阅读说明：本技术 一种基于人工智能的简历自动编辑系统及方法 (Automatic resume editing system and method based on artificial intelligence ) 是由 梁蓓蓓 潘虹男 闫涵 张力 朱玮 于 2021-09-26 设计创作，主要内容包括：本发明公开了一种基于人工智能的简历自动编辑系统及方法,包括简历数据处理系统和用户系统；其中,简历数据处理系统包括预处理模块,对简历数据预处理获得标准简历文本和非标准简历文本；还包括模型训练模块,将标准简历文本进行训练得到数据模型；数据分类模块,对非标准简历文本进行识别分类的数据分类模块；自动编辑模块,对分类完成的简历文本自动编辑形成标准简历数据。用户系统包括用于记录用户身份及相关信息的注册及登录模块、用于对简历导出文件模板进行设置的简历模板设置模块、用于对用户输入的非标准简历数据转换为标准简历数据的简历内容转换模块和用于将用户确认后的标准简历数据按预设简历模板导出为简历文件的简历导出模块。(The invention discloses an automatic resume editing system and method based on artificial intelligence, which comprises a resume data processing system and a user system; the resume data processing system comprises a preprocessing module, a data processing module and a data processing module, wherein the preprocessing module is used for preprocessing resume data to obtain a standard resume text and a non-standard resume text; the model training module is used for training the standard resume text to obtain a data model; the data classification module is used for identifying and classifying the non-standard resume text; and the automatic editing module is used for automatically editing the classified resume texts to form standard resume data. The user system comprises a registration and login module for recording the identity of a user and related information, a resume template setting module for setting a resume exporting file template, a resume content conversion module for converting non-standard resume data input by the user into standard resume data, and a resume exporting module for exporting the standard resume data confirmed by the user into a resume file according to a preset resume template.)

1. An automatic resume editing system based on artificial intelligence is characterized by comprising a resume data processing system and a user system; wherein the content of the first and second substances,

the resume data processing system comprises: the system comprises a preprocessing module, a model training module, a data prediction module and an automatic editing module;

the preprocessing module is used for splitting the resume data into a plurality of resume texts and removing interference information to obtain preprocessed resume texts; the method comprises the steps of including standard resume texts and non-standard resume texts;

the model training module is used for training the preprocessed standard resume text to obtain a data model;

the data classification module is used for identifying and classifying the preprocessed non-standard resume text based on the data model;

the automatic editing module is used for automatically editing the classified resume texts to form standard resume data;

the user system includes: the system comprises a registration and login module, a resume template setting module, a resume content conversion module and a resume export module;

the registration and login module records the user identity and related information;

the resume template setting module is used for setting a resume template for exporting resume files;

the resume content conversion module is used for converting non-standard resume data input by a user into standard resume data and feeding the converted standard resume data back to the user for confirmation;

and the resume exporting module exports the confirmed standard resume data into a resume file according to a preset resume template.

2. The system of claim 1, wherein the preprocessing module comprises:

the identification unit is used for acquiring the resume data collected in advance and identifying the attributes of the resume data, wherein the attributes comprise standard resume data and non-standard resume data;

the first preprocessing unit is used for carrying out data splitting on the standard resume data and labeling the standard resume data for classification to obtain a standard resume text;

the second preprocessing unit is used for carrying out data splitting on the non-standard resume data to obtain a non-standard resume text;

the filtering unit deletes the interference information in the standard resume text and the non-standard resume text;

the first definition unit is used for taking the standard resume text after the interference information is deleted as training data of the data model;

and the second definition unit is used for taking the non-standard resume text after the interference information is deleted as the data to be classified of the data model.

3. The system of claim 2, wherein the system comprises:

the resume data is text data corresponding to a complete resume;

the resume text is text data obtained by splitting the resume data according to a predefined rule.

4. The system of claim 1, wherein the data model training module comprises:

the model construction unit is used for training the standard resume text to obtain an initial data model;

after the user system is applied, the data model is updated iteratively according to data fed back by the user;

the data classification module comprises:

and the data classification unit is used for identifying and classifying the non-standard resume texts according to the data model to obtain the resume texts with unified classification identifiers.

5. The system of claim 1, wherein the automatic editing module comprises:

the editing unit automatically edits the resume text carrying the uniform classification identification based on a predefined editing rule to form standard resume data;

the predefined editing rules comprise a classification display sequence and a resume text display sequence.

6. The system of claim 1, wherein the login and registration module comprises:

the recording unit is used for recording the user identity and the use record thereof;

and the setting unit is used for setting corresponding use help and incentive measures according to the user identity and the user use record.

7. The system of claim 1, wherein the resume template setup module comprises:

the user-defined unit is used for selecting corresponding formats and contents in a system preset range and generating a user-defined resume template according to the selected formats and contents;

the resume content conversion module comprises:

the deleting unit deletes the special symbols or the standard resume data of the nonstandard classified information in the resume data conversion process;

the modification unit is used for adjusting the converted standard resume data to obtain resume data confirmed by a user;

and the display unit provides a user application interface, displays the comparison of the resume contents before and after the content conversion, and stores the resume data confirmed by the user.

8. An artificial intelligence based automatic resume editing method applied to the artificial intelligence based automatic resume editing system as claimed in any one of claims 1 to 8, wherein the method comprises the following steps:

preprocessing resume data;

performing data training on the standard resume text obtained through preprocessing to obtain a data model;

based on the data model, carrying out classification recognition on the non-standard resume text obtained through preprocessing, and automatically editing the resume text after classification recognition to form standard resume data;

and after the automatic conversion of the current resume data from the non-standard resume to the standard resume is completed through an operation interface of the user system, updating the data model according to the actual application feedback.

9. The method of claim 8, wherein the pre-processing resume data comprises:

acquiring pre-collected resume data, and identifying attributes of the resume data, wherein the attributes comprise standard resume data and non-standard resume data;

carrying out data splitting on the standard resume data, and labeling the classification of the standard resume data to obtain a standard resume text;

obtaining a non-standard resume text by performing data splitting on the non-standard resume data;

deleting the interference information in the standard resume text and the non-standard resume text;

taking the standard resume text with the interference information deleted as training data of the data model;

taking the non-standard resume text after the interference information is deleted as the data to be classified of the data model;

wherein the interference information comprises: meaningless special characters, non-standard paragraph symbols, non-standard classification information.

10. The method as claimed in claim 8, wherein the step of classifying and recognizing the preprocessed non-standard resume text based on the data model and automatically editing the classified and recognized resume text to form standard resume data comprises:

identifying and classifying the non-standard resume texts according to the data model to obtain the resume texts with unified classification identifiers; automatically editing the resume text carrying the uniform classification identification based on a predefined editing rule to form standard resume data;

the automatic editing method comprises the following steps: reorganizing the sequence of the resume texts according to the classified display sequence; and the number of the first and second groups,

and sequencing according to the position sequence or time factor of the similar resume texts in the original resume data.

Technical Field

The invention relates to the technical field of artificial intelligence, in particular to a resume automatic editing system and method based on artificial intelligence.

Background

Artificial intelligence techniques have become popular for text recognition. Artificial intelligence: various machine learning, neural networks, deep learning algorithms and models are broadly referred to herein. In particular, based on algorithms, models are derived through data learning and used for classification, ordering and prediction of data.

Resume is key data in the recruitment service process, in actual service, recruiters often need to process resume data in different formats, and resumes in complicated formats have great negative influence on the efficiency of works such as screening, statistics and analysis of resumes in the recruitment process. For example, some resumes place skill information in front, some in back, and some lack this information. When the recruitment process involves a plurality of links, the effect of the non-uniform resume format on the efficiency of the whole recruitment process is larger.

Disclosure of Invention

Aiming at the defects in the prior art, the invention provides a resume automatic editing system and method based on an artificial intelligence technology, aiming at providing a method for sorting resumes in different formats into a designated resume format by utilizing the artificial intelligence technology and providing a solution for improving the efficiency for recruiting related services.

The technical scheme of the invention is as follows:

a resume automatic editing system based on artificial intelligence comprises a resume data processing system and a user system; wherein the content of the first and second substances,

the resume data processing system comprises: the system comprises a preprocessing module, a model training module, a data prediction module and an automatic editing module;

the preprocessing module is used for splitting the resume data into a plurality of resume texts and removing interference information to obtain preprocessed resume texts; the method comprises the steps of including standard resume texts and non-standard resume texts;

the model training module is used for training the preprocessed standard resume text to obtain a data model;

the data classification module is used for identifying and classifying the preprocessed non-standard resume text based on the data model;

the automatic editing module is used for automatically editing the classified resume texts to form standard resume data;

the user system includes: the system comprises a registration and login module, a resume template setting module, a resume content conversion module and a resume export module;

the registration and login module records the user identity and related information;

the resume template setting module is used for setting a resume template for exporting resume files;

the resume content conversion module is used for converting non-standard resume data input by a user into standard resume data and feeding the converted standard resume data back to the user for confirmation;

and the resume exporting module exports the confirmed standard resume data into a resume file according to a preset resume template.

Preferably, the preprocessing module comprises:

the identification unit is used for acquiring the resume data collected in advance and identifying the attributes of the resume data, wherein the attributes comprise standard resume data and non-standard resume data;

the first preprocessing unit is used for carrying out data splitting on the standard resume data and labeling the standard resume data for classification to obtain a standard resume text;

the second preprocessing unit is used for carrying out data splitting on the non-standard resume data to obtain a non-standard resume text;

the filtering unit deletes the interference information in the standard resume text and the non-standard resume text;

the first definition unit is used for taking the standard resume text after the interference information is deleted as training data of the data model;

and the second definition unit is used for taking the non-standard resume text after the interference information is deleted as the data to be classified of the data model.

Furthermore, the resume data is text data corresponding to a complete resume;

the resume text is text data obtained by splitting the resume data according to a predefined rule.

Preferably, the data model training module includes:

the model construction unit is used for training the standard resume text to obtain an initial data model;

and after the user system is applied, the adjusting unit iteratively updates the data model according to the data fed back by the user.

Preferably, the data classification module includes:

and the data classification unit is used for identifying and classifying the non-standard resume texts according to the data model to obtain the resume texts with unified classification identifiers.

Preferably, the automatic editing module includes:

the editing unit automatically edits the resume text carrying the uniform classification identification based on a predefined editing rule to form standard resume data;

the predefined editing rules comprise a classification display sequence and a resume text display sequence.

Preferably, the login and registration module includes:

the recording unit is used for recording the user identity and the use record thereof;

and the setting unit is used for setting corresponding use help and incentive measures according to the user identity and the user use record.

Preferably, the resume template setting module includes:

the user-defined unit is used for selecting corresponding formats and contents in a system preset range and generating a user-defined resume template according to the selected formats and contents;

the resume content conversion module comprises:

the deleting unit deletes the special symbols or the standard resume data of the nonstandard classified information in the resume data conversion process;

the modification unit is used for adjusting the converted standard resume data to obtain resume data confirmed by a user;

and the display unit provides a user application interface, displays the comparison of the resume contents before and after the content conversion, and stores the resume data confirmed by the user.

An artificial intelligence based automatic resume editing method applied to an artificial intelligence based automatic resume editing system as claimed in any one of claims 1 to 8, the method comprising:

preprocessing resume data;

performing data training on the standard resume text obtained through preprocessing to obtain a data model;

based on the data model, carrying out classification recognition on the non-standard resume text obtained through preprocessing, and automatically editing the resume text after classification recognition to form standard resume data;

and after the automatic conversion of the current resume data from the non-standard resume to the standard resume is completed through an operation interface of the user system, updating the data model according to the actual application feedback.

Preferably, the preprocessing the resume data includes:

acquiring pre-collected resume data, and identifying attributes of the resume data, wherein the attributes comprise standard resume data and non-standard resume data;

carrying out data splitting on the standard resume data, and labeling the classification of the standard resume data to obtain a standard resume text;

obtaining a non-standard resume text by performing data splitting on the non-standard resume data;

deleting the interference information in the standard resume text and the non-standard resume text;

taking the standard resume text with the interference information deleted as training data of the data model;

taking the non-standard resume text after the interference information is deleted as the data to be classified of the data model;

wherein the interference information comprises: meaningless special characters, non-standard paragraph symbols, non-standard classification information.

Preferably, the classifying and recognizing the non-standard resume text obtained through the preprocessing based on the data model, and automatically editing the resume text after the classifying and recognizing to form the standard resume data includes:

identifying and classifying the non-standard resume texts according to the data model to obtain the resume texts with unified classification identifiers; automatically editing the resume text carrying the uniform classification identification based on a predefined editing rule to form standard resume data;

the automatic editing method comprises the following steps: reorganizing the sequence of the resume texts according to the classified display sequence; and the number of the first and second groups,

and sequencing according to the position sequence or time factor of the similar resume texts in the original resume data.

The invention has the beneficial effects that:

the invention provides an automatic resume editing system and method based on artificial intelligence, which arranges resumes in different formats into a designated resume format by utilizing an artificial intelligence technology, provides a solution for improving efficiency for recruitment related services, and simultaneously improves user experience of a client for intelligently editing resumes.

Drawings

In order to more clearly illustrate the detailed description of the invention or the technical solutions in the prior art, the drawings that are needed in the detailed description of the invention or the prior art will be briefly described below. Throughout the drawings, like elements or portions are generally identified by like reference numerals. In the drawings, elements or portions are not necessarily drawn to scale.

Fig. 1 is a schematic structural diagram of an automatic resume editing system based on artificial intelligence according to an embodiment of the present invention;

FIG. 2 is a flowchart of a resume data processing procedure according to an embodiment of the present invention;

FIG. 3 is a flowchart of a user-system interaction process method according to an embodiment of the present invention;

fig. 4 is a flowchart of an automatic resume editing method based on artificial intelligence according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and therefore are only examples, and the protection scope of the present invention is not limited thereby.

It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which the invention pertains.

Referring to fig. 1, an embodiment of the present invention provides an automatic resume editing system based on artificial intelligence, including: a resume data processing system and a user system. The resume data processing system comprises a preprocessing module, a model training module, a data classification module and an automatic editing module; the user system comprises a registration and login module, a resume template setting module, a resume content conversion module and a resume exporting module.

The preprocessing module is used for splitting the resume data into a plurality of resume texts and removing interference information; obtaining a preprocessed resume text; the preprocessed resume text comprises a standard resume text and a non-standard resume text; the resume data is text data corresponding to a complete resume, and the resume text is the text data after the resume data is split according to a certain rule;

the preprocessing module needs to process resume data from various sources, including: for standard resume data, data splitting is needed and classification is marked to be used as data model training data; and for the non-standard resume data, performing data splitting without labeling and classifying to serve as data to be classified of the data model.

Specifically, the preprocessing module includes:

the identification unit is used for acquiring the resume data collected in advance and identifying the attributes of the resume data, wherein the attributes comprise standard resume data and non-standard resume data;

the first preprocessing unit is used for carrying out data splitting on the standard resume data and labeling the standard resume data for classification to obtain a standard resume text;

the second preprocessing unit is used for carrying out data splitting on the non-standard resume data to obtain a non-standard resume text;

the filtering unit deletes the interference information in the standard resume text and the non-standard resume text;

the first definition unit is used for taking the standard resume text after the interference information is deleted as training data of the data model;

and the second definition unit is used for taking the non-standard resume text after the interference information is deleted as the data to be classified of the data model.

The following factors need to be considered comprehensively when data are split: 1. resume content order; 2. the resume titles are classified; 3. resume paragraphs and punctuation; 4. resume text length restriction; 5. invalid and nonsense characters are removed.

The model training module is used for training the preprocessed resume text to obtain a data model; the initial data model is obtained according to a large amount of standard resume data, and after the system is applied, the data model is continuously adjusted according to the subsequently supplemented standard resume data and the user use data, so that the model accuracy is improved.

The data model training module comprises:

the model construction unit is used for training the standard resume text to obtain an initial data model;

and after the user system is applied, the adjusting unit iteratively updates the data model according to the data fed back by the user.

The data classification module is used for identifying and classifying the preprocessed resume text according to a data model;

the data classification module comprises: and the data classification unit is used for identifying and classifying the non-standard resume texts according to the data model, and the resume texts with unified classification marks can be obtained after the identification and classification are carried out on the data model.

The resume text data after the data model classification is also verified, and the method comprises the following steps: date of birth, cell phone number, identification number, etc.

And the automatic editing module is used for automatically editing the classified resume texts to form standard resume data.

Specifically, the automatic editing module comprises an editing unit, and the editing unit automatically edits the resume text carrying the uniform classification identifier based on a predefined editing rule to form standard resume data; the automatic editing rule needs to be preset, so the predefined editing rule is the preset automatic editing rule, and includes a classification display sequence, a resume text display sequence, and the like.

In the user system: the registration and login module records the user identity and related information; wherein, through the user identity and the usage record thereof, corresponding usage help and incentive measures can be set.

The login and registration module comprises:

the recording unit is used for recording the user identity and the use record thereof;

and the setting unit is used for setting corresponding use help and incentive measures according to the user identity and the user use record.

The resume template setting module is used for setting a resume export file template; the users can export the resume data by using a resume template preset by the system and can also customize the resume template; when the user self-defines the resume template, the format and the content of the resume template can be set by the user, but the specific format and the content need to be selected in the range appointed by the system. For example, the system appointment resume template is classified as: basic information (name, gender, age, mobile phone number, mailbox, presence or absence of job), educational experience (academic calendar, graduate college, specialty, start and stop time), professional skill, work experience, project experience. The user self-defines the template, can select all the classified information or part of the classified information, and can adjust the sequence of the information of each part in the resume.

The resume template setting module comprises:

the user-defined unit is used for selecting corresponding formats and contents in a system preset range and generating a user-defined resume template according to the selected formats and contents;

the resume content conversion module is used for converting non-standard resume data input by a user into standard resume data and feeding the converted standard resume data back to the user for confirmation;

in the standard resume data content conversion process, original special symbols or non-standard classification information are removed. The resume conversion function provides two multi-line text entry areas: the contents of the original resume and the AI resume are both empty by default; the user copies the resume (non-standard resume) to be converted and pastes the resume into the original resume area, the conversion is determined, the resume after automatic editing is displayed in the AI resume area after the system processes the resume, and the user can directly store the AI resume and can modify the AI resume on the basis of the AI resume.

The resume content conversion module comprises:

the deleting unit deletes the special symbols or the standard resume data of the nonstandard classified information in the resume data conversion process;

the modification unit is used for adjusting the converted standard resume data to obtain resume data confirmed by a user;

and the display unit provides a user application interface, displays the comparison of the resume contents before and after the content conversion, and stores the resume data confirmed by the user.

And the resume exporting module exports the confirmed standard resume data into a resume file according to a preset resume template.

The user can inquire the stored resume data, select the resume data to be exported and confirm, the system exports the resume data into the resume file according to the resume template set by the user, and the user can download the file in the system.

Referring to fig. 2, the specific execution flow is:

the standard resume data is split into standard resume text data through a preprocessing module; obtaining a data model by standard resume text data through a data training module; the non-standard resume data is split into non-standard resume texts through a preprocessing module; forming classified resume texts by the non-standard resume texts through a data classification module; the classified resume text is converted into resume data finished by AI edition through an automatic editing module.

Among these, when comparing the resume data edited by the AI with the standard resume data, there may be the following situations: 1. partial appointed contents of the standard resume are lacked (such as the lack of an identification card number, the lack of academic information and the like); 2. some content repeats or deviations (e.g., educational experiences are included in the work experience, etc.).

Referring to fig. 3, the specific execution flow is:

the system obtains an initial data model by training a certain number of standard resume texts in advance; the system is applied and implemented, the user converts the non-standard resume data into the standard resume data by using the system (the user system provides a front end and a related prompt function; the resume data processing system provides a back end data processing function); and the user confirms the resume data converted by the system or confirms the resume data after modification, and the confirmed resume data can be used as the training data for updating the subsequent data model.

Referring to fig. 4, an embodiment of the present invention further provides an automatic resume editing method based on artificial intelligence, which is applied to the above-mentioned automatic resume editing system based on artificial intelligence, and the method includes:

s101, determining standard resume contents, and splitting a certain number of standard resumes to obtain standard resume texts (model training data);

correspondingly, step S101 corresponds to the step of preprocessing the resume data:

acquiring resume data collected in advance, and identifying attributes of the resume data; and obtaining a standard resume text and deleting the interference information in the standard resume text by splitting the data of the standard resume data and marking the classification of the data.

S102, performing data training on the standard resume text by adopting a selected artificial intelligence technology to obtain a data model;

s103, classifying and identifying the non-standard resume text (obtained by splitting non-standard resume data) through model application; correspondingly, step S103 corresponds to the step of preprocessing the resume data: acquiring pre-collected resume data, identifying attributes of the resume data, splitting data of non-standard resume data to obtain a non-standard resume text, and deleting interference information in the non-standard resume text; taking the non-standard resume text after the interference information is deleted as the data to be classified of the data model;

s104, automatically editing the identified resume text to form a standard resume;

and S105, periodically adding the resume data confirmed by the user into training data, adjusting the training model and improving the model accuracy.

Correspondingly, the steps S102-S105 are to carry out data training on the standard resume text obtained through preprocessing to obtain a data model; based on the data model, carrying out classification recognition on the non-standard resume text obtained through preprocessing, and automatically editing the resume text after classification recognition to form standard resume data;

and after the automatic conversion of the current resume data from the non-standard resume to the standard resume is completed through an operation interface of the user system, updating the data model according to the actual application feedback.

The method comprises the following steps of preprocessing a standard resume text, carrying out classification recognition on the preprocessed non-standard resume text based on a data model, automatically editing the resume text after the classification recognition, and forming standard resume data specifically comprises the following steps:

identifying and classifying the non-standard resume texts according to the data model to obtain the resume texts with unified classification identifiers; and automatically editing the resume text carrying the uniform classification identification based on a predefined editing rule to form standard resume data.

The standard resume data refers to data which meet the preset resume content classification and related requirements; the non-standard resume data refers to other data with a format different from that of the standard resume data.

The automatic editing method comprises the following steps: reorganizing the sequence of the resume texts according to the classified display sequence; and sorting according to the position sequence or time factor of the similar resume texts in the original resume data.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.