Automatic file arrangement framework and method based on large language model and computer program product

Abstract

The invention discloses an automatic file arrangement framework and method based on a large language model and a computer program product. The framework comprises a demonstration creating module and a file processing module. The demonstration creating module is configured to acquire arrangement process information of at least one key file in the to-be-arranged files, and input the arrangement process information into the large language model, so that the large language model learns the arrangement process information; and the file processing module is configured to process the plurality of to-be-arranged files through the learned large language model to obtain a file target path of the plurality of to-be-arranged files, and arrange the to-be-arranged files to a target folder according to the file target path. According to the method, the files can be sorted in batches in a short time, different items can be flexibly adapted based on the learned large language model, the sorted files meeting the requirements can be output, the working pressure of manual sorting can be relieved, the time cost brought by manual file sorting can be reduced, and the sorting efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of large language models, and in particular to an automatic file organization framework, method and computer program product based on a large language model. Background Art

[0002] In the current production workflow, after receiving the production files from Party A, the producers need to organize them into a unified file format according to the internal file specifications. This step involves the creation, copying, pasting, and moving of a large number of files / folders, which is time-consuming and laborious to do manually. However, there is no unified input format for organizing files, and the amount of data and organization requirements vary with different projects. This cannot be solved by traditional matching algorithms, resulting in file organization being overly dependent on manpower. Summary of the invention

[0003] The purpose of this application is to provide an automatic file organization framework, method and computer program product based on a large language model to solve the technical problem that the existing production file organization relies on manual work, resulting in low efficiency. The various technical effects that can be produced by the preferred technical solution among the many technical solutions provided in this application are described in detail below.

[0004] To achieve the above objectives, this application provides the following technical solutions: In a first aspect, the present application provides an automatic file organization framework based on a large language model, comprising a demonstration creation module and a file processing module; the demonstration creation module is configured to obtain organization process information of at least one key file among multiple files to be organized, and input the organization process information into the large language model so that the large language model can learn the organization process information; the file processing module is configured to process the multiple files to be organized through the learned large language model, obtain the file target paths of the multiple files to be organized, and organize the files to be organized into a target folder according to the file target paths.

[0005] In some embodiments, the automatic file organization framework based on a large language model further includes an analysis module, and the analysis module is configured to analyze an initial folder including a plurality of files to be organized to obtain a filtered folder list.

[0006] In some embodiments, the file processing module includes a creation agent and a file operation agent; the creation agent is configured to construct multiple empty folders according to the file target path; the file operation agent is configured to copy the corresponding files to be organized in the empty folders to obtain the target folder.

[0007] In some embodiments, the file processing module also includes a filtering agent and a first checking agent; the filtering agent filters the initial folder according to the filtering folder list, and sends the filtered initial folder to the file operation agent; the first checking agent is configured to confirm the legitimacy of the multiple empty folders.

[0008] In some embodiments, the large language model-based automatic file organization framework includes a checking module, which includes a second checking agent, and the second checking agent is configured to check the target folder to confirm whether the target folder itself and the files in the target folder are complete.

[0009] In some embodiments, the inspection module includes a supplementary agent, and the supplementary agent is configured to obtain missing files to be sorted from the initial folder according to the inspection result of the second inspection agent to supplement the target folder to obtain a final target folder.

[0010] In some embodiments, the demonstration creation module converts the format of the sorting process information and inputs it into the large language model, and the creation agent converts the format of the initial folder and inputs it into the learned large language model.

[0011] In some embodiments, the demonstration creation module organizes the key files to obtain the demonstration path of the key files, and the organization process information includes the demonstration path and the initial file path of the key files in the initial folder.

[0012] In a second aspect, the present application provides an automatic file organization method based on a large language model. The automatic file organization method based on a large language model is applied to the automatic file organization framework based on a large language model as described in the first aspect. The automatic file organization method based on a large language model may include: obtaining organization process information of at least one key file among multiple files to be organized, inputting the organization process information into the large language model so that the large language model learns the organization process information; processing the multiple files to be organized through the learned large language model to obtain the file target paths of the multiple files to be organized, and organizing the files to be organized into a target folder according to the file target paths.

[0013] In a third aspect, the present application provides a computer program product, which is stored on a data carrier and is designed to execute the automatic file organization method based on a large language model as described in the second aspect.

[0014] Implementing one of the above technical solutions of the present application has the following advantages or beneficial effects: the automatic file sorting framework based on the large language model of the present application demonstrates that the creation module obtains the sorting process information of the files to be sorted, and after the large language model is learned, the file processing module cooperates with the large language model to sort the files to be sorted from the initial folder to the target folder. In this case, the present application can sort files in batches in a short time, and can flexibly adapt to different projects based on the learned large language model, and output sorted files that meet the requirements. The present application can reduce the work pressure of manual sorting, reduce the time cost of manual sorting of files, and improve sorting efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. It is obvious that the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings: Figure 1 It is a structural block diagram of an automatic file arrangement framework based on a large language model according to an embodiment of the present application; Figure 2 It is a flowchart of an automatic file organization method based on a large language model according to an embodiment of the present application; Figure 3 It is a structural block diagram of the processing device of an embodiment of the present application.

[0016] In the figure: 1. Automatic file organization framework based on large language model; 10. Analysis module; 20. Presentation creation module; 30. File processing module; 31. Creation agent; 32. Filtering agent; 33. File operation agent; 34. First inspection agent; 40. Inspection module; 41. Second inspection agent; 42. Supplementary agent; 5. Processing device; 50. Memory; 51. Processor. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solutions and advantages of the present application clearer, the various exemplary embodiments to be described below will refer to the corresponding drawings, which constitute a part of the exemplary embodiments, wherein various exemplary embodiments that may be used to implement the present application are described. Unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation methods described in the following exemplary embodiments do not represent all implementation methods consistent with the present disclosure. It should be understood that they are only examples of processes, methods, and devices that are consistent with some aspects disclosed in the present application as detailed in the attached claims, and other embodiments may also be used, or the embodiments listed herein may be modified in structure and function without departing from the scope and essence of the present application.

[0018] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", etc. indicate the orientation or positional relationship based on the drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the elements referred to must have a specific orientation, be constructed and operated in a specific orientation. The terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. The term "multiple" means two or more. The terms "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, an integral connection, a mechanical connection, an electrical connection, a communication connection, a direct connection, an indirect connection through an intermediate medium, and can be the internal connection of two elements or the interaction relationship between two elements. The term "and / or" includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0019] In order to illustrate the technical solution described in the present application, a specific embodiment is provided below, and only the parts related to the embodiment of the present application are shown.

[0020] The present application relates to an automatic file arrangement framework, which can be constructed based on a large language model and includes multiple intelligent agents that cooperate with each other. The automatic file arrangement framework of the present application can receive at least one initial folder, each of which can include multiple files to be arranged, and then the automatic file arrangement framework can arrange the files to be arranged into a target folder according to the file target path, thereby completing the automatic arrangement of the files to be arranged. Correspondingly, the initial folder can also include multiple folders to be arranged for storing the files to be arranged, and the position of the files to be arranged in the initial folder can be the initial path of the file.

[0021] The automatic file arrangement framework of the present application can be applied to scenarios where a large number of files need to be arranged according to certain rules. For example, in the field of film production, the files to be arranged in the present application can be film production files. The present application does not limit the types of files to be arranged, for example, they can be text files, video files, etc.

[0022] like Figure 1 As shown, the present application provides a production automatic file organization framework 1 based on a large language model, including: a demonstration creation module 20 and a file processing module 30.

[0023] In some embodiments, the presentation creation module 20 may be configured to obtain the organization process information of at least one key file among the multiple files to be organized, and input the organization process information into the large language model so that the large language model can learn the organization process information.

[0024] In some embodiments, the file processing module 30 can be configured to process multiple files to be sorted through the learned large language model, obtain file target paths of the multiple files to be sorted, and sort the files to be sorted into a target folder according to the file target paths.

[0025] In some embodiments, the demonstration creation module 20 may receive an initial folder, which may include multiple folders to be sorted, each folder to be sorted may include at least one file to be sorted. The demonstration creation module 20 may randomly obtain at least one file to be sorted as a key file, or may obtain all or part of the files to be sorted in at least one folder to be sorted as key files.

[0026] In some embodiments, the arrangement process information of the key files can represent the pre-arrangement process of the key files from the initial folder to the target folder, and the arrangement process information can be the path change information before and after the arrangement of the key files, that is, the file path of the key files in the initial folder and the file path of the key files in the target folder. In this case, the arrangement process information is obtained through the pre-arrangement process, and the arrangement process of other files to be arranged can be indicated through the arrangement process information.

[0027] In some embodiments, the presentation creation module 20 may receive the arrangement process information provided by the user or the user, thereby being able to make adjustments based on actual project requirements to make the file arrangement more accurate.

[0028] In some embodiments, the demonstration creation module 20 can organize the key files to obtain the demonstration path of the key files, and the organization process information can include the demonstration path and the file initial path of the key files in the initial folder. The demonstration path can refer to the file path when the key files need to be organized into the target folder, that is, the demonstration path can be considered to be the same as the file target path of the key files. The organization process information can be a file path pair including the file initial path and the demonstration path, and each key file includes at least one corresponding file path pair.

[0029] In some embodiments, the demonstration creation module 20 can convert the format of the sorting process information and input it into the large language model. Specifically, the demonstration creation module 20 can convert the sorting process information into a string form, and then input the sorting process information in the string form into the large language model. The large language model can learn the mapping relationship between the files to be sorted before and after sorting based on the sorting process information, that is, it can learn the mapping relationship between the file initial path of the files to be sorted and the file target path of the files to be sorted. In this case, the learned large language model can output the file target path based on the file initial path of other files to be sorted based on the mapping relationship, thereby improving the convenience of subsequent sorting and improving the sorting efficiency.

[0030] In some embodiments, the automatic file organization framework 1 based on a large language model may further include an analysis module 10. The analysis module 10 may be configured to analyze an initial folder including a plurality of files to be organized to obtain a filtered folder list.

[0031] In some embodiments, the filter folder list can be used to prompt the files to be sorted that need to be filtered, such as useless files, duplicate files, etc.

[0032] In some embodiments, the file processing module 30 may include a creation agent 31 and a file operation agent 33. The creation agent 31 may be configured to construct multiple empty folders according to the file target path; the file operation agent 33 may be configured to copy the corresponding files to be sorted in the empty folder to obtain the target folder. Both the creation agent 31 and the file operation agent 33 can obtain the file target path according to the learned large language model, and the large language model can output prompt words and input them to the creation agent 31 and the file operation agent 33. Specifically, when the creation agent 31 receives the corresponding prompt words, the creation agent 31 can create an empty folder according to demand, and the empty folder and the prompt words output by the large language model can be used as inputs of the file operation agent 33, and the file operation agent 33 can copy the files to be sorted into the corresponding empty folders. Thus, the automatic sorting of files can be achieved through the cooperation of the agent and the large language model.

[0033] In some embodiments, the creation agent 31 can convert the format of the initial folder and input it into the learned large language model, and the learned large language model can output the file target path. Further, the learned large language model can output prompt words, which can be input into the creation agent 31 and the file operation agent 33, so that the creation agent 31 constructs an empty folder, and the file operation agent 33 organizes the files to be organized into the empty folder to obtain the target folder.

[0034] In some embodiments, the file processing module 30 may further include a filtering agent 32 and a first checking agent 34. The filtering agent 32 may filter the initial folder according to the filtering folder list and send the filtered initial folder to the file operation agent 33; the first checking agent 34 may be configured to confirm the legitimacy of multiple empty folders. Accordingly, the learned large language model may output prompt words for the first checking agent 34 to guide the first checking agent 34 to operate.

[0035] Specifically, the filtering agent 32 can filter some of the files or folders to be sorted in the initial folder, and then the creating agent 31 can input the filtered initial folder into the large language model to obtain the file target path. Subsequently, after the creating agent 31 creates the empty folder, the first checking agent 34 can confirm the legitimacy of the empty folder. The first checking agent 34 can confirm the legitimacy of the empty folder by judging whether the file target path complies with the operating system rules, whether the file target path contains illegal characters, whether the file target path has access rights, and whether the file target path exists.

[0036] In some embodiments, the automatic file arrangement framework 1 based on the large language model may include a check module 40, and the check module 40 may include a second check agent 41. The second check agent 41 may be configured to check the target folder to confirm whether the target folder itself and the files in the target folder are complete. Specifically, the initial folder and the target folder may be used as inputs of the second check agent 41, and the second check agent 41 may be used to check whether the folders and files in the target folder are missing, and output the check result.

[0037] In some embodiments, the inspection module 40 may include a supplementary agent 42, which may be configured to obtain missing files to be sorted from the initial folder to supplement the target folder according to the inspection result of the second inspection agent 41, so as to obtain the final target folder. In this way, the integrity of the target folder can be guaranteed and the error of automatic sorting can be reduced.

[0038] The following are the test results of using the automatic file organization framework 1 based on the large language model of the embodiment of the present application to test four animation projects used in actual production (see Table 1). The data used for evaluation was checked by professional producers and supervisors: Table 1 The test results are evaluated by the following two indicators: The overall accuracy of the file can refer to whether the files in the folders of the standard answer and the framework output are correctly copied and the accuracy is calculated. The higher the indicator, the better, and the maximum is 100. The required steps can refer to how many steps are required to calculate the file in the output folder to become the standard answer, where creation, copying, pasting, and deletion are each a step. The lower the indicator, the better, and the minimum is 0.

[0039] It can be seen that the automatic file organization framework 1 based on a large language model in the embodiment of the present application exceeds that of non-field practitioners and trainee producers in terms of the overall accuracy of files and the indicators of required steps, and most of the required steps are within 10 steps, which means that the producer only needs to simply check and supplement the remaining operations to achieve file organization, thereby improving the work efficiency of the producer.

[0040] The automatic file sorting framework 1 based on the large language model of the present application, the demonstration creation module 20 obtains the sorting process information of the files to be sorted, and after the large language model is learned, the file processing module 30 cooperates with the large language model to sort the files to be sorted from the initial folder to the target folder. In this case, the present application can sort files in batches in a short time, and can flexibly adapt to different projects based on the learned large language model, and output sorted files that meet the requirements. The present application can reduce the work pressure of manual sorting, reduce the time cost of manual sorting of files, and improve sorting efficiency.

[0041] like Figure 2 As shown, the present application also relates to an automatic file organization method based on a large language model. The automatic file organization method based on a large language model is applied to the automatic file organization framework 1 based on a large language model as described above. The automatic file organization method based on a large language model may include: S1. Obtaining the sorting process information of at least one key file among the multiple files to be sorted, and inputting the sorting process information into the large language model so that the large language model can learn the sorting process information; S2. Process the multiple files to be sorted by using the learned large language model to obtain the file target paths of the multiple files to be sorted, and sort the files to be sorted into a target folder according to the file target paths.

[0042] Those skilled in the art can understand that all or part of the features / steps of the above-mentioned method embodiments can be implemented by methods, data processing systems or computer programs, and these features can be implemented without hardware, entirely by software, or by a combination of hardware and software. The aforementioned computer program can be stored in one or more computer-readable storage media, and the storage medium stores the computer program. When the computer program is executed (such as by a processor), the steps of the above-mentioned automatic file organization method embodiment based on a large language model are executed.

[0043] The aforementioned storage media that can store program codes include: static hard disks, solid-state hard disks, random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), optical storage devices, magnetic storage devices, flash memory, magnetic disks or optical disks and / or combinations of the above devices, that is, they can be implemented by any type of volatile or non-volatile storage device or a combination thereof.

[0044] like Figure 3 As shown, the present application also provides an embodiment of a processing device 5, including one or more processors 51 and a memory 50; wherein the memory 50 is used to store one or more computer programs, and the one or more processors 51 are used to execute one or more computer programs stored in the memory 50, so that the processor 51 executes the features / steps of the above-mentioned embodiment of the automatic file organization method based on a large language model.

[0045] The present application also provides a computer program product, which is stored on a data carrier and is designed to perform the automatic file arrangement method based on a large language model as described above. Therefore, the computer program product according to the present application produces the same advantages as those described in detail with reference to the device according to the present application. The computer program product can be executed as a computer-readable instruction code with each appropriate programming language such as JAVA, C++, etc. In addition, the computer program product can be provided on a network, such as the Internet, or a network, such as an Internet user, can download the computer program product from a network, such as the Internet when needed. The computer program product can be implemented by means of a computer program, i.e., software, or by means of one or more dedicated electronic circuits, i.e., hardware, or in any mixed form, i.e., by means of software components and hardware components, or in a mixed form of software, hardware, or software and hardware.

[0046] The above is only the preferred embodiment of the present application. Those skilled in the art will appreciate that various changes or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present application. In addition, under the guidance of the present application, these features and embodiments may be modified to adapt to specific circumstances and materials without departing from the spirit and scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of the present application belong to the protection scope of the present application.

Claims

1. An automatic file arrangement framework based on a large language model, characterized in that: Includes demonstration creation module and file processing module; The demonstration creation module is configured to obtain the sorting process information of at least one key file among the multiple files to be sorted, and input the sorting process information into the large language model so that the large language model can learn the sorting process information; The file processing module is configured to process the multiple files to be sorted through the learned large language model to obtain the file target paths of the multiple files to be sorted, and sort the files to be sorted into a target folder according to the file target paths.

2. The automatic file arrangement framework based on a large language model according to claim 1 is characterized in that: The automatic file arrangement framework based on a large language model further includes an analysis module, and the analysis module is configured to analyze an initial folder including a plurality of files to be arranged to obtain a filtered folder list.

3. The automatic file arrangement framework based on a large language model according to claim 2 is characterized in that: The file processing module includes a creation agent and a file operation agent; the creation agent is configured to construct multiple empty folders according to the file target path; the file operation agent is configured to copy the corresponding files to be sorted in the empty folders to obtain the target folder.

4. The automatic file arrangement framework based on a large language model according to claim 3 is characterized in that: The file processing module further comprises a filtering agent and a first checking agent; the filtering agent filters the initial folder according to the filtering folder list, and sends the filtered initial folder to the file operation agent; The first checking agent is configured to confirm the legitimacy of the multiple empty folders.

5. The automatic file arrangement framework based on a large language model according to claim 4 is characterized in that: The automatic file organization framework based on a large language model includes a checking module, and the checking module includes a second checking agent, and the second checking agent is configured to check the target folder to confirm whether the target folder itself and the files in the target folder are complete.

6. The automatic file arrangement framework based on a large language model according to claim 5 is characterized in that: The inspection module includes a supplementary agent, and the supplementary agent is configured to obtain missing files to be sorted from the initial folder according to the inspection result of the second inspection agent to supplement the target folder and obtain a final target folder.

7. The automatic file arrangement framework based on a large language model according to claim 3 is characterized in that: The demonstration creation module converts the format of the sorting process information and inputs it into the large language model, and the creation agent converts the format of the initial folder and inputs it into the learned large language model.

8. The automatic file arrangement framework based on a large language model according to claim 2, characterized in that: The demonstration creation module organizes the key files to obtain the demonstration path of the key files, and the organization process information includes the demonstration path and the initial file path of the key files in the initial folder.

9. An automatic file arrangement method based on a large language model, characterized in that: The automatic file arrangement method based on a large language model is applied to the automatic file arrangement framework based on a large language model as claimed in any one of claims 1 to 8, and the automatic file arrangement method based on a large language model comprises: Acquire arrangement process information of at least one key file among the multiple files to be arranged, and input the arrangement process information into the large language model so that the large language model can learn the arrangement process information; The plurality of files to be sorted are processed by the learned large language model to obtain file target paths of the plurality of files to be sorted, and the files to be sorted are sorted into a target folder according to the file target paths.

10. A computer program product, characterized in that The computer program product is stored on a data medium and is designed to execute the method for automatic document organization based on a large language model according to claim 9 .

Images