Text processing method, system and equipment based on large model API (Application Program Interface) and medium
Through the text processing method based on the big model API, the problem of insufficient processing capabilities for complex text in the prior art is solved, efficient text processing and multi-domain problem answers are achieved, and the scalability and flexibility of the system are improved.
Patent Information
- Application Number
- CN202411750081.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-02
- Publication Date
- 2025-03-25
AI Technical Summary
The prior art is difficult to effectively deal with complex texts, especially in language features with complex sentence structures or context-dependent, resulting in reduced accuracy of understanding and generation. Small models have insufficient breadth of knowledge, cannot effectively answer complex or multi-field questions, and there are problems with insufficient scalability.
The text processing method based on the big model API is adopted, and user requests are received through the front-end user interface, preprocessed and called the big model API for text processing. The script execution engine is used to run preset scripts, which supports a variety of text processing tasks, such as feature extraction, text summary, keyword extraction, etc.
It realizes efficient processing of complex texts, improves the accuracy of understanding and generation, supports multi-domain question answering, and has good scalability and flexibility.
Smart Images
Figure CN119692334A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of text processing technology, and in particular to a text processing method, system, device and medium based on a large model API. Background Art
[0002] At present, with more and more information of various types, it is often necessary to analyze and process some disordered problems. Ordinary systems cannot analyze and process complex texts. For complex sentence structures or context-dependent language features, the accuracy of understanding and generation is reduced; small models often lack sufficient knowledge breadth and background knowledge to answer complex or multi-domain questions, and there are problems such as limited scenarios for single business systems and lack of support for expansion. Summary of the invention
[0003] The purpose of this application is to provide a text processing method, system, device and medium based on a large model API to alleviate the above-mentioned technical problems existing in the prior art.
[0004] In a first aspect, the present invention provides a text processing method based on a big model API, the method is applied to a text processing architecture based on a big model API, the text processing architecture based on a big model API includes: a front-end user interface, a text preprocessing module, a big model API calling module and a script execution engine;
[0005] Methods include:
[0006] In response to a content processing request initiated by a user through a front-end user interface, detecting whether the content processing request is a static processing request;
[0007] If yes, the content processing request is directly responded to through the front-end Web server; if it is a non-static processing request, the content processing request is forwarded to the text input module in the application server through the front-end Web server;
[0008] After receiving the content processing request, the text input module verifies the text format and transmits the content processing request to the text preprocessing module so that the text is preprocessed by the text preprocessing module to obtain text data;
[0009] The large model API calling module calls external services or machine learning models based on the processing type and text data corresponding to the content processing request, and runs the pre-set corresponding script through the script execution engine to perform text processing on the text data to obtain the target text processing result.
[0010] In an optional implementation, after forwarding the content processing request to the text input module in the application server through the front-end Web server, the method further includes:
[0011] Publish content processing requests to the Kafka message queue;
[0012] Among them, the Kafka message queue is a middleware used to receive, store and distribute data to different processing modules.
[0013] In an optional implementation, the large model API calling module calls an external service or a machine learning model based on the processing type and text data corresponding to the content processing request, and runs a pre-set corresponding script through the script execution engine to perform text processing on the text data to obtain a target text processing result, including:
[0014] The large model API calling module calls an external service or a machine learning model based on the processing type and text data corresponding to the content processing request, wherein the processing type includes at least one or more of feature extraction, text summarization, keyword extraction, entity relationship extraction, and language identification;
[0015] Based on the processing type, the script execution engine runs a pre-set Groovy script to process the text data and obtain the target text processing result.
[0016] In an optional implementation, the text processing architecture based on the large model API further includes a result storage module; and the method further includes:
[0017] Storing the target text processing results in a result storage module;
[0018] The result storage module includes at least one or more of a MySQL database, an Oracle database or an MPP database.
[0019] In an optional implementation, the text processing architecture based on the large model API further includes a result display module; and the method further includes:
[0020] Read the target text processing result from the result storage module;
[0021] The target text processing results are displayed to the user through the front-end user interface.
[0022] In an optional embodiment, the method further comprises:
[0023] Store the preset high-frequency access data in the cache server;
[0024] The preset high-frequency access data includes user personal setting data or frequently used result data.
[0025] In an optional implementation, the text processing architecture based on the large model API further includes an additional business system, wherein the additional business system is used to perform additional business processing on the target text processing result.
[0026] In a second aspect, the present invention provides a text processing system based on a big model API, the system includes a text processing architecture based on a big model API, and the text processing architecture based on a big model API includes: a front-end user interface, a text preprocessing module, a big model API calling module and a script execution engine;
[0027] The system is used for:
[0028] In response to a content processing request initiated by a user through a front-end user interface, detecting whether the content processing request is a static processing request;
[0029] If yes, the content processing request is directly responded to through the front-end Web server; if it is a non-static processing request, the content processing request is forwarded to the text input module in the application server through the front-end Web server;
[0030] After receiving the content processing request, the text input module verifies the text format and transmits the content processing request to the text preprocessing module so that the text is preprocessed by the text preprocessing module to obtain text data;
[0031] The large model API calling module calls external services or machine learning models based on the processing type and text data corresponding to the content processing request, and runs the pre-set corresponding script through the script execution engine to perform text processing on the text data to obtain the target text processing result.
[0032] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the text processing method based on the large model API of any of the aforementioned implementations.
[0033] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the text processing method based on the large model API of any one of the aforementioned implementations.
[0034] The text processing method, system, device and medium based on the large model API provided by this application have the following beneficial effects:
[0035] By configuring a text processing architecture based on the big model API, the architecture includes a big model API call module and a script execution engine. When text processing is required, the powerful computing power of the big model can be used to quickly complete complex text processing tasks such as sentiment analysis and named entity recognition. At the same time, the big model API supports a variety of text processing tasks, such as text classification, sentiment analysis, keyword extraction, entity relationship extraction, etc., which can be flexibly selected and combined according to actual needs; through the script execution engine, custom scripts can be written to process specific text tasks, further enhancing the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0037] Figure 1 A structural diagram of a text processing architecture based on a large model API provided in an embodiment of the present application;
[0038] Figure 2 A deployment diagram provided for an embodiment of the present application;
[0039] Figure 3 A flowchart of a text processing method based on a large model API provided in an embodiment of the present application;
[0040] Figure 4 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0041] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.
[0042] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0043] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.
[0044] An embodiment of the present application provides a text processing method based on a big model API. The method is applied to a text processing architecture based on a big model API. The text processing architecture based on a big model API includes: a front-end user interface, a text preprocessing module, a big model API calling module and a script execution engine.
[0045] In one embodiment, the text processing architecture based on the large model API builds a text processing system based on the large model API through the Spring Boot framework, uses Kafka as a message queue to realize data flow, and combines Groovy scripts to process the results returned by the API. The system includes a front-end user interface, a text preprocessing module, an API call module, a script execution engine, and a result storage and display module. It supports a variety of large models (such as BERT, GPT), ensuring efficient data processing and good scalability. For a specific architectural design process diagram, see Figure 1 shown.
[0046] When deployed on a single machine, all components (front-end web server, application server, Kafka, database, and script execution environment) are installed on the same machine, which is suitable for small projects or test environments and is easy to manage and debug. When deployed in cluster mode, various components (such as load balancer, front-end web server cluster, application server cluster, Kafka cluster, database cluster, and script execution environment cluster) are distributed across multiple machines to provide high availability and scalability, which is suitable for production environments. See the deployment diagram for details. Figure 2 shown.
[0047] Applied to the above architecture, see Figure 3 As shown, the text processing method based on the large model API provided in the embodiment of the present application includes the following steps:
[0048] Step S110 , in response to a content processing request initiated by a user through a front-end user interface, detecting whether the content processing request is a static processing request.
[0049] In one implementation, a static processing request refers to a processing request for a web page or a picture, for example, security detection of a web page, information extraction of a picture, and the like.
[0050] Step S120: if yes, the front-end Web server directly responds to the content processing request; if it is a non-static processing request, the front-end Web server forwards the content processing request to the text input module in the application server.
[0051] When it is determined that the content processing request is the aforementioned static processing request, the request can be directly processed, and the method of calling the large model API is not involved in this application. If the content processing request is not the aforementioned static processing request, that is, the content processing request is a request for text processing, the content processing request is forwarded to the text input module in the application server through the front-end Web server.
[0052] Step S130, after receiving the content processing request, the text input module verifies the text format and transmits the content processing request to the text preprocessing module, so that the text preprocessing module performs preprocessing to obtain text data.
[0053] In one embodiment, the preprocessing performed by the text preprocessing module may include cleaning the text, removing irrelevant characters, tokenization, and other processing.
[0054] Step S140, the large model API calling module calls the external service or machine learning model based on the processing type and text data corresponding to the content processing request, and runs a pre-set corresponding script through the script execution engine to perform text processing on the text data to obtain the target text processing result.
[0055] In one embodiment, the processing type includes at least one or more of element extraction, text summarization, keyword extraction, entity relationship extraction, and language identification. The large model API call module calls an external service or machine learning model based on the processing type and text data corresponding to the content processing request, and runs a pre-set Groovy script through the script execution engine based on the processing type to perform text processing on the text data to obtain the target text processing result.
[0056] In one example, when a user inputs a content processing request (a text processing request in this case), the processing type for the request is carried. For example, if a user inputs multiple text reports and needs to query the text reports for specified keyword information, the processing type is keyword extraction. The large model API call module then calls external services or machine learning models related to keyword extraction to process the request, thereby improving the scalability of the system and the diverse requirements for text processing.
[0057] Furthermore, in order to ensure the feasibility of processing after multiple users initiate requests at the same time, after forwarding the content processing request to the text input module in the application server through the front-end Web server, in one embodiment, the content processing request can be published to the Kafka message queue; wherein the Kafka message queue is a middleware for receiving, storing and distributing data to different processing modules.
[0058] Furthermore, the above-mentioned text processing architecture based on the big model API also includes a result storage module; in order to facilitate the storage of the processed target text processing results and facilitate subsequent display and call, in an optional implementation, the target text processing results can be stored in the result storage module; wherein the result storage module includes at least one or more of a MySQL database, an Oracle database or an MPP database.
[0059] The above-mentioned text processing architecture based on the large model API also includes a result display module. In actual applications, the target text processing result can also be read from the result storage module; and the target text processing result can be displayed to the user through the front-end user interface.
[0060] In addition, in order to improve the response speed, in an optional implementation, preset high-frequency access data can be stored in the cache server; wherein, the preset high-frequency access data includes user personal setting data or frequently used result data, and the preset high frequency can be data that is accessed more frequently, such as once a day, multiple times a day, or once every few days.
[0061] In an optional implementation, in order to further expand the system business capabilities and enhance business processing requirements, the above-mentioned text processing architecture based on the large model API also includes an additional business system, wherein the additional business system is used to perform additional business processing on the target text processing results.
[0062] To facilitate understanding, the present application embodiment provides a more detailed system architecture description and text processing flow description below.
[0063] First of all, the system mainly consists of the following parts:
[0064] 1. User interface: Web front end, allowing users to upload files or enter text. Its main function is to provide a user-friendly web interface, support file upload and text input; support result display and download.
[0065] 2. Text input module: responsible for receiving data submitted by users and publishing it to the Kafka message queue. Its main function is to receive text data submitted by users and publish the data to the original data topic of Kafka.
[0066] 3. Kafka message queue: As a middleware, it is responsible for receiving, storing and distributing data to different processing modules. Its main function is to manage multiple topics, including raw data topics, pre-processed data topics and processing result topics; and to achieve asynchronous communication and data distribution.
[0067] 4. Text preprocessing module: preprocesses the original text, such as word segmentation, stop word removal, etc., and publishes the processed text to Kafka again. Its main functions are to subscribe to the original data topic; preprocess the text (such as word segmentation, stop word removal, etc.); publish the preprocessed text to the preprocessed data topic.
[0068] 5. API call module: subscribes to preprocessed text and calls the large model API for advanced text analysis. Its main functions are to subscribe to preprocessed data topics; call external APIs (such as BERT, GPT, etc.) for text analysis; and send the results returned by the API to the script execution engine.
[0069] 6. Script execution engine: executes Groovy scripts according to different task types and processes the results returned by the API. Its main functions are to call different Groovy scripts according to the task type; process different types of text analysis results (element extraction, text summarization, keyword extraction, entity relationship extraction, language identification, etc.); and send the processed results to the result storage module.
[0070] 7. Result storage module: stores the processed results in the database. Its main function is to store the processed results in the database (MySQL, Oracle, etc.); provide API for other modules or systems to access the stored data.
[0071] 8. Result display module: reads the processing results from the database and displays them to the user through the Web front end. Its main function is to read the processing results from the database and display them to the user through the Web front end.
[0072] 9. Other business systems: subscribe to the processing result topic, receive and use the processed data. Its main function is to subscribe to the processing result topic; use the processed data for further processing or analysis.
[0073] In a specific implementation, the technical selection of the above architecture can be adopted as follows:
[0074] 1) Backend framework: Spring Boot;
[0075] 2) Scripting language: Groovy;
[0076] 3) Message queue: Apache Kafka;
[0077] 4) Database: MySQL / Oracle / MPP;
[0078] 5) Front-end framework: React / Angular / Vue.js (in actual applications, you can also choose according to the team's familiarity);
[0079] 6) Text processing API: BERT / GPT, etc.
[0080] In practical applications, sensitive data is encrypted throughout the entire text processing process to ensure input security; a user authentication mechanism is adopted to ensure that only legitimate users can access the system; all operation logs are recorded to facilitate tracking and auditing.
[0081] The above-mentioned text processing architecture based on the big model API of this application adopts a microservice architecture, so that each module can be deployed and expanded independently; uses tools such as Jenkins and GitLab CI to achieve automated testing and deployment; integrates tools such as Prometheus and Grafana to achieve system monitoring, and sends alarm notifications via email or SMS.
[0082] In summary, by using the above-mentioned text processing architecture based on the big model API, a highly scalable and easy-to-maintain text processing platform is built, which can meet the text processing needs in various scenarios and support seamless integration with other business systems.
[0083] Based on the above method embodiment, the embodiment of the present application further provides a text processing system based on a large model API, the system includes a text processing architecture based on a large model API, and the text processing architecture based on a large model API includes: a front-end user interface, a text preprocessing module, a large model API calling module and a script execution engine; the system is used to:
[0084] In response to a content processing request initiated by a user through a front-end user interface, detecting whether the content processing request is a static processing request;
[0085] If yes, the content processing request is directly responded to through the front-end Web server; if it is a non-static processing request, the content processing request is forwarded to the text input module in the application server through the front-end Web server;
[0086] After receiving the content processing request, the text input module verifies the text format and transmits the content processing request to the text preprocessing module so that the text is preprocessed by the text preprocessing module to obtain text data;
[0087] The large model API calling module calls external services or machine learning models based on the processing type and text data corresponding to the content processing request, and runs the pre-set corresponding script through the script execution engine to perform text processing on the text data to obtain the target text processing result.
[0088] In a feasible implementation, after forwarding the content processing request to the text input module in the application server through the front-end Web server, the content processing request is published to the Kafka message queue; wherein the Kafka message queue is a middleware for receiving, storing and distributing data to different processing modules.
[0089] In a feasible implementation, the large model API calling module calls an external service or machine learning model based on the processing type and text data corresponding to the content processing request, and runs a pre-set corresponding script through the script execution engine to perform text processing on the text data to obtain a target text processing result, including: the large model API calling module calls an external service or machine learning model based on the processing type and text data corresponding to the content processing request, wherein the processing type includes at least one or more of feature extraction, text summarization, keyword extraction, entity relationship extraction, and language identification; based on the processing type, a pre-set Groovy script is run through the script execution engine to perform text processing on the text data to obtain a target text processing result.
[0090] In a feasible implementation, the text processing architecture based on the large model API also includes a result storage module; the target text processing results are stored in the result storage module; wherein the result storage module includes at least one or more of a MySQL database, an Oracle database or an MPP database.
[0091] In a feasible implementation, the text processing architecture based on the large model API also includes a result display module; reads the target text processing result from the result storage module; and displays the target text processing result to the user through the front-end user interface.
[0092] In a feasible implementation manner, preset high-frequency access data is stored in a cache server; wherein the preset high-frequency access data includes user personal setting data or frequently used result data.
[0093] In a feasible implementation, the text processing architecture based on the large model API also includes an additional business system, wherein the additional business system is used to perform additional business processing on the target text processing result.
[0094] The text processing system based on the big model API provided in the embodiment of the present application has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for parts not mentioned in the embodiment of the text processing system based on the big model API, reference may be made to the corresponding contents in the aforementioned text processing method embodiment based on the big model API.
[0095] The present application also provides an electronic device, such as Figure 4As shown, it is a schematic diagram of the structure of the electronic device, wherein the electronic device 100 includes a processor 41 and a memory 40, the memory 40 stores computer executable instructions that can be executed by the processor 41, and the processor 41 executes the computer executable instructions to implement any of the above-mentioned text processing methods based on the large model API.
[0096] exist Figure 4 In the illustrated embodiment, the electronic device further includes a bus 42 and a communication interface 43 , wherein the processor 41 , the communication interface 43 and the memory 40 are connected via the bus 42 .
[0097] Among them, the memory 40 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 42 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 42 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0098] The processor 41 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 41. The above processor 41 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor 41 reads the information in the memory and completes the steps of the text processing method based on the large model API in the aforementioned embodiment in combination with its hardware.
[0099] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above-mentioned text processing method based on the large model API. The specific implementation can be found in the aforementioned method embodiment, which will not be repeated here.
[0100] The computer program products of the text processing methods, systems, devices and media based on the big model API provided in the embodiments of the present application include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods in the previous method embodiments. For specific implementations, please refer to the method embodiments, which will not be repeated here.
[0101] Unless otherwise specifically stated, the relative steps, numerical expressions and values of the components and steps set forth in these embodiments do not limit the scope of the present application.
[0102] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.
[0103] In the description of this application, it should also be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A text processing method based on a large model API, characterized in that: The method is applied to a text processing architecture based on a large model API, and the text processing architecture based on a large model API includes: a front-end user interface, a text preprocessing module, a large model API calling module and a script execution engine; The method comprises: In response to a content processing request initiated by a user through a front-end user interface, detecting whether the content processing request is a static processing request; If yes, directly respond to the content processing request through the front-end Web server; if it is a non-static processing request, forward the content processing request to the text input module in the application server through the front-end Web server; After receiving the content processing request, the text input module verifies the text format and transmits the content processing request to the text preprocessing module, so that the text preprocessing module performs preprocessing to obtain text data; The large model API calling module calls an external service or a machine learning model based on the processing type corresponding to the content processing request and the text data, and performs text processing on the text data by running a pre-set corresponding script through the script execution engine to obtain a target text processing result.
2. The text processing method based on the large model API according to claim 1 is characterized in that: After forwarding the content processing request to the text input module in the application server through the front-end Web server, the method further includes: Publishing the content processing request to a Kafka message queue; The Kafka message queue is a middleware used to receive, store and distribute data to different processing modules.
3. The text processing method based on the large model API according to claim 1, characterized in that: The large model API calling module calls an external service or a machine learning model based on the processing type corresponding to the content processing request and the text data, and performs text processing on the text data by running a preset corresponding script through the script execution engine to obtain a target text processing result, including: The large model API calling module calls an external service or a machine learning model based on the processing type corresponding to the content processing request and the text data, wherein the processing type includes at least one or more of feature extraction, text summarization, keyword extraction, entity relationship extraction, and language identification; Based on the processing type, the script execution engine runs a preset Groovy script to perform text processing on the text data to obtain a target text processing result.
4. The text processing method based on the large model API according to claim 1 or 3, characterized in that: The text processing architecture based on the large model API also includes a result storage module; the method also includes: Storing the target text processing result in the result storage module; The result storage module includes at least one or more of a MySQL database, an Oracle database or an MPP database.
5. The text processing method based on the large model API according to claim 4 is characterized in that: The text processing architecture based on the large model API also includes a result display module; the method also includes: Read the target text processing result from the result storage module; The target text processing result is presented to the user through the front-end user interface.
6. The text processing method based on the large model API according to claim 1 is characterized in that: The method further comprises: Store the preset high-frequency access data in the cache server; The preset high-frequency access data includes user personal setting data or common result data.
7. The text processing method based on the large model API according to claim 1 is characterized in that: The text processing architecture based on the large model API also includes an additional business system, wherein the additional business system is used to perform additional business processing on the target text processing result.
8. A text processing system based on a large model API, characterized in that: The system includes a text processing architecture based on a large model API, and the text processing architecture based on a large model API includes: a front-end user interface, a text preprocessing module, a large model API calling module and a script execution engine; The system is used to: In response to a content processing request initiated by a user through a front-end user interface, detecting whether the content processing request is a static processing request; If yes, directly respond to the content processing request through the front-end Web server; if it is a non-static processing request, forward the content processing request to the text input module in the application server through the front-end Web server; After receiving the content processing request, the text input module verifies the text format and transmits the content processing request to the text preprocessing module, so that the text preprocessing module performs preprocessing to obtain text data; The large model API calling module calls an external service or a machine learning model based on the processing type corresponding to the content processing request and the text data, and performs text processing on the text data by running a pre-set corresponding script through the script execution engine to obtain a target text processing result.
9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the text processing method based on the large model API as described in any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the text processing method based on the large model API as described in any one of claims 1 to 7.