CN115858474A - AIGC-based file arrangement system - Google Patents

Abstract

The invention provides an AIGC-based file arrangement system which is characterized by comprising a storage module, an analysis module, a classification module, an application module and an output module, wherein the storage module is used for storing files of users, the analysis module analyzes the files based on AIGC technology, the classification module classifies the files by utilizing information generated by the analysis module, the application module provides application functions for the users, and the output module is used for generating reports for decision making; the system analyzes and formulates classification rules through files for training, and rapidly classifies new files based on the formulated classification rules, so that the effect of rapidly arranging a large number of files can be achieved.

Description

A file arrangement system based on AIGC

Technical Field

The present invention relates to the field of file system structure, and in particular to a file arrangement system based on AIGC.

Background Art

In daily work and life, a large number of text files are generated. In order to improve work efficiency, text files need to be sorted and classified. In traditional file sorting systems, users need to manually label, sort and classify each file, which is a large workload and prone to errors. Now we need an intelligent file sorting system to assist in sorting files, reduce the time spent on sorting files, and improve the effective utilization of working time.

The foregoing discussion of the background art is intended only to facilitate an understanding of the present invention. This discussion does not acknowledge or admit that any of the material referred to is part of the common general knowledge.

Many file sorting systems have been developed. After extensive searching and reference, we found that the existing sorting systems include the system disclosed in the publication number CN110245119B. These systems generally include: a storage system obtains first information of a first file, wherein the first file is stored in a storage medium in the form of data slices, the first information includes N data slices of the first file and the number of unit storage areas occupied by each data slice in the storage medium, two of the N data slices occupy discontinuous unit storage areas, and N is an integer greater than or equal to 2; the storage system determines a first parameter of the first file based on the first information, wherein the first parameter is used to characterize the degree of aggregation of the location where the first file is stored in the storage medium. However, the system only sorts out the storage aspect, and cannot automatically classify and process a large number of files, and cannot improve work efficiency.

Summary of the invention

The purpose of the present invention is to propose a file arrangement system based on AIGC in view of the existing deficiencies.

The present invention adopts the following technical solution:

A file arrangement system based on AIGC, comprising a storage module, an analysis module, a classification module, an application module and an output module;

The storage module is responsible for storing the user's files, the analysis module analyzes the files based on the AIGC technology, the classification module classifies the files using the information generated by the analysis module, the application module provides application functions for the user, and the output module is responsible for generating reports for decision-making;

The analysis module receives training files, converts the files into feature information, creates a hyperplane based on the feature information, and sends the hyperplane information to the classification module. The classification module calculates and processes the files to be classified based on the hyperplane to obtain a classification code, each bit of the classification code corresponds to a hyperplane, and the classification module saves the files to be classified to the corresponding area of the storage module according to the classification code;

Further, the analysis module includes a vocabulary statistics unit, a word frequency matrix processing unit, a feature processing unit and a classification analysis unit, the vocabulary statistics unit creates a vocabulary table according to the input text file and performs vocabulary statistics on each text file based on the vocabulary table, the word frequency matrix processing unit generates an m*n matrix according to the statistical results, wherein m represents the number of files and n represents the number of words in the vocabulary table, the feature processing unit obtains the n-dimensional feature number of each file according to the word frequency matrix processing, and the classification analysis unit creates a hyperplane based on the feature number and the classification code of the text file;

Furthermore, the feature processing unit performs calculation processing based on the element values in the matrix according to the following formula:

；

;

表示矩阵中第x行、第y列的元素值，i表示行数的变量，j表示列数的变量；in,

Represents the element value of the x-th row and y-th column in the matrix, i represents the variable of the number of rows, and j represents the variable of the number of columns;

构成第x个文件的特征数；Depend on

The number of features that make up the xth file;

The hyperplane A set by the classification analysis unit is:

；

;

为超平面系数，

为超平面元素，b为阈值；in,

is the hyperplane coefficient,

is the hyperplane element, b is the threshold;

The hyperplane A satisfies:

；

;

表示一类特征数对应的文件序号，

表示二类特征数对应的文件序号；in,

Indicates the file number corresponding to a type of feature number,

Indicates the file number corresponding to the second type of feature number;

Furthermore, the classification module includes a text processing unit, a calculation processing unit and an execution unit, wherein the text processing unit is used to count the occurrence frequency of specific words in the text file, the calculation processing unit is used to perform calculation tasks, and the execution unit classifies the text according to the calculation results of the calculation processing unit and saves it to the corresponding storage area;

：Furthermore, the calculation processing unit includes a feature number calculation processor and a hyperplane calculation processor, and the feature number calculation processor calculates the classification feature number of the file to be classified according to the following formula:

:

；

;

为所述文本处理单元统计得到的第y个词汇频次；in,

The frequency of the yth word obtained by counting the text processing unit;

The hyperplane calculation processor processes the classification feature number according to the hyperplane, and the calculation result of each hyperplane is:

；

;

的正负性确定分类码上对应位数上的值，并得到分类码，所述执行单元根据分类码将文本文件保存至对应的分类区域。The execution unit is based on

The positive or negative value of determines the value of the corresponding bit in the classification code, and obtains the classification code. The execution unit saves the text file to the corresponding classification area according to the classification code.

The beneficial effects achieved by the present invention are:

This system analyzes the vocabulary, grammar and semantic information in the text, identifies the subject, sentiment and keywords of the document, calculates the importance of each word, converts the document into the feature number of an n-dimensional vector, and creates a hyperplane based on the feature number. The number of hyperplanes determines the upper limit of the number of categories that can be classified. This system can use hyperplanes to automatically label and classify files, greatly improving efficiency and accuracy.

To further understand the features and technical contents of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are only for reference and description and are not intended to limit the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of the overall structural framework of the present invention;

FIG2 is a schematic diagram of the analysis module of the present invention;

FIG3 is a schematic diagram of the classification module of the present invention;

FIG4 is a schematic diagram of the structure of a computing processing unit of the present invention;

FIG. 5 is a schematic diagram of the process of setting a hyperplane according to the present invention.

DETAILED DESCRIPTION

The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual sizes. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

Embodiment 1:

This embodiment provides a file arrangement system based on AIGC, which includes a storage module, an analysis module, a classification module, an application module and an output module in conjunction with FIG1 ;

The storage module is responsible for storing the user's files, the analysis module analyzes the files based on the AIGC technology, the classification module classifies the files using the information generated by the analysis module, the application module provides application functions for the user, and the output module is responsible for generating reports for decision-making;

The analysis module receives training files, converts the files into feature information, creates a hyperplane based on the feature information, and sends the hyperplane information to the classification module. The classification module calculates and processes the files to be classified based on the hyperplane to obtain a classification code, each bit of the classification code corresponds to a hyperplane, and the classification module saves the files to be classified to the corresponding area of the storage module according to the classification code;

The analysis module includes a vocabulary statistics unit, a word frequency matrix processing unit, a feature processing unit and a classification analysis unit. The vocabulary statistics unit creates a vocabulary table according to the input text file and performs vocabulary statistics on each text file based on the vocabulary table. The word frequency matrix processing unit generates an m*n matrix according to the statistical results, wherein m represents the number of files and n represents the number of words in the vocabulary table. The feature processing unit obtains the n-dimensional feature number of each file according to the word frequency matrix processing. The classification analysis unit creates a hyperplane based on the feature number and the classification code of the text file.

The feature processing unit performs calculation processing based on the element values in the matrix according to the following formula:

；

;

表示矩阵中第x行、第y列的元素值，i表示行数的变量，j表示列数的变量；in,

Represents the element value of the x-th row and y-th column in the matrix, i represents the variable of the number of rows, and j represents the variable of the number of columns;

构成第x个文件的特征数；Depend on

The number of features that make up the xth file;

The hyperplane A set by the classification analysis unit is:

；

;

为超平面系数，

为超平面元素，b为阈值；in,

is the hyperplane coefficient,

is the hyperplane element, b is the threshold;

The hyperplane A satisfies:

；

;

表示一类特征数对应的文件序号，

表示二类特征数对应的文件序号；in,

Indicates the file number corresponding to a type of feature number,

Indicates the file number corresponding to the second type of feature number;

The classification module includes a text processing unit, a calculation processing unit and an execution unit, wherein the text processing unit is used to count the occurrence frequency of specific words in the text file, the calculation processing unit is used to perform calculation tasks, and the execution unit classifies the text according to the calculation results of the calculation processing unit and saves it to the corresponding storage area;

：The calculation processing unit includes a feature number calculation processor and a hyperplane calculation processor. The feature number calculation processor calculates the classification feature number of the file to be classified according to the following formula:

:

；

;

为所述文本处理单元统计得到的第y个词汇频次；in,

The frequency of the yth word obtained by counting the text processing unit;

The hyperplane calculation processor processes the classification feature number according to the hyperplane, and the calculation result of each hyperplane is:

；

;

的正负性确定分类码上对应位数上的值，并得到分类码，所述执行单元根据分类码将文本文件保存至对应的分类区域。The execution unit is based on

The positive or negative value of determines the value of the corresponding bit in the classification code, and obtains the classification code. The execution unit saves the text file to the corresponding classification area according to the classification code.

Embodiment 2:

This embodiment includes all the contents of the first embodiment, and provides a file arrangement system based on AIGC, including a storage module, an analysis module, a classification module, an application module and an output module;

The storage module is responsible for storing the user's files. The analysis module analyzes the files based on AIGC technology to identify the subject, keywords and other information of the file content. The classification module classifies the files using the information generated by the analysis module. The application module provides users with a variety of application functions. The output module is responsible for generating reports for decision-making and presenting them to users in an appropriate form.

In conjunction with FIG2 , the analysis module includes a vocabulary statistics unit, a word frequency matrix processing unit, a feature processing unit and a classification analysis unit. The vocabulary statistics unit can process each input text file, and the processing process includes decomposition, word removal, extraction and statistics. The decomposition process is to decompose the entire text into multiple phrases, the word removal process is to delete connecting words, the extraction process is to extract the stems in the phrases, and the statistical process is to count the number of times each stem appears. The vocabulary statistics unit creates a vocabulary table based on the extracted stems to record the words that have appeared;

The word frequency matrix processing unit generates an m*n matrix according to the statistical results, wherein m represents the number of files, n represents the number of words in the vocabulary, each row represents a file, each column represents a word, and each element represents the frequency of the word appearing in the file;

The feature processing unit performs calculation processing based on the element values in the matrix according to the following formula:

；

;

表示矩阵中第x行、第y列的元素值，i表示行数的变量，j表示列数的变量；in,

Represents the element value of the x-th row and y-th column in the matrix, i represents the variable of the number of rows, and j represents the variable of the number of columns;

构成第x个文件的特征数；Depend on

The number of features that make up the xth file;

个超平面来实现对

个类型文件的分类分析，文件的类型用

位的二进制数表示，所述二进制数称为分类码，每个超平面对应于分类码的其中一位，所述分类码随文本文件一同发送至所述分析模块，文本文件经处理得到特征数后，分类码与对应的特征数进行配对被发送至所述分类分析单元；The classification analysis unit is configured by

A hyperplane is used to realize

Classification analysis of file types, the file types are

The binary number of bits is represented by the classification code, each hyperplane corresponds to one bit of the classification code, and the classification code is sent to the analysis module together with the text file. After the text file is processed to obtain the feature number, the classification code is paired with the corresponding feature number and sent to the classification analysis unit;

5, the process of the classification analysis unit setting a hyperplane includes the following steps:

S1. Determine the number of classification code bits corresponding to the hyperplane, called the target bit;

S2. Classify the classification codes into two categories according to the value of the target bit. The classification codes with the target bit value of 1 are the first-class codes, and the classification codes with the target bit value of 0 are the second-class codes.

S3, classifying the feature numbers according to the classification results of the classification codes in step S2, that is, the feature numbers corresponding to the first-class code are the first-class feature numbers, and the feature numbers corresponding to the second-class code are the second-class feature numbers;

S4. Set a hyperplane A:

；

;

为超平面系数，

为超平面元素，b为阈值；in,

is the hyperplane coefficient,

is the hyperplane element, b is the threshold;

The hyperplane A satisfies:

；

;

表示一类特征数对应的文件序号，

表示二类特征数对应的文件序号，满足的不等式的形式确定了正负性与0、1值的对应关系；in,

Indicates the file number corresponding to a type of feature number,

It represents the file number corresponding to the second type of feature number. The form of the inequality satisfied determines the corresponding relationship between the positive and negative values 0 and 1;

，最终得到确定的超平面：S5. Adjust the value of the threshold b so that the shortest distance from the first type of feature number to the hyperplane is equal to the shortest distance from the second type of feature number to the hyperplane. The threshold at this time is recorded as

, and finally get the determined hyperplane:

；

;

到超平面的距离公式为：Number of features

The distance formula to the hyperplane is:

；

;

个超平面，所述超平面信息被发送至所述分类模块，所述超平面信息中包含了正负性与0、1的对应关系；The classification analysis unit is set according to the above process to obtain

A hyperplane, the hyperplane information is sent to the classification module, and the hyperplane information contains the correspondence between positive and negative and 0, 1;

In conjunction with FIG3 , the classification module includes a text processing unit, a calculation processing unit and an execution unit, wherein the text processing unit is used to count the occurrence frequency of specific words in the text file, the calculation processing unit is used to perform calculation tasks, and the execution unit classifies the text according to the calculation results of the calculation processing unit and saves it to the corresponding storage area;

The text processing unit stores the vocabulary table created by the vocabulary statistics unit, and performs statistics based on the words recorded in the vocabulary table;

：4, the calculation processing unit includes a feature number calculation processor and a hyperplane calculation processor, and the feature number calculation processor calculates the classification feature number of the file to be classified according to the following formula:

:

；

;

为所述文本处理单元统计得到的第y个词汇频次；in,

The frequency of the yth word obtained by counting the text processing unit;

个超平面对分类特征数进行处理，每个超平面的计算结果为：The hyperplane computing processor is based on

Hyperplanes process the classification features, and the calculation result of each hyperplane is:

；

;

的正负性确定分类码上对应位数上的值，并得到分类码，所述执行单元根据分类码将文本文件保存至对应的分类区域；The execution unit is based on Ns

The positive or negative value of determines the value of the corresponding bit on the classification code, and obtains the classification code, and the execution unit saves the text file to the corresponding classification area according to the classification code;

The storage module includes a storage unit and a logic unit, the storage unit is divided into Ns+1 storage areas, one of which is used to store text files to be classified, and the storage area is called a temporary area, and the other Ns storage areas are used to store classified text files, and the storage area is called a classification area. The logic unit is used to record the logical relationship between the Ns classification areas;

The application module is used to provide an application interface, which includes a classification interface and a report interface. The classification interface is connected to the temporary area, and the input text file is saved to the temporary area through the classification interface. After the temporary area receives the new file, the classification module is started to classify and save the input text file. The report interface is used to receive time information and count the newly added text files within the time information to obtain the proportion of various classified files added in the corresponding time period.

The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims (5)

1. A file arrangement system based on AIGC, characterized by comprising a storage module, an analysis module, a classification module, an application module and an output module; The storage module is responsible for storing the user's files, the analysis module analyzes the files based on the AIGC technology, the classification module classifies the files using the information generated by the analysis module, the application module provides application functions for the user, and the output module is responsible for generating reports for decision-making; The analysis module receives training files, converts the files into feature information, creates a hyperplane based on the feature information, and the hyperplane information is sent to the classification module. The classification module calculates and processes the files to be classified based on the hyperplane to obtain a classification code. Each bit of the classification code corresponds to a hyperplane. The classification module saves the files to be classified to the corresponding area of the storage module according to the classification code. 2. A file sorting system based on AIGC as described in claim 1, characterized in that the analysis module includes a vocabulary statistics unit, a word frequency matrix processing unit, a feature processing unit and a classification analysis unit, the vocabulary statistics unit creates a vocabulary table according to the input text file and performs vocabulary statistics on each text file based on the vocabulary table, the word frequency matrix processing unit generates an m*n matrix according to the statistical results, wherein m represents the number of files and n represents the number of words in the vocabulary table, the feature processing unit obtains the n-dimensional feature number of each file according to the word frequency matrix processing, and the classification analysis unit creates a hyperplane based on the feature number and the classification code of the text file. 3. A file arrangement system based on AIGC as claimed in claim 2, characterized in that the feature processing unit performs calculation processing based on the element values in the matrix according to the following formula:

; in,

Represents the element value of the x-th row and y-th column in the matrix, i represents the variable of the number of rows, and j represents the variable of the number of columns; Depend on

The number of features that make up the xth file; The hyperplane A set by the classification analysis unit is:

; in,

is the hyperplane coefficient,

is the hyperplane element, b is the threshold; The hyperplane A satisfies:

; in,

Indicates the file number corresponding to a type of feature number,

Indicates the file number corresponding to the second type of feature number. 4. A file sorting system based on AIGC as described in claim 3, characterized in that the classification module includes a text processing unit, a calculation processing unit and an execution unit, the text processing unit is used to count the occurrence frequency of specific words in the text file, the calculation processing unit is used to perform calculation tasks, and the execution unit classifies the text according to the calculation results of the calculation processing unit and saves it to the corresponding storage area. 5. A file sorting system based on AIGC as claimed in claim 4, characterized in that the calculation processing unit includes a feature number calculation processor and a hyperplane calculation processor, and the feature number calculation processor calculates the classification feature number of the file to be classified according to the following formula:

:

; in,

The frequency of the yth word obtained by counting the text processing unit; The hyperplane calculation processor processes the classification feature number according to the hyperplane, and the calculation result of each hyperplane is:

; The execution unit is based on

The positive or negative value of determines the value of the corresponding bit in the classification code, and obtains the classification code. The execution unit saves the text file to the corresponding classification area according to the classification code.

Images