Data architecture generation method and device, computer equipment and storage medium

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to a data architecture generation method and device, computer equipment and a storage medium, and the method comprises the steps: reading a system database, and obtaining historical architecture data from the system database; calling an initial NLP model, and inputting the historical architecture data into the NLP model for model training processing to obtain a target NLP model; receiving service demand information sent by the user terminal; inputting the service demand information into the target NLP model to perform a data architecture generation operation to obtain initial architecture data; sending the initial architecture data to the user terminal, and receiving feedback data sent by the user terminal; performing optimization adjustment on the initial architecture data according to the feedback data to obtain target architecture data; and generating a target data model corresponding to the target architecture data according to an automatic tool. According to the invention, the efficiency of database establishment and data management can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data architecture generation method, apparatus, computer equipment and storage medium. Background Art

[0002] A common problem with existing automated database model generators such as Drem io and FastAP I-MySQL-Generator is that they require a lot of upfront investment to configure the system, as well as ongoing maintenance to adapt to changing business needs. In addition, automated tools may be limited in handling very complex or non-standardized tasks, requiring manual intervention to ensure that the generated architecture and code meet specific business rules and compliance requirements. Because they achieve automation at the bottom layer of system construction, but the system built on this technology is general and has no support for specific business. Developers need to analyze and disassemble business requirements to complete data structure design and manually develop, etc., in order to finally implement specific business logic.

[0003] It can be seen that the existing automatic database model generation method has the problem of low efficiency in database construction and data management. Summary of the invention

[0004] The purpose of the embodiments of the present application is to propose a data architecture generation method, apparatus, computer equipment and storage medium to solve the problem of low efficiency in database construction and data management in existing automated database model generation methods.

[0005] In order to solve the above technical problems, the present application embodiment provides a data architecture generation method, which adopts the following technical solution:

[0006] Reading a system database, and obtaining historical architecture data in the system database;

[0007] Calling an initial NLP model, and inputting the historical architecture data into the NLP model for model training processing to obtain a target NLP model;

[0008] Receiving business demand information sent by a user terminal;

[0009] Inputting the business requirement information into the target NLP model to perform a data architecture generation operation to obtain initial architecture data;

[0010] Sending the initial architecture data to the user terminal, and receiving feedback data sent by the user terminal;

[0011] Optimizing and adjusting the initial architecture data according to the feedback data to obtain target architecture data;

[0012] A target data model corresponding to the target architecture data is generated according to an automated tool.

[0013] Furthermore, after the step of reading the system database and obtaining the historical architecture data in the system database, and before the step of calling the initial NLP model and inputting the historical architecture data into the NLP model for model training processing to obtain the target NLP model, the following steps are also included:

[0014] Perform data completion processing on the historical architecture data.

[0015] Furthermore, the step of generating a target data model corresponding to the target architecture data according to an automated tool specifically comprises the following steps:

[0016] Generate an accurate target data model based on the encoding and decoding mechanism of the Transformer model.

[0017] Furthermore, the step of optimizing and adjusting the initial architecture data according to the feedback data to obtain the target architecture data specifically includes the following steps:

[0018] Obtain text information based on user feedback content, process the text through the NLP sentiment analysis model, and obtain the sentiment tendency of user feedback;

[0019] Classify the emotional tendency according to the emotional analysis algorithm to obtain emotional category data;

[0020] Performing intensity analysis on the emotional tendency to obtain an emotional intensity value;

[0021] confirming the overall satisfaction of the feedback data according to the emotional tendency, the emotional category data and the emotional intensity value;

[0022] Identify the key factors that affect the overall satisfaction based on product features, service links and user attributes;

[0023] The initial architecture data is optimized and adjusted according to the key factors to obtain the target architecture data.

[0024] Furthermore, after the step of generating a target data model corresponding to the target architecture data according to an automated tool, the following steps are also included:

[0025] Performing a compliance check operation on the target data model to obtain a compliance check result;

[0026] If the compliance test result is normal, a data compliance signal is output;

[0027] If the compliance detection result is abnormal, a data non-compliance signal is output.

[0028] In order to solve the above technical problems, the embodiment of the present application further provides a data architecture generation device, which adopts the following technical solution:

[0029] A historical data acquisition module, used for reading a system database and acquiring historical architecture data in the system database;

[0030] A model training module, used to call the initial NLP model and input the historical architecture data into the NLP model for model training processing to obtain a target NLP model;

[0031] A demand acquisition module is used to receive business demand information sent by a user terminal;

[0032] An architecture generation module, used to input the business requirement information into the target NLP model to perform a data architecture generation operation to obtain initial architecture data;

[0033] A feedback acquisition module, used to send the initial architecture data to the user terminal and receive feedback data sent by the user terminal;

[0034] An optimization and adjustment module, used to optimize and adjust the initial architecture data according to the feedback data to obtain target architecture data;

[0035] A model generation module is used to generate a target data model corresponding to the target architecture data according to an automated tool.

[0036] Furthermore, the device also includes:

[0037] The data completion module is used to complete the historical architecture data.

[0038] Furthermore, the model generation module includes:

[0039] The model generation submodule is used to generate an accurate target data model based on the encoding and decoding mechanism of the Transformer model.

[0040] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0041] It includes a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the data architecture generation method as described above when executing the computer-readable instructions.

[0042] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0043] The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the data architecture generation method described above are implemented.

[0044] The present application provides a data architecture generation method, including: reading a system database, obtaining historical architecture data in the system database; calling an initial NLP model, and inputting the historical architecture data into the NLP model for model training processing to obtain a target NLP model; receiving business demand information sent by a user terminal; inputting the business demand information into the target NLP model for data architecture generation operation to obtain initial architecture data; sending the initial architecture data to the user terminal, and receiving feedback data sent by the user terminal; optimizing and adjusting the initial architecture data according to the feedback data to obtain target architecture data; generating a target data model corresponding to the target architecture data according to an automated tool. Compared with the prior art, the present application can not only improve the efficiency of data processing, but also enhance the reliability and adaptability of data architecture through functions such as predictive analysis, intelligent optimization and automated compliance checking. In addition, the present application can effectively improve the efficiency of database construction and data management, and the intelligent solution provides more consistent and reliable design results, reducing the occurrence of human errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0047] Figure 2 This is a flowchart of the implementation of the data architecture generation method provided in Example 1 of the present application;

[0048] Figure 3 It is a structural diagram of a data architecture generating device provided in Embodiment 2 of the present application;

[0049] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0051] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0052] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0053] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0054] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0055] The terminal devices 101, 102, and 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0056] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0057] It should be noted that the data architecture generation method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the data architecture generation device is generally set in the server / terminal device.

[0058] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0059] Embodiment 1

[0060] Continue to refer Figure 2 , shows a flow chart of an embodiment of a data architecture generation method according to the present application. The data architecture generation method comprises: step S201, step S202, step S203, step S204, step S205, step S206 and step S207.

[0061] In step S201 , the system database is read to obtain historical architecture data from the system database.

[0062] In the embodiment of the present application, the historical architecture data is first obtained by using SQL query. Assuming that the data table name is `histor i ca l_arch i tectu res`, the query statement `SELECT FROM historical_arch i tectures` can be used to extract the data set.

[0063] In step S202, the initial NLP model is called, and the historical architecture data is input into the NLP model for model training processing to obtain a target NLP model.

[0064] In the embodiment of the present application, assuming that the model is BERT, the parameters can be adjusted by setting the learning rate to 00002 and the training rounds to 5 to ensure the convergence and accuracy of the model.

[0065] In step S203, service requirement information sent by the user terminal is received.

[0066] In an embodiment of the present application, when the user terminal sends business demand information, its format can be verified. As an example, assuming that the information is required to be in JSON format, if the format does not match, it needs to be adjusted through the format conversion module; if data in XML format is received, Python's `xmltod i ct` library can be used to convert it into JSON format to ensure that the input meets the requirements of the NLP model.

[0067] In step S204, the business requirement information is input into the target NLP model to perform a data architecture generation operation to obtain initial architecture data.

[0068] In an embodiment of the present application, after the format meets the requirements, the business demand information is input into the target NLP model for data architecture generation operation. It is assumed that this operation can be implemented through the encoding and decoding mechanism of the Transformer model, and the generated structured data is stored in the `initial_struct_data` variable.

[0069] In step S205, the initial architecture data is sent to the user terminal, and feedback data sent by the user terminal is received.

[0070] In an embodiment of the present application, the generated initial architecture data is sent to the user terminal through a data interface. If data loss or damage occurs during the transmission process, CRC32 checksum and technology can be used to perform data integrity check and repair.

[0071] In the embodiment of the present application, assuming that the original data length is 1024 bytes, a 4-byte CRC check code can be added for integrity verification.

[0072] In an embodiment of the present application, after the complete initial architecture data reaches the user terminal, user feedback data is collected, and the NLP sentiment analysis model can be used to determine whether the feedback content contains optimization suggestions.

[0073] In step S206, the initial architecture data is optimized and adjusted according to the feedback data to obtain the target architecture data.

[0074] In an embodiment of the present application, if the feedback data indicates that the user satisfaction is low (less than 5), the initial architecture data needs to be optimized and adjusted, such as adjusting the data structure or optimizing the query performance, to improve user satisfaction.

[0075] In step S207, a target data model corresponding to the target architecture data is generated according to an automated tool.

[0076] In an embodiment of the present application, an automated tool such as DB Designer is used to perform a data model generation operation based on the optimized target architecture data.

[0077] In an embodiment of the present application, if an exception occurs during the generation process, such as a database connection timeout or insufficient permissions, a retry mechanism can be set to retry up to three times to ensure that the generation process is completed smoothly.

[0078] In an embodiment of the present application, the generated target data model needs to be verified. Assuming that the verification criteria are field integrity and data consistency, a non-null check and primary key constraint verification are performed on each field. If the verification result meets expectations, it is regarded as the final data model; otherwise, the data model needs to be corrected, such as adjusting the field type or modifying the constraint conditions.

[0079] In an embodiment of the present application, a data architecture generation method is provided, including: reading a system database, obtaining historical architecture data in the system database; calling an initial NLP model, and inputting the historical architecture data into the NLP model for model training processing to obtain a target NLP model; receiving business demand information sent by a user terminal; inputting the business demand information into the target NLP model for data architecture generation operation to obtain initial architecture data; sending the initial architecture data to the user terminal, and receiving feedback data sent by the user terminal; optimizing and adjusting the initial architecture data according to the feedback data to obtain target architecture data; generating a target data model corresponding to the target architecture data according to an automated tool. Compared with the prior art, the present application can not only improve the efficiency of data processing, but also enhance the reliability and adaptability of the data architecture through functions such as predictive analysis, intelligent optimization and automated compliance checking. In addition, the present application can effectively improve the efficiency of database construction and data management, and the intelligent solution provides more consistent and reliable design results, reducing the occurrence of human errors.

[0080] Continue reading Figure 3 , showing Figure 2 A flowchart of a specific implementation of step S** in FIG. 1 , for ease of explanation, only the part related to the present application is shown.

[0081] In some optional implementations of the embodiments of the present application, after step S201 and before step S202, the following steps are further included:

[0082] Perform data completion processing on historical architecture data.

[0083] In an embodiment of the present application, if the query result shows that there are null values ​​in the data field, for example, the missing rate of certain key fields exceeds 10%, the KNearest Ne i ghbors (KNN) algorithm is required to complete the data. Specifically, records with complete fields are selected, and the distance to the missing records is calculated by KNN. k=3 is used, that is, the three records with the closest distance are selected to calculate the average for completion.

[0084] In an embodiment of the present application, by completing the historical architecture data, the learning efficiency of the NLP model can be effectively improved, and the accuracy of the data architecture generated by the subsequent NLP model can be improved.

[0085] In some optional implementations of the embodiments of the present application, the step of generating a target data model corresponding to the target architecture data according to an automated tool specifically includes the following steps:

[0086] Generate an accurate target data model based on the encoding and decoding mechanism of the Transformer model.

[0087] In an embodiment of the present application, when analyzing the business demand information sent by the user terminal, it is necessary to clarify the various functional modules and key data processing requirements of the system. For each module, it is necessary to understand its data scale and performance requirements. For example, the product management module may need to process tens of thousands of new product data every day and ensure fast query and retrieval. The type and characteristics of the data source are crucial to system design.

[0088] In the embodiment of the present application, a strategy combining batch processing and stream processing may be used to ensure that the system can acquire and process new data in real time.

[0089] In an embodiment of the present application, after extracting functional requirements and data characteristics, it is necessary to identify the core data entities in the system, such as users, products, orders, and inventory, etc. For these entities, their attributes and relationships can be defined according to business scenarios.

[0090] In the embodiment of the present application, through the above method, a clear data structure diagram can be established to help understand the relationship between the entities in the system.

[0091] In the embodiment of the present application, in order to convert the information of these data entities into a vector representation that can be processed by the Transformer model, a word embedding technology can be used. For each attribute, such as user ID or order amount, an encoder is used to map it into a fixed-length numerical vector.

[0092] In the embodiment of the present application, this method is used to generate the input format of the model so that the Transformer model can be processed and analyzed.

[0093] In the embodiment of the present application, based on the vector generated by the encoder, an autoregressive generation method is adopted to gradually design a data architecture that meets business requirements.

[0094] In an embodiment of the present application, in order to ensure that the generated data architecture meets business requirements, evaluation indicators such as coverage, consistency and scalability can be introduced. Through these indicators, the rationality of the current data architecture can be judged and necessary optimization can be performed.

[0095] During the optimization process of the embodiments of the present application, the model is continuously fine-tuned in combination with feedback from actual applications and changes in business needs, and a continuous iterative optimization process is adopted to ensure that the system always remains efficient and adaptable.

[0096] In the embodiment of the present application, new business requirements are tested and analyzed, deficiencies in the architecture are identified, and new optimization goals are set to ensure that the system can respond to business changes in a timely manner.

[0097] In the embodiments of the present application, the data architecture design and optimization of the system can be gradually realized under the information-based operation process.

[0098] In some optional implementations of the embodiments of the present application, the above step S206 specifically includes the following steps:

[0099] Obtain text information based on user feedback content, process the text through the NLP sentiment analysis model, and obtain the sentiment tendency of user feedback;

[0100] Classify the emotional tendencies according to the emotional analysis algorithm to obtain emotional category data;

[0101] Perform intensity analysis on the emotional tendency to obtain the emotional intensity value;

[0102] Confirm the overall satisfaction of the feedback data based on sentiment tendency, sentiment category data, and sentiment intensity value;

[0103] Identify key factors that affect overall satisfaction based on product features, service links, and user attributes;

[0104] The initial architecture data is optimized and adjusted according to key factors to obtain the target architecture data.

[0105] In an embodiment of the present application, in the user feedback sentiment analysis, the text can first be processed by a deep learning sentiment analysis model, such as BERT (Bidirectional Encoder Representations from Transformers). The model will perform semantic understanding on the input user feedback text, and then determine whether the sentiment tendency of the text is positive, neutral or negative based on a pre-trained sentiment classifier.

[0106] In an embodiment of the present application, keywords such as "shopping experience" and "customer service attitude" are extracted from the feedback text through a keyword extraction algorithm in natural language processing technology, such as TextRank or TF IDF. These keywords can help analyze the specific performance of product features and service links.

[0107] In the embodiment of the present application, assuming that by analyzing a large amount of feedback, it is found that "customer service attitude" appears frequently and is associated with positive emotions, it can be inferred that customer service performance is a key influencing factor of user satisfaction.

[0108] In an embodiment of the present application, the present application can comprehensively obtain the overall satisfaction level of user feedback.

[0109] In the embodiment of the present application, after obtaining the overall satisfaction level of user feedback and combining multi-dimensional factors such as product characteristics, service links and user attributes, the key factors affecting user satisfaction, such as "customer service attitude" and "shopping experience", can be identified, providing clear data support for business optimization.

[0110] In some optional implementations of the embodiments of the present application, the above step S** specifically includes the following steps:

[0111] In some optional implementations of the embodiments of the present application, after step S207, the following steps are further included:

[0112] Perform compliance testing on the target data model to obtain compliance testing results;

[0113] If the compliance test result is normal, a data compliance signal is output;

[0114] If the compliance test result is abnormal, a data non-compliance signal is output.

[0115] In the embodiment of the present application, when performing compliance detection of the target data model, it is first necessary to identify the name or identifier of the target data model. After obtaining the data model, the system automatically records the current time. Next, based on this timestamp, the system extracts a set of applicable detection rules from the preset compliance standard library. These rules may include data type verification, field length restriction, null value check, etc. Then, the target data model is fully scanned according to these rules to simulate a scenario of a detection result. It is assumed that the age field of 3 records in 10 records does not comply with the age restriction rule. At this time, these non-compliant data items will be marked and a list of non-compliant items will be generated. For this list, each non-compliant item will be analyzed, that is, the age field of the record does not comply with the regulations, and a non-compliant description will be obtained. According to the non-compliant description, the system will derive an optimization strategy. For example, for age non-compliant items, the system recommends data verification or cleaning for ages that are out of range, and provides an adjustment suggestion, which may be to set a default value or delete records that are out of range. Finally, the system forms a rectification measure plan based on these adjustment suggestions, and estimates the effect of these measures on the compliance of the target data model.

[0116] In an embodiment of the present application, the present application can integrate compliance rules to automatically check whether the data architecture design complies with legal and regulatory requirements, information security requirements, etc., without the need for human intervention, thereby ensuring the efficiency and accuracy of the detection process.

[0117] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0118] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0119] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0120] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0121] Embodiment 2

[0122] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a data architecture generation device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0123] like Figure 3 As shown, the data architecture generating device 200 of the embodiment of the present application includes:

[0124] The historical data acquisition module 210 is used to read the system database and acquire the historical architecture data in the system database;

[0125] The model training module 220 is used to call the initial NLP model and input the historical architecture data into the NLP model for model training processing to obtain a target NLP model;

[0126] The demand acquisition module 230 is used to receive the service demand information sent by the user terminal;

[0127] The architecture generation module 240 is used to input the business requirement information into the target NLP model to perform a data architecture generation operation to obtain initial architecture data;

[0128] The feedback acquisition module 250 is used to send the initial architecture data to the user terminal and receive feedback data sent by the user terminal;

[0129] The optimization and adjustment module 260 is used to optimize and adjust the initial architecture data according to the feedback data to obtain the target architecture data;

[0130] The model generation module 270 is used to generate a target data model corresponding to the target architecture data according to an automated tool.

[0131] In an embodiment of the present application, a data architecture generation device 200 is provided, including: a historical data acquisition module 210, which is used to read a system database and obtain historical architecture data in the system database; a model training module 220, which is used to call an initial NLP model and input the historical architecture data into the NLP model for model training processing to obtain a target NLP model; a demand acquisition module 230, which is used to receive business demand information sent by a user terminal; an architecture generation module 240, which is used to input the business demand information into the target NLP model for data architecture generation operation to obtain initial architecture data; a feedback acquisition module 250, which is used to send the initial architecture data to the user terminal and receive feedback data sent by the user terminal; an optimization and adjustment module 260, which is used to optimize and adjust the initial architecture data according to the feedback data to obtain the target architecture data; a model generation module 270, which is used to generate a target data model corresponding to the target architecture data according to an automation tool. Compared with the existing technology, this application can not only improve the efficiency of data processing, but also enhance the reliability and adaptability of data architecture through functions such as predictive analysis, intelligent optimization and automated compliance checking. In addition, this application can effectively improve the efficiency of database construction and data management. Intelligent solutions can provide more consistent and reliable design results and reduce the occurrence of human errors.

[0132] In some optional implementations of the embodiments of the present application, the data architecture generating device 200 further includes:

[0133] The data completion module is used to complete the historical architecture data.

[0134] In some optional implementations of the embodiments of the present application, the above-mentioned model generation module includes:

[0135] The model generation submodule is used to generate an accurate target data model based on the encoding and decoding mechanism of the Transformer model.

[0136] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of a computer device according to an embodiment of the present application.

[0137] The computer device 300 includes a memory 310, a processor 320, and a network interface 330 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 300 having components 310-330, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0138] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0139] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 310 can be an internal storage unit of the computer device 300, such as a hard disk or memory of the computer device 300. In other embodiments, the memory 310 can also be an external storage device of the computer device 300, such as a plug-in hard disk equipped on the computer device 300, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 310 can also include both the internal storage unit of the computer device 300 and its external storage device. In the embodiment of the present application, the memory 310 is generally used to store the operating system and various application software installed on the computer device 300, such as computer-readable instructions of the data architecture generation method. In addition, the memory 310 can also be used to temporarily store various data that have been output or are to be output.

[0140] The processor 320 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip in some embodiments. The processor 320 is generally used to control the overall operation of the computer device 300. In the embodiment of the present application, the processor 320 is used to run the computer-readable instructions stored in the memory 310 or process data, such as computer-readable instructions for running the data architecture generation method.

[0141] The network interface 330 may include a wireless network interface or a wired network interface. The network interface 330 is generally used to establish a communication connection between the computer device 300 and other electronic devices.

[0142] The computer equipment provided by this application can not only improve the efficiency of data processing, but also enhance the reliability and adaptability of the data architecture through functions such as predictive analysis, intelligent optimization and automated compliance checking. In addition, this application can effectively improve the efficiency of database construction and data management. Intelligent solutions can provide more consistent and reliable design results and reduce the occurrence of human errors.

[0143] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the data architecture generation method as described above.

[0144] The computer-readable storage medium provided by this application can not only improve the efficiency of data processing, but also enhance the reliability and adaptability of the data architecture through functions such as predictive analysis, intelligent optimization, and automated compliance checking. In addition, this application can effectively improve the efficiency of database construction and data management, and intelligent solutions can provide more consistent and reliable design results, reducing the occurrence of human errors.

[0145] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0146] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A data architecture generation method, characterized in that: The steps include: Reading a system database, and obtaining historical architecture data in the system database; Calling an initial NLP model, and inputting the historical architecture data into the NLP model for model training processing to obtain a target NLP model; Receiving business demand information sent by a user terminal; Inputting the business requirement information into the target NLP model to perform a data architecture generation operation to obtain initial architecture data; Sending the initial architecture data to the user terminal, and receiving feedback data sent by the user terminal; Optimizing and adjusting the initial architecture data according to the feedback data to obtain target architecture data; A target data model corresponding to the target architecture data is generated according to an automated tool.

2. The data architecture generation method according to claim 1, characterized in that: After the step of reading the system database and obtaining the historical architecture data in the system database, and before the step of calling the initial NLP model and inputting the historical architecture data into the NLP model for model training processing to obtain the target NLP model, the following steps are also included: Perform data completion processing on the historical architecture data.

3. The data architecture generation method according to claim 1, characterized in that: The step of generating a target data model corresponding to the target architecture data according to an automated tool specifically comprises the following steps: Generate an accurate target data model based on the encoding and decoding mechanism of the Transformer model.

4. The data architecture generation method according to claim 1, characterized in that: The step of optimizing and adjusting the initial architecture data according to the feedback data to obtain the target architecture data specifically includes the following steps: Obtain text information based on user feedback content, process the text through the NLP sentiment analysis model, and obtain the sentiment tendency of user feedback; Classify the emotional tendency according to the emotional analysis algorithm to obtain emotional category data; Performing intensity analysis on the emotional tendency to obtain an emotional intensity value; confirming the overall satisfaction of the feedback data according to the emotional tendency, the emotional category data and the emotional intensity value; Identify the key factors that affect the overall satisfaction based on product features, service links and user attributes; The initial architecture data is optimized and adjusted according to the key factors to obtain the target architecture data.

5. The data architecture generation method according to claim 1, characterized in that: After the step of generating a target data model corresponding to the target architecture data according to an automated tool, the following steps are also included: Performing a compliance check operation on the target data model to obtain a compliance check result; If the compliance test result is normal, a data compliance signal is output; If the compliance detection result is abnormal, a data non-compliance signal is output.

6. A data architecture generating device, characterized in that: include: A historical data acquisition module, used for reading a system database and acquiring historical architecture data in the system database; A model training module, used to call an initial NLP model and input the historical architecture data into the NLP model for model training processing to obtain a target NLP model; A demand acquisition module is used to receive business demand information sent by a user terminal; An architecture generation module, used to input the business requirement information into the target NLP model to perform a data architecture generation operation to obtain initial architecture data; A feedback acquisition module, used to send the initial architecture data to the user terminal and receive feedback data sent by the user terminal; An optimization and adjustment module, used to optimize and adjust the initial architecture data according to the feedback data to obtain target architecture data; A model generation module is used to generate a target data model corresponding to the target architecture data according to an automated tool.

7. The data architecture generating device according to claim 6, characterized in that: The device also includes: The data completion module is used to complete the historical architecture data.

8. The data architecture generating device according to claim 6, characterized in that: The model generation module includes: The model generation submodule is used to generate an accurate target data model based on the encoding and decoding mechanism of the Transformer model.

9. A computer device comprising a memory and a processor, characterized in that: The memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the data architecture generation method as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the data architecture generation method as described in any one of claims 1 to 5.

Images