Digital personnel file sample library automatic generation method and system

Abstract

The application belongs to the technical field of file management, and provides a digital personnel file sample library automatic generation method and system, which has the technical scheme of establishing a personnel basic information table; establishing a personnel name library, generating personnel basic information based on the set order of magnitude requirement, filling the generated personnel basic information into the constructed basic information table to obtain a personnel information library; generating corresponding type electronic data according to the formulated different types of templates based on the personnel information library; converting the different types of template generated corresponding type electronic data into personnel file digital images; and processing the personnel file digital images to obtain the final digital personnel file sample library. The establishment of the sample database with high quality and reaching a certain order of magnitude is helpful to the intelligent management and use of personnel files.

Description

Technical Field

[0001] This invention belongs to the field of archives management technology, and in particular to a method and system for automatically generating a digital personnel file sample database. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] With the development of information technology, all industries are showing a trend towards informatization, intelligentization, and digitalization. Traditional personnel file management can no longer meet the needs of daily work, leading to the emergence of digital file construction. Currently, after digitization, manual sorting is still required. Personnel file classification is the most critical and labor-intensive part of the digitization process. Furthermore, due to differences in the work experience of archivists, manual classification methods struggle to distinguish certain difficult-to-classify files, resulting in incorrect classification results. With the development of deep learning, natural language processing, large-scale models, and other related technologies, and the explosive growth of information, how to utilize artificial intelligence technology to build intelligent image classification algorithms has become a primary issue in improving the quality and efficiency of digitization. Currently, the application of both large-scale and small-scale artificial intelligence models relies heavily on sample data. Due to the confidentiality requirements and privacy restrictions of personnel files, it is impossible to establish a high-quality sample database of a certain scale. The lack of sample data leads to problems such as decreased generalization ability of file classification models, unstable training processes, and insufficient feature learning. Summary of the Invention

[0004] To address at least one of the technical problems mentioned above, this invention provides a method and system for automatically generating a digital personnel file sample database. The method constructs a personnel file metadata dataset, establishes template images according to the personnel file catalog classification, and automatically fills in metadata based on the prior structured information of the file template images to form complete personnel file information.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for automatically generating a digital personnel file sample database, comprising the following steps: Establish a basic information table for personnel; Establish a personnel name database, generate basic personnel information based on the set quantity requirements, and populate the generated basic personnel information into the constructed basic information table to obtain the personnel information database. Based on the personnel information database, electronic data of corresponding types is generated according to the established templates for different types; Different types of templates generate corresponding types of electronic data, which are then converted into digital images of personnel files. The final digital personnel file sample library is obtained by processing the digitized images of personnel files.

[0006] Furthermore, establishing a personnel name database includes: Based on the set order of magnitude parameter N1, N1 unique names are randomly generated to establish a personnel name database; based on the set order of magnitude N2, N2 names are randomly selected, with each name having an initial selection weight w set to 1, and the selected names having a selection weight set to 0.01. n n represents the number of times the name is extracted. A personnel information directory is created for each extracted name, and each personnel information directory is assigned a unique number.

[0007] Furthermore, based on the set order of magnitude requirements, basic personnel information is generated, including: Generate the ages of personnel based on their age distribution characteristics; Birth date information is randomly generated based on age information and the current year; Each person is randomly assigned educational background and degree information according to age, and their graduation time and working time are estimated according to their date of birth and time logic. Generate family member information and learning experiences based on preset rules.

[0008] Furthermore, the generation of corresponding data types based on the personnel information database and according to the established templates of different types includes: Develop electronic templates for various types of personnel files, structure each type of electronic template, populate the personnel information data from the personnel information database into the corresponding structured electronic templates, and label the type of each field; Establish prior information for various types of handwritten archives, and generate sample data of various types of handwritten archive materials for each person by combining basic information of the personnel and large model; Obtain a sample library of handwritten images, with each sample representing a type of handwritten style. Each person is randomly assigned a sample. Convert the printed text in the structured electronic templates and various handwritten archival material sample data into handwritten text, generating handwritten material data corresponding to various styles.

[0009] Furthermore, the process of generating handwritten material data corresponding to various styles includes: Edge detection is performed on the original sample image to obtain an edge image. Random noise is added to the edge image. The image with added noise and the edge image are input into the text style local encoder and global encoder. Local features of the text are extracted based on the local encoder and global features of the text are extracted based on the global encoder. The local features and global features of the text are fused to obtain the complete style features. For the input text to be converted to handwriting, a text content encoder is built to extract text content features; A cross-attention mechanism is used to fuse style features and text content features. The fused result serves as a guiding condition for the conditional diffusion model, which in turn guides the generation of handwritten texts of the same style.

[0010] Furthermore, the step of converting different types of templates into corresponding types of electronic data and then into digital images of personnel files includes: The system will generate corresponding data parsing based on different types of templates and map them to a unified, structured intermediate format. Each field corresponds to a specific location in the personnel file template, clearly defining the personnel file material type corresponding to each data record. A digital personnel file template library is established, with corresponding, standardized digital template files for each type of archival material. Based on the identified material type, the appropriate template is selected, and standardized data is precisely filled into the designated locations within the template. A corresponding rendering tool is then used to convert the filled template into the final digital personnel file image. Further, the process of processing the digital personnel file images to obtain the final digital personnel file sample library includes: Set a rotation angle range, randomly select a rotation angle for each digitized archival image, and rotate the image accordingly; A Gaussian blur algorithm is used for batch processing, and the background RGB values ​​of the archive images are set according to preset values; the size of the digitized archive images is normalized, and finally a digitized personnel file sample library is generated.

[0011] A second aspect of the present invention provides an automatic generation system for a digital personnel file sample database, comprising: The personnel information database construction module is used to create a basic information table for personnel; it also creates a personnel name database, generates basic information about personnel based on the set quantity requirements, and populates the generated basic information into the constructed basic information table to obtain the personnel information database. The digital image generation module is used to generate corresponding types of electronic data based on the personnel information database and according to the specified different types of templates; and to convert the electronic data generated by different types of templates into digital images of personnel files. The personnel file sample library generation module is used to process digitized images of personnel files to obtain the final digitized personnel file sample library.

[0012] A third aspect of the present invention provides a computer-readable storage medium.

[0013] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for automatically generating a digital personnel file sample database as described above.

[0014] A fourth aspect of the present invention provides a computer device.

[0015] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the method for automatically generating a digital personnel file sample database as described above.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention innovatively proposes a method for automatically generating a digital personnel file sample database. By constructing a personnel file metadata dataset, template images are established according to the personnel file catalog classification. Based on the prior structured information of the file template images, metadata is filled in to form complete personnel file information. This provides sample support for the application of artificial intelligence technology in personnel file management, which is conducive to improving the efficiency of personnel file management and solving the technical problem of lack of sample data.

[0017] 2. This invention proposes an automatic handwritten document generation algorithm based on a large language model. Based on personnel file content, an external knowledge base is established, and a large RAG model for automatic document generation is built to automatically generate file text information. An improved conditional diffusion model is used to automatically generate different handwritten styles of the generated file text information, establish relevant material information for personnel file handwritten text, enhance the completeness of personnel file information, and further solve the technical problem of lack of sample data.

[0018] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0019] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0020] Figure 1 This is a flowchart of the method for automatically generating a digital personnel file sample library provided in an embodiment of the present invention; Figure 2 This is a flowchart of the automatic generation process of handwritten material data provided in an embodiment of the present invention; Figure 3 This is a diagram of a lightweight convolutional neural network structure provided in an embodiment of the present invention. Detailed Implementation

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0023] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0024] Currently, the application of both large-scale and small-scale modeling technologies relies on the support of sample data. However, current personnel file management only builds a sample database based on basic personnel information, which cannot establish a high-quality sample database of a certain scale. This is not conducive to the intelligent management and application of personnel files. This invention proposes a method and system for automatically generating digital personnel file samples, targeting the catalog, structure, and content data of digital personnel files. By adjusting the system parameters, sample databases of different scales can be constructed.

[0025] Example 1 like Figure 1 As shown in the figure, this embodiment provides a method for automatically generating a digital personnel file sample database, including the following steps: Step 1: Establish a basic information table for personnel; In this embodiment, the key fields of the basic information table of the person to be evaluated include: "name", "gender", "date of birth", "education", "degree", "professional title", "place of origin", "ID number", "employer", "position", "graduating institution", "major", "working hours", "personal awards", "number of salary adjustments", "number of job changes", "whether there is an autobiography", and "family members".

[0026] Step 2: Establish a personnel name database, generate basic personnel information based on the set quantity requirements, and populate the generated basic personnel information into the constructed personnel basic information table; Specifically, the steps include the following: Step 201: Extract personnel names and establish a personnel name database; In this embodiment, according to the set order of magnitude parameter N1, N1 unique names are randomly generated to establish a personnel name database. Personnel names are then randomly selected from the database N2 times, with each name having an initial weight. w If the value is set to 1, then the weight of that name extracted will be set to 0.01. n ,n For each number of times a name is selected, a personnel information directory is created for each selected name, and each personnel information directory is assigned a unique number.

[0027] Step 202: Generate basic personnel information based on the set order of magnitude requirements; Specifically, the steps include the following: Step 2021: Generate the age of personnel based on their age distribution characteristics; Specifically, assume that the age data of the company's employees follows a log-normal distribution. (1), in, For employee age, The average age is 40 in this example. The standard deviation of age is 0.5 in this embodiment; The employee's age is generated according to the probability density function of formula (1). In this embodiment, the age range is set to [20, 60].

[0028] Step 2022: Generate a random birth date based on the age information and the current year; Step 2023: Randomly assign educational background and degree information to each person according to age, and estimate graduation time and working time according to birth date information and time logic; Step 2024: Generate family member information, learning experience, etc. based on the set rules.

[0029] In this embodiment, the setting rules are, for example: (1) Based on the age information of the personnel, the number of family members is randomly selected in the range of [2,6]. The relationship with the employee includes parents, spouse, and children. The names can be randomly generated by introducing the Faker library in Python. (2) The age differences among family members should be reasonable and random to avoid repetition and patterning. The parents' age should be 20 to 35 years older than the employee's age, with the increase being random. The spouse's age should be set to (employee's age ± 5 years), with the age deviation being random, but not less than 22 years.

[0030] (3) Establish a work unit database. Randomly select work units of family members from the work unit database. Family members under the age of 20 do not need to set a work unit.

[0031] (4) Based on the person’s education and graduation time information, the learning experience is automatically generated. The school information (primary school, junior high school, senior high school) can use virtual names.

[0032] Step 203: Fill the generated personnel's basic information into the constructed personnel basic information table to obtain the personnel information database.

[0033] Step 3: Based on the personnel information database, generate corresponding data according to the established templates for different types; Specifically, the steps include the following: Step 301: Develop electronic templates for various types of personnel files, structure the electronic templates for each type, fill the personnel information data in the personnel information database into the corresponding structured electronic templates, and label the type of each field. In this embodiment, the electronic templates for various types of personnel files include multiple sample electronic templates such as personnel resumes, cadre appointment and removal approval forms, professional title recognition forms, and college entrance examination registration information forms. The electronic templates are in Word or Excel format. Each type of electronic template is structured to obtain a structured template, and the personnel information generated in step 2 is automatically filled into the structured template. Furthermore, when automatically filling the generated personnel information into the structured template, each field can be marked with either handwritten or printed input methods according to the actual document form material style; For example, for the personnel file's Category 1 personnel resume, N resumes can be randomly generated based on the employee's age (one resume for every 5-8 years of service), with the review date marked. Then, information such as "name," "age," "education," "degree," "work experience," and "family members" can be automatically filled in according to the personnel resume template, and these fields can be marked as "handwritten." Subsequently, step 302 will convert the relevant electronic data into handwritten text. Information on job changes and salary changes will be automatically filled in the job and salary change table, and the filled fields will be marked as "printed text," which can then be directly converted into a digital file image.

[0034] Step 302: Establish prior information for various types of handwritten archives, and generate sample data of various types of handwritten archive materials for each person by combining the basic information of the personnel and the large model; In this embodiment, specific types of handwritten archives include autobiographical materials in cadre personnel files, handwritten data in resumes, handwritten data in college entrance examination registration forms, etc.; once the type of handwritten archive is determined, the corresponding prior information on handwritten materials can be obtained. Based on basic personnel information such as employee job information, determine whether to establish handwritten files such as autobiographical materials. If so, large-scale model generation technology can be used to automatically generate personnel autobiographical materials for cadres based on prior information such as the employee's educational background and work experience.

[0035] Step 303: Obtain a sample library of handwritten images. Each sample represents a type of handwritten style. Each person is randomly assigned a sample. The printed text in the structured electronic template and various handwritten archival material sample data is converted into handwritten text, generating handwritten material data corresponding to various styles. In this embodiment, the acquired handwritten image sample library is denoted as R, with m samples. The samples are binarized, and each handwritten sample image I represents a handwritten style. To make the virtual archive samples closer to the actual sample format, the printed text in the relevant electronic data needs to be converted to handwritten text. Each person randomly selects a sample from the handwritten image sample library R for binding. The sample data of the bound handwritten sample represents a handwritten style. Corresponding to the handwritten sample style, the handwritten data in the archive is converted into handwritten text, generating the final handwritten material data. The specific steps include the following: Step 3031: First, extract the font style features. Use the Canny edge detection operator to perform edge detection on the original handwritten sample image I to obtain the edge image I. E For image I E Image I is obtained by adding random noise N ; Step 3032: Add random noise to each image I. N Edge Image I E The text is input into a local encoder and a global encoder. Local features of the text are extracted based on the local encoder, and global features of the text are extracted based on the global encoder. The local features and global features of the text are then fused to obtain complete style features. Specifically, the local encoder uses a lightweight convolutional neural network to extract local text features F. local ,like Figure 3 As shown, the lightweight convolutional neural network consists of convolutional layers, normalization layers, and 6 ReLU layers, for a total of 5 layers. The number of convolutional channels are 128, 64, 64, 32, and 32, respectively, and the convolutional kernels are 5×5, 5×5, 3×3, 3×3, and 1×1, respectively. The global encoder model adopts a 2-layer Transformer structure to extract the global structural features F of the text. global A feature-level cascade fusion method is employed to fuse global and local features, resulting in a complete style feature F. style : (2), in, The weights of local text features, The weights are the global structural features of the text.

[0036] Step 3033: For the input text to be converted into handwriting, build a text content encoder. The text content is converted into a vector sequence using a character embedding algorithm. Then, the vector sequence is input into a two-layer Transformer structure to extract the text content features F. content .

[0037] Step 3034: Use a cross-attention mechanism to apply style feature F style and content features F content The fusion process is performed, and the fusion result serves as a guiding condition for the conditional diffusion model, which in turn guides the generation of handwritten text in the same style. In this embodiment, a new loss function is designed for model training in the conditional diffusion model. The definition of the loss function integrates noise prediction loss, edge loss, and multi-scale structural similarity loss to guide the generation of handwritten text of the same style.

[0038] Among them, noise prediction loss , is represented as: , Here, E represents the expectation function. and Let represent the mean of the normal distribution in the forward and reverse processes of the diffusion model, respectively. Original image of handwritten style text. This represents a handwritten-style image after adding noise at time step t in the diffusion model.

[0039] Edge loss function Represented as: , Here, △ represents the Sobel operator.

[0040] Multiscale structural similarity loss Represented as: , here MS-SSIM represent and The multi-scale similarity function.

[0041] The final loss function is defined as: , in, In this embodiment, the weights corresponding to each loss are... Take values ​​of 0.5, 0.3, and 0.2.

[0042] To address the issue of insufficient diversity in generated handwriting styles, this invention utilizes an improved conditional diffusion model algorithm to generate handwriting styles of different characteristics. This method learns to generate fonts of the same style from a single handwriting sample and can add random noise to the original handwriting samples to achieve differences in the same style of font among different individuals. The automatically generated handwriting information is then filled into personnel file forms and related materials.

[0043] Step 304: Generate relevant image data, which mainly includes virtual personnel ID photos, academic degree certificates, award certificates, etc. For example, using large-scale image generation tools, ID photos can be automatically generated based on characteristics such as age and gender. These photos are then pasted into the relevant archival documents based on prior information about the document type. Templates for documents such as graduation certificates, degree certificates, professional title certificates, and award certificates can be generated using image generation tools based on the input image style to create corresponding personnel image archival materials.

[0044] In this embodiment, other relevant data can also be generated based on other defined templates, and can be added according to the actual scenario.

[0045] Step 4: Convert the electronic data of different types of templates into digital images of personnel files, and continue to arrange them according to the file organization order; Specifically, the steps include the following: Step 401: Generate corresponding data according to different types of templates and map them to a unified, structured intermediate format. Each field corresponds to a specific position in the personnel file template, and the personnel file material type corresponding to each data record is specified. Step 402: Establish a digital template library for personnel files. Each type of file material has a corresponding, standardized digital template file. Based on the identified material type, select the corresponding template, accurately fill the standardized data into the designated position of the template, and use the corresponding rendering tool to convert the filled template into the final digital image of the personnel file. Step 403: Classify and sort each generated digital image file according to industry standards or the company's internal record regulations.

[0046] Step 5: Process the digitized images of personnel files to obtain the final digitized personnel file sample library.

[0047] Specifically, the steps include the following: Step 501: Set the rotation angle range For each digitized archival image, a rotation angle is randomly selected, and the image is rotated.

[0048] Step 502: Perform batch processing using the Gaussian blur algorithm, and set the background RGB values ​​of the archive images according to preset values, such as (254, 246, 197); Step 503: Normalize the size of the digitized archive images to finally generate a digitized personnel file sample library.

[0049] Using the above approach, a personnel file metadata dataset is constructed. Template images are created according to the personnel file catalog classification. Based on the prior structured information of the file template images, metadata is populated to form complete personnel file information.

[0050] Example 2 This embodiment provides an automatic generation system for a digital personnel file sample database, including: The personnel information database construction module is used to create a basic information table for personnel; it also creates a personnel name database, generates basic information about personnel based on the set quantity requirements, and populates the generated basic information into the constructed basic information table to obtain the personnel information database. The digital image generation module is used to generate data of corresponding types based on the personnel information database and according to specified templates of different types; and to convert different types of data into digital images of personnel files. The personnel file sample library generation module is used to process digitized images of personnel files to obtain the final digitized personnel file sample library.

[0051] It should be noted that the specific implementation of the automatic generation system for digital personnel file sample database in this embodiment of the invention is similar to the specific implementation of the automatic generation method for digital personnel file sample database in this embodiment of the invention. Please refer to the description in the method section for details. To reduce redundancy, it will not be repeated here.

[0052] Example 3 This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps in the method for automatically generating a digital personnel file sample database as described above.

[0053] Example 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps in the method for automatically generating a digital personnel file sample database as described above.

[0054] Example 5 This embodiment provides a program product, which is a computer program product, including a computer program. The computer program, when executed by a processor, implements the steps in the above-described method for automatically generating a digital personnel file sample database.

[0055] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0056] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0057] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0058] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0059] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0060] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for automatically generating a digital personnel file sample database, characterized in that, Includes the following steps: Establish a basic information table for personnel; Establish a personnel name database, generate basic personnel information based on the set quantity requirements, and populate the generated basic personnel information into the constructed basic information table to obtain the personnel information database. Based on the personnel information database, electronic data of corresponding types is generated according to the established templates for different types; Different types of templates generate corresponding types of electronic data, which are then converted into digital images of personnel files. The digitized images of personnel files are processed to obtain the final digital personnel file sample library; The step of generating corresponding types of electronic data based on a personnel information database and according to different types of templates includes: Develop electronic templates for various types of personnel files, structure each type of electronic template, populate the personnel information data from the personnel information database into the corresponding structured electronic templates, and label the type of each field; Establish prior information for various types of handwritten archives, and generate sample data of various types of handwritten archive materials for each person by combining basic information of the personnel and large model; Obtain a sample library of handwritten images, with each sample representing a type of handwritten style. Each person is randomly assigned a sample. Convert the printed text in the structured electronic templates and various handwritten archival material sample data into handwritten text to generate handwritten material data corresponding to various styles. The process of generating handwritten material data for various styles includes: Edge detection is performed on the original sample image to obtain an edge image. Random noise is added to the edge image. The image with added noise and the edge image are input into the text style local encoder and global encoder. Local features of the text are extracted based on the local encoder and global features of the text are extracted based on the global encoder. The local features and global features of the text are fused to obtain the complete style features. For the input text to be converted to handwriting, a text content encoder is built to extract text content features; A cross-attention mechanism is used to fuse style features and text content features. The fused result serves as a guiding condition for the conditional diffusion model, which in turn guides the generation of handwritten texts of the same style.

2. The method for automatically generating a digital personnel file sample database as described in claim 1, characterized in that, Establishing a personnel name database includes: Based on the set order of magnitude parameter N1, N1 unique names are randomly generated to establish a personnel name database; based on the set order of magnitude parameter N2, N2 names are randomly selected, with each name having an initial selection weight w set to 1, and the selected names having a selection weight set to 0.

01. n n represents the number of times the name is extracted. A personnel information directory is created for each extracted name, and each personnel information directory is assigned a unique number.

3. The method for automatically generating a digital personnel file sample database as described in claim 1, characterized in that, Generate basic personnel information based on the set quantity requirements, including: Generate the ages of personnel based on their age distribution characteristics; Birth date information is randomly generated based on age information and the current year; Each person is randomly assigned educational background and degree information according to age, and their graduation time and working time are estimated according to their date of birth and time logic. Generate family member information and learning experiences based on preset rules.

4. The method for automatically generating a digital personnel file sample database as described in claim 1, characterized in that, The process of generating corresponding types of electronic data from different types of templates and converting them into digital images of personnel files includes: The electronic data will be parsed and mapped to a unified, structured intermediate format according to different types of templates. Each field corresponds to a specific location in the personnel file template, and the type of personnel file material corresponding to each data record is clearly defined. Establish a digital template library for personnel files, with corresponding, standardized digital template files for each type of file material; select the appropriate template based on the identified material type, accurately fill the standardized data into the designated positions of the template, and use the corresponding rendering tool to convert the filled template into the final digital image of the personnel file.

5. The method for automatically generating a digital personnel file sample database as described in claim 1, characterized in that, The process of processing digitized images of personnel files to obtain the final digitized personnel file sample library includes: Set a rotation angle range, randomly select a rotation angle for each digitized archival image, and rotate the image accordingly; A Gaussian blur algorithm is used for batch processing, and the background RGB values ​​of the archive images are set according to preset values; the size of the digitized archive images is normalized, and finally a digitized personnel file sample library is generated.

6. An automatic generation system for digital personnel file sample database, characterized in that: The method for automatically generating a digital personnel file sample database according to any one of claims 1-5 includes: The personnel information database construction module is used to create a basic information table for personnel; it also creates a personnel name database, generates basic information about personnel based on the set quantity requirements, and populates the generated basic information into the constructed basic information table to obtain the personnel information database. The digital image generation module is used to generate corresponding types of electronic data based on the personnel information database and according to the specified different types of templates; and to convert the electronic data generated by different types of templates into digital images of personnel files. The personnel file sample library generation module is used to process digitized images of personnel files to obtain the final digitized personnel file sample library.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for automatically generating a digital personnel file sample library as described in any one of claims 1-5.

8. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for automatically generating a digital personnel file sample library as described in any one of claims 1-5.

Images