result; or, If the number of the sub-results is not greater than the specified number, the preset weight of the AI ​​model corresponding to the sub-result is determined as the sub-result score; The target sub-result is obtained according to the scores of the sub-results.

8. The method according to claim 7, It is characterized in that The step of obtaining the target sub-result according to the scores of each sub-result comprises: The sub-result with the highest score among the sub-results is determined as the target sub-result corresponding to the field.

9. A first server, It is characterized in that comprising a processor and a memory, wherein the processor and the memory are connected via a bus; The memory stores a computer program, and the processor is configured to perform the following operations based on the computer program: In response to an application development instruction sent by a user, determining a type of the application development instruction based on the application development instruction; Filling a preset instruction template corresponding to the type of the application development instruction with the application development instruction to obtain a target instruction; Sending the target instruction to the second server, so that the second server uses multiple artificial intelligence AI models to obtain the target JSON result according to the target instruction; After receiving the target ISON result sent by the second server, the target JSON result is parsed using a preset algorithm to obtain a target code; The target application corresponding to the application development instruction is generated according to the target code.

10. A second server, It is characterized in that comprising a processor and a memory, wherein the processor and the memory are connected via a bus; The memory stores a computer program, and the processor is configured to perform the following operations based on the computer program: Receiving a target instruction sent by the first server, and generating multiple JSON results based on the target instruction using multiple artificial intelligence AI models, wherein the target instruction is obtained by the first server filling a preset instruction template corresponding to the type of the application development instruction using the application development instruction sent by the user; According to the multiple JSON results, a target JSON result is obtained; The target JSON result is sent to the first server, so that the first server uses a preset algorithm to parse the JSON result to obtain a target code, and obtains a target application corresponding to the application development instruction based on the target code.

Images