Resume generation method and device, storage medium and program product

By identifying gender attributes and image processing technology, high-definition and similarity certificate photos are generated, and resumes for different positions are generated based on work experience, which solves the time and energy problems of job seekers when making multiple resumes and improves resume generation Efficiency and diversity of ID licenses.

CN119006637APending Publication Date: 2024-11-22BEIJING CHENGSHI WANGLIN INFORMATION TECH CO LTD

Patent Information

Application Number
CN202411141132.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Job seekers need to spend a lot of time and effort when producing multiple resumes for different positions. The clarity and similarity of the existing technology of the certificate generation is low, and the type is single, which cannot meet the requirements of different positions.

Method used

By identifying the user's gender attributes, selecting the appropriate ID photo template, and using image processing and optimization models to generate high-definition and similar ID photo, and generating resumes for each position based on personal identity information and work experience.

Benefits of technology

It reduces the time and energy required for resume production, improves the diversity and overall similarity of ID photos, and improves the efficiency of resume generation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119006637A_ABST
    Figure CN119006637A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a resume generation method and device, a storage medium and a program product. In the embodiment of the invention, on one hand, the gender attribute of the target object is identified according to the initial feature information of the five sense organs; and selecting each target identification photo template matched with each application post of the user from the plurality of candidate identification photo templates. Furthermore, image processing is performed on the initial feature information of the five sense organs and each target identification photo, and after the initial identification photo is obtained, optimization processing is performed on the initial identification photo based on the at least one prompt word to obtain each target identification photo of the user, so that the definition of the target identification photo and the overall similarity of the target identification photo and the original photo can be improved. And on the other hand, according to the personal identity information of the user, the at least one applied post, the target identification photo related to each applied post and at least part of work experience, the resume of the user for each applied post is generated, so that the time and energy of making the resume can be reduced, and the making efficiency of the resume can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and in particular to a resume generation method, device, storage medium and program product. Background Art

[0002] With the continuous advancement of the Internet era, job seekers mostly apply for jobs through the Internet. Job seekers need to prepare one or more electronic resumes when applying for jobs, and use electronic resumes to explain their past learning and work experience and the job they are applying for, in order to prove to the recruiting company that their abilities and experience meet the requirements of the position they are applying for.

[0003] Usually, job seekers prepare electronic resumes manually, which takes a lot of time and effort. Since the application requirements and work experience required for different job positions are different, manually preparing multiple resumes for different job positions requires a lot of time and effort.

[0004] In addition, each resume needs to be accompanied by the applicant's ID photo. Since different job positions may have different requirements for ID photos, applicants are required to take multiple ID photos of different types. For example, you can use a camera application to take ID photos. At present, most camera applications on the market generate photos based on generative algorithms. Specifically, multiple facial images of the user are input, and the multiple facial images are simply processed using an image processing model. The processed facial images are pasted onto the ID photo template to obtain the ID photo. However, the ID photos generated in the above manner are of a single type, and different types of ID photos need to be taken multiple times. In addition, the clarity of the ID photos and the overall similarity with the original photos are low.

[0005] There is currently no effective solution to the above problems. Summary of the invention

[0006] Multiple aspects of the present application provide a resume generation method, device, storage medium and program product to improve the clarity of ID photos and the overall similarity with the original photos, as well as reduce the time and effort required to prepare resumes and improve resume preparation efficiency.

[0007] The embodiment of the present application provides a resume generation method, which is applied to a server. The method includes: receiving a resume generation request initiated by a user terminal, and based on the resume generation request, obtaining basic information of the user, wherein the basic information includes at least personal identity information, job information and a face image of the user, wherein the job information includes at least at least one job to be applied for and work experience, and the face image includes initial facial feature information of the user; identifying the gender attribute of the user according to the initial facial feature information included in the face image; selecting a target ID photo template for each job to be applied for from a plurality of candidate ID photo templates adapted to the gender attribute of the user according to the gender attribute of the user and at least one job to be applied for; and The initial facial feature information is processed with each target ID photo template respectively to generate each initial ID photo of the user; at least one initial ID photo and at least one prompt word corresponding to the target ID photo template of at least one initial ID photo are input into the image optimization model, and each initial ID photo is refined according to the at least one prompt word to obtain each target ID photo of the user; based on at least one applied position and work experience, at least part of the work experience related to each applied position is determined; based on the user's personal identity information, at least one applied position, the target ID photo related to each applied position, and at least part of the work experience, a resume of the user for each applied position is generated.

[0008] An embodiment of the present application provides another resume generation method, which is applied to a user end, and the method includes: displaying a resume generation page, which includes at least a basic information acquisition control, and the basic information acquisition control is used to provide the user with a function of editing basic information, the basic information includes the user's personal identity information, position information and facial image, the position information includes at least one job application and work experience, and the facial image includes the user's initial facial feature information; in response to the user completing the basic information editing operation based on the basic information acquisition control, sending a resume generation request to the server end to request the server end to generate at least one target ID photo based on the facial feature information and at least one job application, and requesting the server end to generate a resume for each job application based on the user's personal identity information, at least one job application, and the target ID photo related to each job application, and at least part of the work experience.

[0009] An embodiment of the present application also provides an electronic device, comprising: a memory and a processor; the memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program in the memory to implement the steps in the resume generation method provided in the embodiment of the present application.

[0010] The embodiment of the present application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor is enabled to implement the steps in the resume generation method provided in the embodiment of the present application.

[0011] An embodiment of the present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, enables the processor to implement the steps in the resume generation method.

[0012] The technical solution provided by the embodiment of the present application, on the one hand, for the generation of the ID photo of the user, the gender attribute of the target object can be identified according to the initial facial feature information contained in the face image; from the multiple candidate ID photo templates adapted to the user's gender attribute, each target ID photo template adapted to the user's job position is selected. Further, the initial facial feature information and each target ID photo can be image processed, and after obtaining the initial ID photo, the initial ID photo can be optimized based on at least one prompt word to obtain each target ID photo of the user, thereby, before the image processing, it is not necessary to collect multiple facial images of the target object to obtain a high-definition target ID photo, and the overall similarity between the target ID photo and the original photo can be improved. On the other hand, on the basis of generating each target ID photo adapted to each job position, the user's resume for each job position can be generated according to the user's personal identity information, at least one job position, and the target ID photo related to each job position, and at least part of the work experience, which can reduce the time and effort required for making a resume and improve the efficiency of making a resume. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1 A schematic diagram of the structure of a resume generation system provided for an exemplary embodiment of the present application;

[0015] Figure 2 A flowchart of a resume generation method provided for an exemplary embodiment of the present application;

[0016] Figure 3 A flowchart of a resume generation method provided for an exemplary embodiment of the present application;

[0017] Figure 4 A schematic diagram of the structure of a resume generating device provided by an exemplary embodiment of the present application;

[0018] Figure 5 A schematic diagram of the structure of a resume generating device provided by an exemplary embodiment of the present application;

[0019] Figure 6 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0021] It should be noted that the target object information (including but not limited to target object device information, target object personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the target object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for the target object to choose to authorize or refuse. In addition, the various models involved in this application (including but not limited to language models or large models) are in compliance with relevant laws and standards.

[0022] At present, job seekers prepare electronic resumes manually, which takes a lot of time and energy. Since the application requirements and work experience required for different job positions are different, manually preparing multiple resumes for different job positions requires a lot of time and energy for job seekers.

[0023] In addition, each resume needs to be accompanied by the applicant's ID photo, which can be generated through an image processing model, specifically, by inputting multiple facial images of the user, performing simple processing on the multiple facial images using the image processing model, and pasting the processed facial images onto the ID photo template to obtain the ID photo. However, the ID photos generated in the above manner are of a single type, and different types of ID photos need to be taken multiple times, and the clarity of the ID photos and the overall similarity with the original photos are low.

[0024] In view of the above technical problems, in the embodiments of the present application, on the one hand, for the generation of the ID photo of the user, the gender attribute of the target object can be identified according to the initial facial feature information contained in the face image; from the multiple candidate ID photo templates adapted to the user's gender attribute, each target ID photo template adapted to the user's job position is selected. Further, the initial facial feature information and each target ID photo can be image processed, and after obtaining the initial ID photo, the initial ID photo can be optimized based on at least one prompt word to obtain each target ID photo of the user, thereby, before the image processing, it is not necessary to collect multiple facial images of the target object to obtain a high-definition target ID photo, and the overall similarity between the target ID photo and the original photo can be improved. On the other hand, on the basis of generating each target ID photo adapted to each job position, the user's resume for each job position can be generated according to the user's personal identity information, at least one job position, and the target ID photo related to each job position, and at least part of the work experience, which can reduce the time and effort required to prepare the resume and improve the efficiency of resume preparation.

[0025] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0026] Figure 1 The following is a schematic diagram of a resume generation system provided by an exemplary embodiment of the present application. Figure 1 The resume generation system includes: a user terminal 101 and a server terminal 102, and the user terminal 101 and the server terminal 102 can be connected for communication.

[0027] The embodiments of the present application do not limit the implementation form of the user terminal. The user terminal may be a terminal device with a resume generation function. For example, the resume generation function is integrated into the operating system of the terminal device, thereby supporting the resume generation function of the terminal device. Alternatively, the user terminal may also be software with a resume generation function installed on the terminal device, and the software may be an independently running application or a small program that relies on the application to run.

[0028] The embodiments of the present application do not limit the type of terminal device. For example, the terminal device may be a smart handheld device, such as a smart phone, a tablet computer, a laptop computer, or a desktop computer, etc.; for another example, the terminal device may also be a smart wearable device, such as a smart watch, a smart bracelet, etc.

[0029] The embodiment of the present application does not limit the implementation form of the server. The server can be a physical server or a single cloud server.

[0030] In an embodiment of the present application, the user end can display a resume generation page, and the user can upload or enter his basic information through the resume generation page, and send various requests related to generating resumes to the server end, so as to finally achieve the purpose of generating resumes. Among them, the resume generation page contains at least a basic information acquisition control, and the basic information acquisition control is used to obtain the basic information of the user. The basic information at least includes the user's personal identity information, job information and face image, etc. The personal identity information at least includes: the user's name, gender and contact information. The job information includes: at least one job to apply for, and work experience. The job to apply for can be a chef position, a lawyer position, an administrative staff position or a housekeeper position, etc.; the work experience can be a description of the job functions, tenure time and other related content of each position served. The face image includes the user's initial facial feature information, and the initial facial feature information is information used to describe the features of the facial features of the human face. The facial features include eyebrows, eyes, nose, mouth and ears, and the features of the facial features include at least the size, shape, color, etc. of the facial features. It should be noted that the above examples are only exemplary and do not constitute a limitation on this application.

[0031] The embodiments of the present application do not limit the implementation form of the basic information, and the implementation form of the basic information includes but is not limited to the following implementation methods.

[0032] In one possible implementation, the basic information may be in the form of text, pictures and / or videos. That is, the basic information may be in the form of text and pictures; or, the basic information may be in the form of text and videos. The text is a description of the basic information of the user, the picture is a face image, and the video is a video containing a face.

[0033] In another possible implementation, the basic information may be implemented in the form of a picture or a video. That is, the basic information may be implemented in the form of a picture or a video. The picture may contain a face image and text at the same time, or the video may contain a face video and text description at the same time.

[0034] In another possible implementation, the basic information may be implemented in the form of a document. The document may contain both text and images, where the images are human face images; or, the document may contain only at least one image, where the at least one image contains human face images and text; or, the document may contain both first text and a video, where the video contains at least a human face, and the video may also contain a description of a second text, where the text content of the first text may be the same as or different from the text content of the second text. Or, the document may contain only a video, where the video contains a human face image and a description of the text.

[0035] The embodiments of the present application do not limit the implementation form of the basic information acquisition control. For example, the basic information acquisition control can be an upload control or an input box, etc. The upload control can be used to upload documents, pictures or videos, etc., and the input box can be used to input text information. The upload control and the input box can exist at the same time, or only the upload control can exist. Based on this, when all text and face images are contained in the document, picture or video at the same time, the basic information acquisition control can be implemented only as an upload control; when all text and face images cannot be contained in the document, picture or video at the same time, the basic information acquisition control can be implemented as both an upload control and an input box.

[0036] This embodiment does not limit the implementation method of obtaining the user's basic information through the basic information acquisition control, which can be determined based on the implementation form of the basic information acquisition control and the implementation form of the basic information. The implementation methods of obtaining the user's basic information through the basic information acquisition control include but are not limited to the following.

[0037] In an optional implementation, when a picture, video or document contains a facial image and all text, the user's basic information can be obtained only through the upload control, specifically: in response to the user's triggering operation on the upload control, a pop-up window for uploading files is displayed, the pop-up window contains a file selection control, and the file selection control is used for the user to select the file required to generate a resume; in response to the user's triggering operation on the file selection control, multiple files are displayed for the user to select; in response to the user's selection operation on the target file, the user end obtains the target file, and the target file can be one or more of a picture, video or document, depending on the information contained in the picture, video or document.

[0038] In another optional implementation, when a picture, video or document does not contain a facial image and / or all text, the user's basic information can be obtained through an input box and an upload control, specifically: in response to a user triggering an upload control, a pop-up window for uploading files is displayed, the pop-up window includes a file selection control, and the file selection control is used for the user to select files required to generate a resume; in response to a user triggering an operation on the file selection control, multiple files are displayed for the user to select; in response to a user selecting a target file, the user terminal obtains the target file, and the target file can be one or more of a picture, video or document, depending on the information contained in the picture, video or document; and, in response to a user input operation in the input box, text is obtained.

[0039] Furthermore, the resume generation interface of the user side may also include a "confirm" control for resume generation, and the "confirm" control is used to send a resume generation request to the server side, and the resume generation request includes the user's basic information. Specifically, the user side can generate a resume generation request based on the user's basic information in response to the user's triggering operation on the "confirm" control, and send the resume generation request to the server side to request the server side to generate a resume based on the user's basic information.

[0040] Correspondingly, the server receives the resume generation request sent by the user, and obtains the basic information of the user based on the resume generation request.

[0041] In an optional embodiment, based on a resume generation request, obtaining basic information of the user includes: In another optional embodiment, based on a resume generation request, obtaining basic information of the user includes: parsing the resume generation request to obtain text, pictures, videos or documents containing basic information of the user; identifying basic information of the user from the text, pictures, videos or documents.

[0042] In another optional embodiment, based on a resume generation request, obtaining basic information of the user includes: receiving a resume generation request sent by a user terminal; responding to the resume generation request, obtaining text, pictures, videos or documents containing user information from the user terminal; obtaining basic information of the user from the text, pictures, videos or documents.

[0043] In the embodiment of the present application, different job positions may have different requirements for ID photos. For chef positions, the requirement for ID photos may be to wear a chef's hat; for lawyer positions, the requirement for ID photos may be to wear a suit and tie; for administrative staff positions, the requirement for ID photos may be a bun or short hair; for domestic staff positions, the requirement for ID photos is to wear domestic clothes, etc. This embodiment does not make specific limitations on this. Moreover, for the same position, different recruitment companies may have different requirements for ID photos. In addition, different positions or different recruitment companies may also have different requirements for the background color of ID photos. For example, the background color can be white, blue or red, etc. In this regard, in order to meet the needs of applications, for different application positions, ID photos suitable for each application position can be generated to increase the diversity of ID photos.

[0044] Specifically, the user's gender attribute can be identified based on the initial facial feature information contained in the face image; based on the user's gender attribute and at least one job position, a target ID photo template can be selected for each job position from multiple candidate ID photo templates that are adapted to the user's gender attribute; the initial facial feature information is respectively processed with each target ID photo template to generate each initial ID photo of the user.

[0045] In an optional embodiment, the gender attribute of the user is identified based on the initial facial feature information contained in the facial image, including: inputting the facial image into the feature extraction network layer in the facial recognition model to extract the facial features to obtain the initial facial feature information; inputting the initial facial feature information into the gender classification network layer in the facial recognition model to perform gender classification to obtain the gender attribute of the user. This embodiment does not limit the type of facial recognition model. For example, the facial recognition model can be an Insight Face model. InsightFace is a facial recognition system based on deep learning. It is efficient, accurate and scalable. It can use advanced neural network technology to identify and verify faces in various complex environments.

[0046] Optionally, the target facial image is input into the feature extraction network layer in the face recognition model to extract facial features to obtain facial feature information, including: first extracting primary features of the image, such as edges and textures; gradually combining the primary features into more complex feature representations, which contain initial facial feature information; extracting features according to the feature level to be extracted to obtain facial feature information.

[0047] In another optional embodiment, the gender attribute of the user is identified based on the initial facial feature information contained in the facial image, including: inputting the facial image into a semantic segmentation model for semantic segmentation to obtain a binary image containing the facial feature area; obtaining a local image of the facial feature area based on the target facial image and the binary image, the local image being a partial image of the target facial image; inputting the local image into a feature extraction network layer in the facial recognition model to extract facial features to obtain the facial feature information contained in the local image; inputting the facial feature information contained in the local image into the gender classification network layer in the facial recognition model for gender classification to obtain the gender attribute of the user.

[0048] Among them, semantic segmentation refers to a technology in the field of computer vision and image processing, the purpose of which is to assign each pixel in an image to a specific category or object, so as to realize the recognition and segmentation of all objects in the image, such as the recognition and segmentation of facial features such as eyebrows, eyes, nose, mouth and ears. The semantic segmentation model is obtained by pre-training a plurality of facial image samples containing facial feature information. This embodiment does not limit the type of semantic segmentation model. For example, the semantic segmentation model can be a segmentation model based on deep learning of a convolutional neural network (CNN), a U-Net model, a Deep Lab (Deep Lab Semantic Image Segmentation, DeepLab) series model or a mobile network (Efficient Convolutional Neural Networks for Mobile Vision Applications V2, MobileNetV2) model, etc. Among them, the DeepLab series models include but are not limited to DeepLabv1, DeepLabv2, DeepLabv3 and DeepLabv3+ models. The semantic segmentation model can also be a model based on the Transformer-based visual network structure (Vi si on Transformer, ViT) class, such as the SETR (Semant ic Segmentation Transformer) model, the Segmenter model or the SegFormer model, etc.

[0049] The binary image of the facial features area refers to a two-dimensional array or image of the same size as the facial features area, which visually presents a black and white image. Each pixel value in a binary image represents the attribution or attribute of the pixel in a certain classification or recognition task. Specifically, a binary image can be used to represent the result of image segmentation, in which each pixel is assigned a probability label, which indicates the possibility that the corresponding pixel belongs to a specific category. These categories with the highest probability are usually used to determine the final category label of each pixel.

[0050] Optionally, the face image is input into a semantic segmentation model for semantic segmentation to obtain a binary image containing facial features, including: inputting the face image into the encoder of the semantic segmentation model, and using the encoder to gradually extract facial features; inputting the facial features into the decoder of the semantic segmentation model, and using the decoder to gradually restore the image resolution to obtain the pixel value of each pixel; based on the pixel reference value of each facial feature area and the pixel value of each pixel, calculating the category probability of the facial feature area to which each pixel belongs, and obtaining a probability map of each pixel in each facial feature area; converting the probability map into a binary image, in which the facial feature area is marked as 1 and other areas are marked as 0. Each pixel is assigned a probability, indicating the possibility that the pixel belongs to a specific category, and the category with the highest probability is usually used to determine the final category label of each pixel.

[0051] More specifically, in the encoder part, the continuous convolution and pooling operations of the semantic segmentation model gradually reduce the spatial dimension of the face image, while increasing the depth of the facial features to capture more abstract facial features; in the decoder part, the semantic segmentation model gradually restores the spatial dimension of the image through upsampling and transposed convolution, while reducing the depth of the facial features to obtain a feature map of the facial features; at the end of the decoder, the feature map is converted into the category probability of each pixel through one or more convolution layers, which usually involves a convolution layer with multiple output channels, each channel corresponding to a category probability; the output of the convolution layer is converted into a probability distribution using Softmax or other activation functions, and the Softmax function can ensure that for each pixel, the sum of the probabilities of all categories is 1; a probability map is output, in which each element corresponds to the pixel at the corresponding position in the input face image and contains the probability that the pixel belongs to each category; each pixel in the probability map is binarized according to a determined threshold to obtain a binary image. Among them, if the probability that a pixel belongs to a certain category is higher than the threshold, the pixel is marked as 1 (or the corresponding category label) in the binary image, otherwise it is marked as 0. The threshold usually refers to the global threshold used to convert continuous probabilities into discrete category labels. The threshold is the same for all pixels in the same image. This is because the threshold is a global processing method that determines the category based on the probability distribution of the entire image, rather than setting a threshold for each pixel separately. The specific value of the threshold is pre-set according to actual needs. The threshold can be fixed or dynamically selected based on the performance on the validation set.

[0052] It should be noted that the binary image of the facial features in the present embodiment may be a binary image including the facial features; or each facial feature may correspond to a binary image. The binary image of the face includes the following multiple binary images: a binary image corresponding to the eyebrow area, a binary image corresponding to the eye area, a binary image corresponding to the nose area, a binary image corresponding to the mouth area, and a binary image corresponding to the ear area.

[0053] Optionally, a local image of the facial features is obtained based on the target facial image and the binary image, including: based on the size of the binary image and the facial area included, adjusting the facial image to the same size and direction as the binary image to ensure that the two are aligned; locating the facial features according to the binary image; and cropping the facial image according to the positioning result to obtain a local image of the facial features corresponding to the marked area in the binary image. When locating the facial features according to the binary image, it can be achieved by scanning the non-zero values ​​(representing the facial features) in the binary image. It should be noted that if the facial features are close to the edge of the image, special processing may be required during cropping to ensure the integrity of the local image.

[0054] Optionally, the local image is input into the feature extraction network layer in the face recognition model to extract facial features to obtain facial feature information of the local image, including: first extracting primary features of the local image, such as edges and textures; gradually combining the primary features into more complex feature representations, which contain initial facial feature information; extracting features according to the feature level to be extracted to obtain facial feature information.

[0055] Furthermore, after obtaining the gender attribute of the user, a target ID photo template may be selected from candidate ID photo templates based on the gender attribute of the user and at least one job position applied for.

[0056] In an optional embodiment, a target ID photo template is selected from candidate ID photo templates based on the user's gender attribute and at least one job position applied for, including: determining a candidate ID photo template that matches the user's gender attribute based on the user's gender attribute, and sending the candidate ID photo template to a user terminal so that the user terminal can display the candidate ID photo template to the user; and receiving a selection request sent by the user terminal in response to the user's selection operation, and determining any candidate ID photo template selected by the user as the target ID photo template based on the selection request.

[0057] In another optional embodiment, a target ID photo template is selected from candidate ID photo templates based on the user's gender attribute and at least one job position applied for, including: obtaining the user's template requirement information; determining, based on the user's gender attribute, a candidate ID photo template that matches the user's gender attribute; and selecting, from the candidate ID photo templates, an ID photo template that matches the user's template requirement information as the target ID photo template.

[0058] Furthermore, after obtaining the target ID photo template that matches the template requirement information of the user, the initial facial feature information can be processed with each target ID photo template to generate each initial ID photo of the user. The specific implementation method of processing the initial facial feature information with each target ID photo template to generate each initial ID photo of the user can refer to the relevant description of the following embodiment, which will not be repeated here.

[0059] In addition, the user's descriptions of work experience for different positions may be mixed together without distinction, so it is necessary to classify the user's work experience in different positions so as to generate a resume based on the job experience of each position. Optionally, based on at least one job position and work experience, determining at least part of the work experience related to each job position includes: obtaining work experience descriptions related to each job position from a resume database; based on the work experience descriptions related to each job position, selecting work experience from the user's work experience whose semantic similarity with the work experience descriptions related to each job position meets a preset threshold, as at least part of the work experience related to each job position.

[0060] Furthermore, after obtaining the user's personal identity information, at least one job position applied for, target ID photos related to each job position applied for, and at least part of the work experience, a resume of the user for each job position applied for can be generated based on the user's personal identity information, at least one job position applied for, target ID photos related to each job position applied for, and at least part of the work experience.

[0061] In some embodiments, based on the user's personal identity information, at least one job position, target ID photos related to each job position, and at least part of the work experience, a resume of the user for each job position is generated, including: according to each job position, obtaining a target resume template adapted to each job position, the target resume template has a resume format; according to the resume format corresponding to each job position, adding the user's personal identity information, at least one job position, target ID photos related to each job position, and at least part of the work experience to the corresponding position of the target resume template adapted to each job position, and generating the user's resume for each job position. The resume format includes but is not limited to: the filling position of personal identity information, at least one job position, target ID photos related to each job position, at least part of the work experience, the size of the target ID photo in the resume, the font and size of the text in the resume, etc.

[0062] Furthermore, the user terminal displays a list of user resumes, which at least includes a view control for each resume, and each view control for each resume is associated with the corresponding resume. In response to the user triggering the view control for the target resume, the user terminal sends a view request for the target resume to the server terminal; accordingly, after receiving the view request for the target resume sent by the user terminal, the server terminal sends the target resume to the user terminal for the user to view the target resume.

[0063] Furthermore, the target resume displayed by the user terminal also includes a content editing control, which is used to modify and / or add and / or delete the target resume. Specifically, the user terminal responds to the modification and / or addition and / or deletion operations on the target resume triggered by the content editing control, and sends a request to modify and / or add and / or delete the target resume to the server terminal; after receiving the modification and / or addition and / or deletion request sent by the user terminal, the responding server terminal modifies the first target content and / or adds the second target content and / or deletes the third target content based on the modification and / or addition and / or deletion request to obtain an updated target resume; the updated target resume is sent to the user terminal for the user to view the updated target resume and is stored locally on the user terminal.

[0064] Furthermore, users can also submit resumes through the user end to find relevant jobs. Specifically, when the user end is implemented as a terminal device, a recruitment platform can also be installed on the terminal device, and users can submit resumes on the recruitment platform, wherein the recruitment platform will display multiple recruiter lists, and the recruiter list will display recruitment positions and resume submission controls. More specifically, the user determines the target recruiter based on the recruitment positions displayed in the recruitment list; in response to the user's triggering operation on the resume submission control of the target recruiter, a resume upload window is displayed; in response to the user's triggering operation on the resume upload window, a resume list is displayed; in response to the user's selection operation on the target resume, the target resume to be uploaded is determined; in response to the user's secondary triggering operation on the resume submission control, a resume submission request is generated, and the resume submission request is sent to the recruiter.

[0065] The above embodiment is a description of the resume generation and resume delivery process. The following will describe in detail the generation and optimization process of the user ID photo.

[0066] In some embodiments, the initial facial feature information is separately processed with each target ID photo template to generate each initial ID photo of the user, including: inputting the initial facial feature information and each target ID photo template into an image fusion model, fusing the initial facial feature information into each target ID photo template to obtain each intermediate ID photo; inputting each intermediate ID photo into an image restoration model, and repairing the facial area in each intermediate ID photo to obtain each initial ID photo of the user.

[0067] Optionally, the initial facial feature information and each target ID photo template are input into the image fusion model, and the initial facial feature information is fused into each target ID photo template to obtain each intermediate ID photo, including: inputting the initial facial feature information into the style adaptation network layer in the image fusion model, identifying the initial facial feature information and the style of each target ID photo template, and in the case where the style of the initial facial feature information does not match the style of each target ID photo template, adjusting the style of the initial facial feature information according to the style of each target ID photo template to obtain each target facial feature information; inputting each target facial feature information and each target ID photo template into the image fusion model, identifying the position information of the facial features in each target ID photo template, and correcting the facial feature information in each target ID photo template to the facial feature information of each target according to the position information of the facial features in each target ID photo template, to obtain each first initial intermediate ID photo. This embodiment does not limit the type of fusion model. For example, the fusion model can be an Inswapper model, which is a deep learning model for face replacement function, which can replace one person's face with another person's face in an image or video. The replacement is not a direct replacement of the face image, but a replacement at the face feature level.

[0068] The above-mentioned first initial intermediate ID photos are obtained by preliminarily fusing the initial facial feature information with the target ID photo template, and the clarity of the facial features and the similarity with the photographed user's facial image are relatively low.

[0069] In order to improve the clarity of the facial features of each first initial intermediate ID photograph, each first initial intermediate ID photograph may be input into an image restoration model to restore the face region in each first initial intermediate ID photograph to obtain each second initial intermediate ID photograph.

[0070] In some embodiments, a variational autoencoder (VAE) is also introduced. VAE consists of two parts, an encoder and a decoder. The encoder maps the input data to the distribution parameters (usually mean and variance) of a latent space, and the decoder generates data from the distribution of the latent space.

[0071] Optionally, the image restoration model includes: an image defect detection network layer, an encoder, a restoration network layer, and a decoder. Based on this, each first initial intermediate ID photo is input into the image restoration model, and the face area in each first initial intermediate ID photo is restored to obtain each second initial intermediate ID photo, including: inputting each first intermediate ID photo into the image defect detection network layer of the image restoration model, detecting the defect area of ​​each first intermediate ID photo, and generating a mask image of the defect area when the defect area is detected, the mask image is a binary image used to identify the defect area in the image; further, the face image (the original face image, and the features contained in the original face image are considered to be complete and accurate), each first intermediate ID photo and each mask image are input into the encoder, and the encoder uses a multi-layer convolutional neural network layer to extract the mask image in each first intermediate ID photo. The incomplete features contained in the local image corresponding to the intermediate ID photo, and the encoder uses a multi-layer convolutional neural network layer to extract the complete features contained in the local images corresponding to each mask image in the original face image; further, the incomplete features, the complete features, the first intermediate ID photos and the mask images are input into the repair network layer of the image repair model, and the incomplete features of the local images corresponding to the first intermediate ID photos are repaired according to the complete features to obtain the repaired face features; the repaired face features are input into the decoder, and the decoder is used to reconstruct the local face images corresponding to the incomplete areas; the reconstructed local face images are fused with the first intermediate ID photos to obtain the second intermediate ID photos.

[0072] Among them, the image defect detection network layer can be regarded as a Code Attention module, which can use the attention mechanism to enhance the model's ability to capture information about defective areas. Specifically, in order to enable the model to perceive the relative position relationship between different features, relative position encoding is introduced, which helps the model identify features around the defective area and better understand its structure. Among them, the conditional attention mechanism can adjust the attention distribution according to specific conditions (such as the position and size of the defective area), which enables the model to focus more on features related to the defective area in a targeted manner. The multi-head self-attention mechanism can process information at different positions in parallel, allowing the model to capture information from different representation subspaces at the same time, which helps to better understand the context of the defective area. In addition, the Code Attention module can also establish a connection between the encoder and the decoder, using feature maps of different resolutions to provide more comprehensive contextual information, which helps the model capture details of the defective area at different scales.

[0073] Among them, the features provided by the decoder are multi-scale feature representations, and correspondingly, the restored features are also multi-scale feature representations. When using the decoder to generate each second intermediate ID photo, the decoder uses the multi-scale feature representation and the feature sequence generated by the CodeAttention module, and uses a multi-head self-attention mechanism to process information from different representation subspaces in parallel, which helps to capture global context information. The cross-attention layer allows the hidden state of the decoder to interact with the output of the encoder, thereby combining the features extracted by the encoder with the code sequence. The layer normalization and residual connection in the decoder help stabilize the training process and prevent the gradient from disappearing or exploding. The spatial resolution of the feature map is gradually increased through the upsampling layer in the network structure, thereby gradually restoring the details of the image. In addition, the feature map is further refined using a convolutional layer to generate a feature representation of the same size as the original image. Further, the features at different levels are fused using feature fusion technology to enhance the details and quality of the reconstructed image. Finally, the feature map is converted into the final pixel value through a convolutional layer to obtain the second intermediate ID photo. The tanh activation function is usually used to limit the range of pixel values ​​to [-1,1].

[0074] Furthermore, in order to improve the clarity of the ID photo and the similarity with the facial image of the user taken, a Wensheng graph model can be introduced, and each initial ID photo and at least one prompt word corresponding to the target ID photo template of each initial ID photo are input into the image optimization model, and each initial ID photo is refined according to at least one prompt word to obtain each target ID photo of the user. Among them, the Wensheng graph model is used to output an image that conforms to the description of the text information based on the input image and text information after a certain number of iterations. This embodiment does not limit the type of Wensheng graph model, for example, it can be an SD model. In addition, when selecting the SD model, a model that has been generalized after pre-training, adapted to the race of the user and has a high image clarity can be selected, such as the Stable Diffusion XL (SDXL) model. The SDXL model is a new version of the SD model series, which has made significant improvements and optimizations in image generation quality.

[0075] Among them, the text information refers to at least one prompt word corresponding to each target ID photo template, the user's gender and the user's actual needs. At least one prompt word includes at least a positive prompt word and a reverse prompt word. The positive prompt word is a text description or keyword used to guide the model to generate a specific type or style and high-quality image. The reverse prompt word refers to a text description or keyword used to guide the model to avoid generating certain specific features or elements. The reverse prompt word is opposite to the positive prompt word, and the two work together in the generation process of the model to achieve more accurate control of facial features. In addition, this embodiment does not limit the method for obtaining text information. For example, the text information is stored in association with each ID photo template, that is, each ID photo template is associated with the positive prompt word and the reverse prompt word related to the ID photo template.

[0076] In some embodiments, in order to enhance the functionality and flexibility of the text graph model, a plug-in model may be integrated into the text graph model. This embodiment does not specifically limit the type of plug-in model. For example, the plug-in model may be an Instant ID model. The Instant ID model includes a facial feature constraint model and a facial feature extraction model. The facial feature constraint model may be a Controlnet model, and the facial feature extraction model may be an Ipadapter model.

[0077] Based on the above, each initial ID photo and at least one prompt word corresponding to the target ID photo template of each initial ID photo can be further input into the image optimization model, and each initial ID photo is refined according to the at least one prompt word to obtain each target ID photo of the user. Optionally, each initial ID photo and at least one prompt word corresponding to the target ID photo template of each initial ID photo are input into the image optimization model, and each initial ID photo is refined according to the at least one prompt word to obtain each target ID photo of the user, including: obtaining first relative position information of facial features contained in the target facial image of the user; constraining the position of facial features of each initial ID photo using a facial feature constraint model to obtain second relative position information of the facial features after constraint; and inputting each initial ID photo into a facial feature extraction model to obtain facial features of each initial ID photo. The method comprises the steps of: determining the resolution of the target ID photo, creating a latent space of each target ID photo according to the resolution, wherein the vector dimension of the latent space is adapted to the feature space dimension of each target ID photo; using an encoder, mapping the second relative position information of the five senses and the feature information of the five senses of each initial ID photo to the latent space, and obtaining the latent space features of the five senses of each initial ID photo in the latent space; according to at least one prompt word, using a sampler, collecting the features of the five senses adapted to the at least one prompt word from the latent space features of the five senses; using a decoder, decoding the feature vectors of the five senses, and obtaining each target ID photo.

[0078] The above embodiments are mainly aimed at the refined processing of facial features, but the clarity of the skin color and texture of each target ID photo and the similarity of the skin color and texture with the photographed user's facial image are relatively poor.

[0079] In order to solve the technical problem that the clarity of the skin color and texture of the target ID photo and the similarity of the skin color and texture with the photographed user's face image are poor, in this embodiment, it also includes: inputting each target ID photo into the skin color enhancement and magnification model, magnifying each target ID photo according to the magnification factor of the skin color enhancement and magnification model, and enhancing the skin color pixels of each magnified target ID photo to obtain each first intermediate optimized ID photo; obtaining each first redrawing area of ​​each first intermediate optimized ID photo; inputting each first redrawing area into the facial feature extraction model to obtain facial feature feature information contained in each first redrawing area: Using an encoder, the facial feature information contained in each first redrawn area is mapped to each latent space to obtain the latent space features of the facial feature information contained in each first redrawn area in each latent space; according to at least one prompt word, using a sampler, the facial feature features that are adapted to at least one prompt word are collected from the latent space features corresponding to the facial feature information contained in each first redrawn area in each latent space; using a decoder, the facial feature features that are adapted to at least one prompt word are collected from the latent space features corresponding to the facial feature information contained in each first redrawn area in each latent space to be decoded to obtain each redrawn second intermediate optimized ID photo.

[0080] Optionally, each target ID photo is input into a skin color enhancement magnification model, each target ID photo is magnified according to the magnification factor of the skin color enhancement magnification model, and the skin color pixels of each enlarged target ID photo are enhanced to obtain each first intermediate optimized ID photo, including: obtaining image information of the skin color area of ​​the face in each target ID photo, the image information including the first color vector of each pixel point in the skin color area, the first color vector including the first red component color difference value and the first blue component color difference value; calculating the first skin color center area in the skin color area according to the first red component color difference value and the first blue component color difference value; obtaining the face of each target ID photo after the skin color enhancement magnification model is enlarged Image information of the skin color area of ​​the face, the image information includes the second color vector of each pixel in the skin color area, the second color vector includes the second red component color difference value and the second blue component color difference value; according to the second red component color difference value and the second blue component color difference value contained in the second color component, the second skin color center area in the skin color area is calculated; according to the first red component color difference value, the first blue component color difference value, the first skin color center area and the second red component color difference value, the second blue component color difference value, the second skin color center area, the offset of the first color vector and the second color vector of each pixel in the two skin color center areas is calculated; according to the offset, the image is subjected to skin color enhancement processing. Thus, the selection of the skin color center area in the dynamic skin color model is set, so that the human eye's perception of color difference in the selected skin color center area truly reflects the real skin color in the current scene, so that the processing method has a good skin color enhancement effect and has wide applicability.

[0081] In order to improve the clarity of each first intermediate optimized ID photo, the second redrawn area of ​​each second intermediate optimized ID photo can also be obtained; each second redrawn area is input into a facial feature extraction model to obtain facial feature information contained in each second redrawn area: using an encoder, the facial feature information contained in each second redrawn area is mapped to each latent space to obtain the latent space features of the facial feature information contained in each second redrawn area in each latent space; according to at least one prompt word, using a sampler, the facial feature features that are adapted to at least one prompt word are collected from the latent space features corresponding to the facial feature information contained in each second redrawn area in each latent space; using a decoder, the facial feature features that are adapted to at least one prompt word are collected from the latent space features corresponding to the facial feature information contained in each second redrawn area in each latent space to obtain each redrawn optimized ID photo.

[0082] In addition, it should be noted that a sampler can also be introduced in the above embodiments. In image processing, the sampler can select or extract a specific part from an image or a set of images. When processing face images, the DPM++2M Karras sampler can be selected. Samplers have a variety of functions, such as data sampling: in machine learning, samplers are used to select a portion of data from a large data set for training or verification to improve the efficiency and performance of the model algorithm; feature point sampling: in image feature extraction, samplers can be used to select key points or feature points, which are very important in image recognition and matching; image region selection: in image segmentation or object detection tasks, samplers can be used to select regions of interest for more detailed processing; image fusion: in image synthesis or fusion, samplers may be used to select content from different images and merge them into a new image; image super-resolution: in image super-resolution technology, samplers are used to extract feature information from low-resolution images to generate higher-resolution images; image denoising: samplers can select key information in the image during the denoising process to reduce the impact of noise on image quality; image style transfer: in style transfer tasks, samplers can be used to select and apply features of a specific style to the target image; image generation: when using a generative model, samplers may be used to sample from the latent space to generate a new image.

[0083] At this point, the resume generation system has completed the execution process of the resume generation method. On the one hand, it is not necessary to collect multiple face images of the target object before image processing to obtain a high-definition target ID photo, and the overall similarity between the target ID photo and the original photo can be improved. On the other hand, on the basis of generating each target ID photo adapted to each job position, the user's resume for each job position can be generated based on the user's personal identity information, at least one job position, and the target ID photo related to each job position, and at least part of the work experience, which can reduce the time and effort required for preparing a resume and improve the efficiency of preparing a resume.

[0084] Figure 2 The following is a flow chart of a resume generation method provided by an exemplary embodiment of the present application. Figure 1 As shown, the resume generation method is applied to the server, and the method includes:

[0085] 201. Receive a resume generation request initiated by a user terminal, and based on the resume generation request, obtain basic information of the user, the basic information at least including: personal identity information, job information and facial image of the user, the job information at least including at least one job and work experience, the facial image including initial facial feature information of the user;

[0086] 202. Identify the gender attribute of the user based on the initial facial feature information contained in the facial image;

[0087] 203. According to the gender attribute of the user and at least one job position to be applied for, select a target ID photo template for each job position from a plurality of candidate ID photo templates that are adapted to the gender attribute of the user;

[0088] 204. Perform image processing on the initial facial feature information and each target ID photo template to generate each initial ID photo of the user;

[0089] 205. Input at least one initial ID photo and at least one prompt word corresponding to a target ID photo template of the at least one initial ID photo into an image optimization model, and perform fine processing on each initial ID photo according to the at least one prompt word to obtain each target ID photo of the user;

[0090] 206. Determine at least part of the work experience related to each applied position based on at least one applied position and work experience;

[0091] 207. Generate a resume of the user for each job position based on the user's personal identity information, at least one job position, a target ID photo related to each job position, and at least part of the work experience.

[0092] In an optional embodiment, based on a resume generation request, basic information of the user is obtained, including: parsing the resume generation request to obtain text, pictures and / or videos containing the basic information of the user, a resume generation page is displayed on the user end, the resume generation page at least includes a basic information acquisition control, the text, pictures and / or videos are uploaded by the user through the basic information acquisition control; the basic information of the user is identified from the text, pictures and / or videos.

[0093] In another optional embodiment, based on a resume generation request, obtaining the user's basic information includes: receiving a resume generation request sent by a user terminal; responding to the resume generation request, obtaining text, pictures and / or videos containing user information from the user terminal, wherein the user terminal displays a resume generation page, and the resume generation page at least includes a basic information acquisition control, and the text, pictures and / or videos are uploaded by the user through the basic information acquisition control; obtaining the user's basic information from the text, pictures and / or videos.

[0094] In an optional embodiment, the gender attribute of the user is identified based on the initial facial feature information contained in the facial image, including: inputting the facial image into the feature extraction network layer in the face recognition model to extract the facial features to obtain the initial facial feature information; inputting the initial facial feature information into the gender classification network layer in the face recognition model to perform gender classification to obtain the gender attribute of the user.

[0095] In another optional embodiment, the gender attribute of the user is identified based on the initial facial feature information contained in the facial image, including: inputting the facial image into a semantic segmentation model for semantic segmentation to obtain a binary image containing the facial feature area; obtaining a local image of the facial feature area based on the target facial image and the binary image, the local image being a partial image of the target facial image; inputting the local image into a feature extraction network layer in the facial recognition model to extract facial features to obtain the facial feature information contained in the local image; inputting the facial feature information contained in the local image into the gender classification network layer in the facial recognition model for gender classification to obtain the gender attribute of the user.

[0096] In an optional embodiment, a target ID photo template is selected from candidate ID photo templates based on the user's gender attribute and at least one job position applied for, including: determining a candidate ID photo template that matches the user's gender attribute based on the user's gender attribute, and sending the candidate ID photo template to a user terminal so that the user terminal can display the candidate ID photo template to the user; and receiving a selection request sent by the user terminal in response to the user's selection operation, and determining any candidate ID photo template selected by the user as the target ID photo template based on the selection request.

[0097] In another optional embodiment, a target ID photo template is selected from candidate ID photo templates based on the user's gender attribute and at least one job position applied for, including: obtaining the user's template requirement information; determining, based on the user's gender attribute, a candidate ID photo template that matches the user's gender attribute; and selecting, from the candidate ID photo templates, an ID photo template that matches the user's template requirement information as the target ID photo template.

[0098] In some embodiments, based on at least one job position and work experience, at least part of the work experience related to each job position is determined, including: obtaining work experience descriptions related to each job position from a resume database; based on the work experience descriptions related to each job position, selecting work experience from the user's work experience whose semantic similarity with the work experience descriptions related to each job position meets a preset threshold, as at least part of the work experience related to each job position.

[0099] In some embodiments, a resume of the user for each job position is generated based on the user's personal identity information, at least one job position applied for, a target ID photo related to each job position applied for, and at least part of the work experience, including: according to each job position applied for, obtaining a target resume template adapted to each job position applied for, the target resume template having a resume format; according to the resume format corresponding to each job position applied for, adding the user's personal identity information, at least one job position applied for, a target ID photo related to each job position applied for, and at least part of the work experience to the corresponding position of the target resume template adapted to each job position applied for, thereby generating a resume of the user for each job position applied for.

[0100] Furthermore, a viewing request for a target resume sent by a user terminal can also be received. The user terminal displays a resume list of users, and the resume list at least includes viewing controls for each resume. The viewing request for the target resume is generated in response to a trigger operation of the user on the viewing control of the target resume; the target resume is sent to the user terminal for the user to view; a modification, addition and / or deletion request for the target resume sent by the user terminal is received. The target resume includes a content editing control. The modification, addition and / or deletion request for the target resume is generated in response to an input operation of the user on the content editing control in an editable state; based on the modification, addition and / or deletion request, the first target content is modified, the second target content is added and / or the third target content is deleted to obtain an updated target resume; the updated target resume is sent to the user terminal for the user to view.

[0101] Furthermore, a delivery request for a target resume sent by a user terminal may be received, wherein the delivery request includes a target job position corresponding to the target resume; and the target resume is delivered to a recruiter recruiting for the target job position according to the target job position.

[0102] The detailed implementation methods and beneficial effects of each step provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0103] Figure 3 The following is a flow chart of another resume generation method provided by another exemplary embodiment of the present application. Figure 3 , the method is applied to a user terminal, and the method comprises:

[0104] 301. Displaying a resume generation page, which at least includes a basic information acquisition control, and the basic information acquisition control is used to provide the user with a function of editing basic information, wherein the basic information includes the user's personal identity information, position information, and face image, wherein the position information includes at least one applied position and work experience, and the face image includes the user's initial facial features information;

[0105] 302. In response to the user completing the basic information editing operation based on the basic information acquisition control, a resume generation request is sent to the server to request the server to generate at least one target ID photo based on the facial feature information and at least one job position, and to request the server to generate a resume of the user for each job position based on the user's personal identity information, at least one job position, the target ID photo related to each job position, and at least part of the work experience.

[0106] Furthermore, the user's resume list can also be displayed, and the resume list has viewing controls for each resume; in response to the user's trigger operation on the target viewing control, the target resume associated with the target viewing control is displayed, and the target resume has a content editing control displayed; in response to the user's selection operation on the editable state of the content editing control, the state of the target resume is switched to an editable state; in response to the user's modification, addition and / or deletion operations on the target resume, the modified, added and / or deleted target resume is displayed.

[0107] The detailed implementation methods and beneficial effects of each step provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0108] Figure 4 This is a schematic diagram of the structure of a resume generation device provided by an exemplary embodiment of the present application. Figure 4 As shown, including:

[0109] The acquisition module 41 is used to receive a resume generation request initiated by the user terminal, and based on the resume generation request, acquire the basic information of the user, the basic information at least includes: the user's personal identity information, job information and face image, the job information at least includes at least one job and work experience, and the face image includes the user's initial facial features information;

[0110] The recognition module 42 is used to recognize the gender attribute of the user based on the initial facial features information contained in the face image;

[0111] A selection module 43, configured to select a target ID photo template for each job position from a plurality of candidate ID photo templates adapted to the user's gender attribute according to the user's gender attribute and at least one job position;

[0112] The first generating module 44 is used to perform image processing on the initial facial features information and each target ID photo template to generate each initial ID photo of the user;

[0113] The optimization module 45 is used to input at least one initial ID photo and at least one prompt word corresponding to the target ID photo template of the at least one initial ID photo into the image optimization model, and perform fine processing on each initial ID photo according to the at least one prompt word to obtain each target ID photo of the user;

[0114] A determination module 46, configured to determine at least part of the work experience related to each applied position based on at least one applied position and work experience;

[0115] The second generating module 47 is used to generate a resume of the user for each job position according to the user's personal identity information, at least one job position, a target ID photo related to each job position, and at least part of the work experience.

[0116] In an optional embodiment, when the acquisition module obtains the basic information of the user based on the resume generation request, it is specifically used to: parse the resume generation request to obtain text, pictures and / or videos containing the basic information of the user, and the user end displays a resume generation page, which at least includes a basic information acquisition control, and the text, pictures and / or videos are uploaded by the user through the basic information acquisition control; identify the basic information of the user from the text, pictures and / or videos.

[0117] In another optional embodiment, when the acquisition module acquires the user's basic information based on a resume generation request, it is specifically used to: receive a resume generation request sent by a user terminal; respond to the resume generation request, and acquire text, pictures and / or videos containing user information from the user terminal, wherein the user terminal displays a resume generation page, and the resume generation page at least includes a basic information acquisition control, and the text, pictures and / or videos are uploaded by the user through the basic information acquisition control; and acquire the user's basic information from the text, pictures and / or videos.

[0118] In an optional embodiment, when the recognition module identifies the gender attribute of the user based on the initial facial feature information contained in the facial image, it is specifically used to: input the facial image into the feature extraction network layer in the face recognition model to extract the facial features to obtain the initial facial feature information; input the initial facial feature information into the gender classification network layer in the face recognition model to perform gender classification to obtain the gender attribute of the user.

[0119] In another optional embodiment, when the recognition module identifies the gender attribute of the user based on the initial facial feature information contained in the facial image, it is specifically used to: input the facial image into a semantic segmentation model for semantic segmentation to obtain a binary image containing the facial feature area; obtain a local image of the facial feature area based on the target facial image and the binary image, the local image being a partial image of the target facial image; input the local image into the feature extraction network layer in the facial recognition model to extract facial features to obtain the facial feature information contained in the local image; input the facial feature information contained in the local image into the gender classification network layer in the facial recognition model for gender classification to obtain the gender attribute of the user.

[0120] In an optional embodiment, when the selection module selects a target ID photo template from candidate ID photo templates according to the gender attribute of the user and at least one job position, the selection module is specifically used to: determine a candidate ID photo template that matches the gender attribute of the user according to the gender attribute of the user, and send the candidate ID photo template to the user terminal so that the user terminal can display the candidate ID photo template to the user; and receive a selection request sent by the user terminal in response to a selection operation of the user, and determine any candidate ID photo template selected by the user as the target ID photo template according to the selection request;

[0121] In another optional embodiment, when the selection module selects a target ID photo template from candidate ID photo templates based on the user's gender attribute and at least one applied position, it is specifically used to: obtain the user's template requirement information; determine the candidate ID photo template that matches the user's gender attribute based on the user's gender attribute; and select an ID photo template that matches the user's template requirement information from the candidate ID photo templates as the target ID photo template.

[0122] In some embodiments, when the determination module determines at least part of the work experience related to each job applied for based on at least one job applied for and work experience, it is specifically used to: obtain work experience descriptions related to each job applied for from a resume database; based on the work experience descriptions related to each job applied for, select work experience from the user's work experience whose semantic similarity with the work experience descriptions related to each job applied for meets a preset threshold, as at least part of the work experience related to each job applied for.

[0123] In some embodiments, when the generation module generates a resume of a user for each job application based on the user's personal identity information, at least one job application, target ID photos related to each job application, and at least part of the work experience, the generation module is specifically used to: obtain a target resume template adapted to each job application based on each job application, and the target resume template has a resume format; according to the resume format corresponding to each job application, add the user's personal identity information, at least one job application, target ID photos related to each job application, and at least part of the work experience to the corresponding position of the target resume template adapted to each job application, and generate a resume of the user for each job application.

[0124] Furthermore, the device is also used to: receive a viewing request for a target resume sent by a user terminal, the user terminal displays a resume list of users, the resume list at least includes viewing controls for each resume, the viewing request for the target resume is generated in response to a trigger operation of the user on the target resume viewing control; send the target resume to the user terminal for the user to view; receive a modification, addition and / or deletion request for the target resume sent by the user terminal, the target resume includes a content editing control, the modification, addition and / or deletion request for the target resume is generated in response to a user input operation on the content editing control in an editable state; based on the modification, addition and / or deletion request, modify the first target content, add the second target content and / or delete the third target content to obtain an updated target resume; send the updated target resume to the user terminal for the user to view.

[0125] Furthermore, the device is also used to: receive a delivery request for a target resume sent by a user terminal, the delivery request including a target job position corresponding to the target resume; and deliver the target resume to a recruiter recruiting for the target job position according to the target job position.

[0126] Furthermore, when the generation module performs image processing on the initial facial feature information and each target ID photo template respectively to generate each initial ID photo of the user, it is specifically used to: input the initial facial feature information and each target ID photo template into an image fusion model, fuse the initial facial feature information into each target ID photo template to obtain each intermediate ID photo; input each intermediate ID photo into an image restoration model, repair the face area in each intermediate ID photo to obtain each initial ID photo of the user.

[0127] Furthermore, the Wenshengtu model is integrated with a plug-in model, which includes a facial feature constraint model and a facial feature extraction model; when the generation module inputs each initial ID photo and at least one prompt word corresponding to the target ID photo template of each initial ID photo into the image optimization model, and refines each initial ID photo according to at least one prompt word to obtain each target ID photo of the user, it is specifically used to: obtain first relative position information of facial features contained in the target face image of the user; input the first relative position information of facial features and each initial ID photo into the facial feature constraint model, constrain the position of facial features of each initial ID photo based on the first relative position information of facial features, and obtain second relative position information of facial features after constraint; and input each initial ID photo into the facial feature extraction model. , to obtain the facial feature information of each initial ID photo; determine the resolution of each target ID photo, create the latent space of each target ID photo according to the resolution of each target ID photo, and the vector dimension of each latent space is adapted to the feature space dimension of each target ID photo; use the encoder to map the second relative position information of the facial features and the facial feature information of each initial ID photo to the respective latent space, and obtain the latent space features of the facial features of each initial ID photo in the respective latent space; according to at least one prompt word, use the sampler to collect the facial feature features adapted to at least one prompt word from the latent space features of the facial features of the respective latent space, and obtain at least one facial feature adapted to at least one prompt word; use the decoder to decode the facial feature features adapted to at least one prompt word, and obtain each target ID photo of the user.

[0128] The detailed implementation and beneficial effects of each module provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0129] Figure 5 The following is a flow chart of another resume generation method provided by another exemplary embodiment of the present application. Figure 3 , the method is applied to a user terminal, and the method comprises:

[0130] A display module 51 is used to display a resume generation page. The resume generation page at least includes a basic information acquisition control. The basic information acquisition control is used to provide the user with a function of editing basic information. The basic information includes the user's personal identity information, job information and face image. The job information includes at least one job and work experience. The face image includes the user's initial facial features information.

[0131] The sending module 52 is used to respond to the user's completion of the basic information editing operation based on the basic information acquisition control, and send a resume generation request to the server to request the server to generate at least one target ID photo based on the facial feature information and at least one job application, and request the server to generate a resume of the user for each job application based on the user's personal identity information, at least one job application, and the target ID photo related to each job application, and at least part of the work experience.

[0132] Furthermore, the user's resume list can also be displayed, and the resume list has viewing controls for each resume; in response to the user's trigger operation on the target viewing control, the target resume associated with the target viewing control is displayed, and the target resume has a content editing control displayed; in response to the user's selection operation on the editable state of the content editing control, the state of the target resume is switched to an editable state; in response to the user's modification, addition and / or deletion operations on the target resume, the modified, added and / or deleted target resume is displayed.

[0133] The detailed implementation and beneficial effects of each module provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0134] Figure 6 The following is a schematic diagram of the structure of an electronic device provided by an exemplary embodiment of the present application. Figure 6 As shown, it includes: a memory 60a and a processor 60b; the memory 60a is used to store computer programs; the processor 60b is coupled to the memory 60a and is used to execute the computer programs to perform the steps in the above methods.

[0135] Furthermore, if Figure 6 As shown, the electronic device also includes: a communication component 60c, a display 60d, a power component 60e, an audio component 60f and other components. Figure 6 Only some components are shown schematically, which does not mean that the electronic device only includes Figure 6 Components shown.

[0136] The detailed implementation and beneficial effects of the electronic device provided in the embodiments of the present application have been described in detail in the aforementioned embodiments and will not be elaborated here.

[0137] The exemplary embodiments of the present application further provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor is caused to implement the steps in the above-mentioned method embodiments.

[0138] An exemplary embodiment of the present application further provides a computer program product, which includes a computer program / instructions. When the computer program / instructions are executed by a processor, the processor is enabled to implement the steps in the above-mentioned method embodiments.

[0139] The above-mentioned memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static 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), magnetic storage, flash memory, magnetic disk or optical disk.

[0140] The above-mentioned communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (Ultra Wide Band, UWB) technology, Bluetooth (BlueTooth, BT) technology and other technologies.

[0141] The above-mentioned display includes a screen, and the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0142] The power supply assembly provides power to various components of the device where the power supply assembly is located. The power supply assembly may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device where the power supply assembly is located.

[0143] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, compact disk read-only memory (Compact Disk Read-Only Memory, CD-ROM), optical storage, etc.) that contain computer-usable program code.

[0144] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0147] In a typical configuration, a computing device includes one or more processors (Central Processing Unit, CPU), input / output interface, network interface and memory.

[0148] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash memory (flashRAM). The memory is an example of a computer-readable medium.

[0149] Computer-readable media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0150] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0151] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A resume generation method, characterized in that: Applied to the server, the method includes: Receive a resume generation request initiated by a user terminal, and based on the resume generation request, obtain basic information of the user, wherein the basic information includes at least personal identity information, job information, and a facial image of the user, wherein the job information includes at least at least one job and work experience, and the facial image includes initial facial feature information of the user; Identifying the gender attribute of the user according to the initial facial feature information contained in the facial image; According to the gender attribute of the user and the at least one job position, selecting a target ID photo template for each job position from a plurality of candidate ID photo templates adapted to the gender attribute of the user; Performing image processing on the initial facial feature information and each target ID photo template respectively to generate each initial ID photo of the user; Inputting the at least one initial ID photo and at least one prompt word corresponding to the target ID photo template of the at least one initial ID photo into the image optimization model, and performing fine processing on each initial ID photo according to the at least one prompt word to obtain each target ID photo of the user; Determine at least part of the work experience related to each of the applied positions according to the at least one applied position and the work experience; A resume of the user for each job position is generated based on the user's personal identity information, at least one job position, a target ID photo related to each job position, and at least part of the work experience.

2. The method according to claim 1, characterized in that Based on the resume generation request, basic information of the user is obtained, including: Parsing the resume generation request to obtain text, pictures and / or videos containing basic information of the user, wherein the user terminal displays a resume generation page, wherein the resume generation page at least contains a basic information acquisition control, and the text, pictures and / or videos are uploaded by the user through the basic information acquisition control; identifying the basic information of the user from the text, pictures and / or videos; or, Receive a resume generation request sent by the user terminal; respond to the resume generation request, obtain text, pictures and / or videos containing the user information from the user terminal, the user terminal displays a resume generation page, the resume generation page at least contains a basic information acquisition control, the text, pictures and / or videos are uploaded by the user through the basic information acquisition control; obtain the basic information of the user from the text, pictures and / or videos.

3. The method according to claim 1, characterized in that Identifying the gender attribute of the user according to the initial facial feature information contained in the facial image includes: Input the face image into the feature extraction network layer in the face recognition model to extract the facial features, so as to obtain the initial facial feature information; input the initial facial feature information into the gender classification network layer in the face recognition model to perform gender classification, so as to obtain the gender attribute of the user; or, The facial image is input into a semantic segmentation model for semantic segmentation to obtain a binary image containing facial features; a local image of the facial features is obtained based on the target facial image and the binary image, wherein the local image is a partial image of the target facial image; the local image is input into a feature extraction network layer in a facial recognition model to extract facial features to obtain facial feature information contained in the local image; the facial feature information contained in the local image is input into a gender classification network layer in the facial recognition model for gender classification to obtain the gender attribute of the user.

4. The method according to claim 1, characterized in that: Selecting a target ID photo template from candidate ID photo templates according to the gender attribute of the user and the at least one job position, including: Determine, according to the gender attribute of the user, a candidate ID photo template that is adapted to the gender attribute of the user, and send the candidate ID photo template to the user terminal, so that the user terminal can display the candidate ID photo template to the user; and receive a selection request sent by the user terminal in response to a selection operation of the user, and determine, according to the selection request, any candidate ID photo template selected by the user as a target ID photo template; or, Acquire the template requirement information of the user; determine, based on the gender attribute of the user, a candidate ID photo template that matches the gender attribute of the user; and select, from the candidate ID photo templates, an ID photo template that matches the template requirement information of the user as the target ID photo template.

5. The method according to claim 1, characterized in that Determining at least part of the work experience related to each of the applied positions according to the at least one applied position and the work experience includes: Obtaining work experience descriptions related to each job position from a resume database; According to the work experience descriptions related to the job positions, work experience whose semantic similarity with the work experience descriptions related to the job positions meets a preset threshold is selected from the user's work experience as at least part of the work experience related to the job positions.

6. The method according to claim 1, characterized in that Generating a resume of the user for each job position according to the user's personal identity information, at least one job position, a target ID photo related to each job position, and at least part of the work experience, including: According to the job positions, a target resume template adapted to the job positions is obtained, wherein the target resume template has a resume format; According to the resume format corresponding to each job position, the user's personal identity information, at least one job position, the target ID photo related to each job position, and at least part of the work experience are added to the corresponding position of the target resume template adapted to each job position, and the user's resume for each job position is generated.

7. The method according to claim 1, characterized in that Also includes: Receiving a viewing request for a target resume sent by the user terminal, the user terminal displays a resume list of the user, the resume list at least including a viewing control for each resume, the viewing request for the target resume is generated in response to a trigger operation of the user on the viewing control for the target resume; sending the target resume to the user terminal for the user to view; Receiving a modification, addition and / or deletion request for the target resume sent by the user end, the target resume includes a content editing control, and the modification, addition and / or deletion request for the target resume is generated in response to the user's input operation on the content editing control in an editable state; based on the modification, addition and / or deletion request, modifying the first target content, adding the second target content and / or deleting the third target content, to obtain an updated target resume; The updated target resume is sent to the user terminal for the user to view.

8. The method according to any one of claims 1 to 7, characterized in that Also includes: Receiving a delivery request for a target resume sent by the user end, wherein the delivery request includes a target job position corresponding to the target resume; According to the target job position, the target resume is delivered to the recruiter of the target job position.

9. The method according to claim 1, characterized in that: The initial facial feature information is subjected to image processing with each target ID photo template to generate each initial ID photo of the user, including: Inputting the initial facial feature information and the target ID photo templates into an image fusion model, and fusing the initial facial feature information into the target ID photo templates to obtain intermediate ID photos; The intermediate ID photos are input into the image restoration model, and the face area in each intermediate ID photo is restored to obtain each initial ID photo of the user.

10. The method according to claim 1, characterized in that Also includes: A Wensheng graph model, wherein the Wensheng graph model is integrated with a plug-in model, wherein the plug-in model includes a facial feature constraint model and a facial feature extraction model; Inputting each of the initial ID photos and at least one prompt word corresponding to the target ID photo template of each of the initial ID photos into an image optimization model, and performing fine processing on each of the initial ID photos according to the at least one prompt word to obtain each of the target ID photos of the user, including: Acquire first relative position information of facial features contained in a target facial image of the user; Inputting the first relative position information of the facial features and the initial ID photos into the facial feature constraint model, constraining the positions of the facial features of the initial ID photos based on the first relative position information of the facial features to obtain second relative position information of the facial features after being constrained; and inputting the initial ID photos into the facial feature extraction model to obtain facial feature information of the initial ID photos; Determine the resolution of each target ID photo, and create a latent space of each target ID photo according to the resolution of each target ID photo, wherein the vector dimension of each latent space is adapted to the feature space dimension of each target ID photo; Mapping the second relative position information of the facial features and the facial feature information of each of the initial ID photos to respective latent spaces using an encoder to obtain latent space features of the facial features of each of the initial ID photos in the respective latent spaces; According to the at least one prompt word, using a sampler, collect facial features that match the at least one prompt word from the latent space features of the facial features in the respective latent spaces, to obtain at least one facial feature that matches the at least one prompt word; The facial features matched with the at least one prompt word are decoded by using a decoder to obtain target ID photos of the user.

11. A resume generation method, characterized in that: Applied to a user terminal, the method includes: Displaying a resume generation page, the resume generation page at least comprising a basic information acquisition control, the basic information acquisition control being used to provide the user with a function of editing basic information, the basic information comprising the user's personal identity information, position information and face image, the position information comprising at least one applied position and work experience, the face image comprising initial facial feature information of the user; In response to the user completing the basic information editing operation based on the basic information acquisition control, a resume generation request is sent to the server to request the server to generate at least one target ID photo based on the facial feature information and the at least one job applied for, and to request the server to generate a resume of the user for each job applied for based on the user's personal identity information, at least one job applied for, the target ID photo related to each job applied for, and at least part of the work experience.

12. The method according to claim 11, characterized in that Also includes: Displaying a resume list of the user, wherein the resume list has a viewing control for each resume; In response to a user triggering operation on a target viewing control, displaying a target resume associated with the target viewing control, wherein a content editing control is displayed in the target resume; In response to a user's selection operation on the editable state of the content editing control, switching the state of the target resume to an editable state; In response to the user's modification, addition and / or deletion operations on the target resume, the modified, added and / or deleted target resume is displayed.

13. An electronic device, characterized in that: include: Memory and processor; The memory is used to store a computer program; the processor is coupled to the memory and is used to execute the computer program in the memory to implement the steps in the method according to any one of claims 1-10 or 11-12.

14. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is enabled to implement the steps of the method according to any one of claims 1 to 10 or 11 to 12.

15. A computer program product, characterized in that The method comprises a computer program / instruction, which, when executed by a processor, enables the processor to implement the steps of the method according to any one of claims 1 to 10 or 11 to 12.

Citation Information

Patent Citations

  • Image processing method, device, computer equipment and storage medium

    CN113570684A

  • Resume indexing system and method based on human face recognition figure image

    CN116484035A

  • Form filling method and system applied to power grid field and electronic equipment

    CN117057325A

  • Employment information processing method and device, electronic equipment and storage medium

    CN117709916A

  • Identification photo generation method and device, electronic equipment and storage medium

    CN118430052A

Cited By

  • Image processing and identification photo generation method and device, storage medium and program product

    CN119006636A

  • Image processing and identification photo generation method and device, storage medium and program product

    CN119006636B

  • Identification photo generation method and electronic equipment

    CN120526003A

  • A method for generating an ID photo and an electronic device

    CN120526003B