CN111737485A - Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning - Google Patents
Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning Download PDFInfo
- Publication number
- CN111737485A CN111737485A CN202010468710.2A CN202010468710A CN111737485A CN 111737485 A CN111737485 A CN 111737485A CN 202010468710 A CN202010468710 A CN 202010468710A CN 111737485 A CN111737485 A CN 111737485A
- Authority
- CN
- China
- Prior art keywords
- information
- matching
- basic data
- post
- resume
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Animal Behavior & Ethology (AREA)
- Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a human-guard matching method and a human-guard matching system based on knowledge graph and deep learning, wherein the human-guard matching method comprises the following steps: s101: acquiring first basic data information of a post to be matched and effective information of the first basic data information; s102: adding effective information into the knowledge graph, processing the information of the knowledge graph and the first basic data information, inputting the processed information into the reasoning model, obtaining a matching score of the selected resume and the post, and obtaining an optimal reasoning model according to the matching score; s103: and processing the second basic data information and the knowledge graph information of the second basic data information, inputting the processed second basic data information and the processed second basic data information into an optimal reasoning model, and acquiring the matching score of the resume data to be selected and the post through the optimal reasoning model. The method can accurately, efficiently and quickly carry out matching, obtain the matching result of the resume and the post, has high efficiency of screening and matching the resume, greatly reduces the time and energy of personnel units and job seekers, and improves the overall management level of enterprise personnel recruitment.
Description
Technical Field
The invention relates to the field of artificial intelligence application, in particular to a human sentry matching method and a human sentry matching system based on knowledge graph and deep learning.
Background
With the continuous development of internet technology, more and more recruitment units for online recruitment and more job seekers for job finding through the internet are provided, and the network recruitment gradually replaces the traditional face-to-face recruitment mode, in particular to a recruitment website, so that the problem of 'difficulty in recruiting talents' and the problem of 'difficulty in job hunting' of job seekers are solved to a certain extent by using the rapid job position searching and recommending technology, the talent searching and recommending technology and the abundant job position resources and talent resources of the recruitment websites.
At present, enterprises usually grab a large amount of resumes meeting the recruitment conditions from the internet by establishing personnel recruitment software, but the resumes are usually messy and do not realize accurate matching and sorting and classification of the recruitment conditions and the resumes, when the enterprises have the recruitment requirements, the enterprises still need to spend a large amount of manpower and time to acquire the resumes from the personnel recruitment software for manual accurate screening, the efficiency of resume screening and matching is slow, a large amount of time and energy are consumed by personnel units and job seekers, and the overall management level of the personnel recruitment of the enterprises is reduced.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a human-post matching method and a human-post matching system based on knowledge maps and deep learning, the knowledge maps are used for describing the relationship between the selected resume data and the post, an inference model is integrated according to the relationship and first basic data for reasoning to obtain an optimal inference model, the optimal inference model is used for obtaining the matching score between the resume data to be selected and the post, the matching can be accurately, efficiently and rapidly carried out, the matching result between the resume and the post is obtained, the efficiency of resume screening and matching is high, the time and the energy of a person using unit and a job seeker are greatly reduced, and the overall management level of enterprise personnel recruitment is improved.
In order to solve the above problems, the present invention adopts a technical solution as follows: a human-sentry matching method based on knowledge graph and deep learning comprises the following steps: s101: acquiring first basic data information of a post to be matched, and extracting effective information related to the post to be matched from the first basic data information, wherein the first basic data information comprises selected resume data, recruitment information of the post and recruitment interaction records; s102: adding the effective information into a knowledge graph, processing the information of the knowledge graph and first basic data information, inputting the processed information into an inference model, obtaining a matching score of the selected resume and the post, and obtaining an optimal inference model according to the matching score; s103: acquiring knowledge graph information of second basic data information, processing the second basic data information and the knowledge graph information, inputting the processed second basic data information and the processed knowledge graph information into the optimal reasoning model, and acquiring matching scores of resume data to be selected and the post through the optimal reasoning model, wherein the second basic data information comprises the first basic data information, the resume data to be selected and the recruitment information of the post corresponding to the resume data to be selected.
Further, the effective information includes a study, a work age, and keywords in project experience.
Further, the recruitment interaction record comprises whether to take, interview and offer.
Further, the step of processing the information of the knowledge graph and the first basic data information and inputting the processed information into the inference model specifically includes: and respectively coding the information of the knowledge graph and the first basic data information and inputting the information into the reasoning model.
Further, the selected resume data is data of the recording resume matched with the position to be matched.
Further, the step of obtaining the optimal inference model according to the matching score specifically includes:
and judging the accuracy of the reasoning model according to the matching score, and optimizing the reasoning model according to the accuracy to obtain the optimal reasoning model.
Further, the inference model is optimized multiple times based on the framework of tensorflow to obtain the best inference model.
Further, the step of obtaining the first basic data information of the post to be matched specifically includes:
and acquiring first basic data information of the same post to be matched of different companies or acquiring first basic data information of the same post to be matched of the same company.
Further, the step of obtaining the matching score between the resume data to be selected and the post through the optimal inference model further includes: and recommending the resume to be selected according to the matching score, and collecting feedback information.
Based on the same inventive concept, the invention also provides a sentry matching system, which comprises a processor and a memory, wherein the processor is connected with the memory: the memory stores first basic data, second basic data and a computer program, and the processor executes the human-sentry matching method based on the knowledge map and the deep learning according to the first basic data, the second basic data and the computer program.
Compared with the prior art, the invention has the beneficial effects that: the method has the advantages that the relation between the selected resume data and the post is described by the knowledge map, the inference model is merged into the inference model according to the relation and the first basic data to perform inference to obtain the optimal inference model, the matching score of the resume data to be selected and the post is obtained through the optimal inference model, matching can be performed accurately, efficiently and rapidly, the matching result of the resume and the post is obtained, resume screening and matching efficiency is high, time and energy of a user unit and a job seeker are greatly reduced, and the overall management level of enterprise personnel recruitment is improved.
Drawings
FIG. 1 is a flow chart of an embodiment of a method for matching a human sentry based on knowledge-graph and deep learning according to the invention;
FIG. 2 is a schematic diagram of an embodiment of obtaining an optimal inference model in the human-job matching method based on knowledge graph and deep learning according to the present invention;
FIG. 3 is a schematic diagram of an embodiment of obtaining a resume to be selected and a post matching condition in the knowledge-graph and deep learning-based human-post matching method of the present invention;
fig. 4 is a block diagram of an embodiment of the inventor post matching system.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
Referring to fig. 1-3, fig. 1 is a flowchart illustrating a method for matching a human job based on knowledge-graph and deep learning according to an embodiment of the present invention; FIG. 2 is a schematic diagram of an embodiment of obtaining an optimal inference model in the human-job matching method based on knowledge graph and deep learning according to the present invention; fig. 3 is a schematic diagram of an embodiment of obtaining a resume to be selected and a post matching condition in the human-post matching method based on knowledge graph and deep learning according to the present invention. The method for matching the human posts based on the knowledge graph and the deep learning is explained in detail with reference to the attached drawings 1-3.
In this embodiment, the human-sentry matching method based on knowledge graph and deep learning includes:
s101: the method comprises the steps of obtaining first basic data information of a post to be matched, and extracting effective information related to the post to be matched from the first basic data information, wherein the first basic data information comprises selected resume data, recruitment information of the post and recruitment interaction records.
In this embodiment, the step of obtaining the first basic data information of the post to be matched specifically includes:
and acquiring first basic data information of the same post to be matched of different companies or acquiring first basic data information of the same post to be matched of the same company. And selecting different first basic data information according to different recruitment requirements, and if the recruitment requirement is universal post recruitment, acquiring the first basic data information of a certain post in the same industry of different companies. And if the recruitment requirement is personalized post recruitment, acquiring first basic data of the post of a company related to the recruitment requirement, and learning the recruitment behavior aiming at the company to realize the personalized recruitment function of a certain post.
In this embodiment, the selected resume data is top scoring resume data of the job seeker logged at the post, that is, data of the logged resume matched with the post to be matched.
In this embodiment, the recruitment interaction record includes interaction information between the job seeker and the recruiter corresponding to the data of whether to take a job, the interview invitation, the interview condition, the interview frequency, the interview mode, and other selected resume data.
In the embodiment, the valid information includes information related to post recruitment requirements, such as a scholarly calendar, a working age, keywords in project experience, a graduation school, an address, and a related certificate.
S102: and adding the effective information into the knowledge graph, processing the information of the knowledge graph and the first basic data information, inputting the processed information into the reasoning model, obtaining the matching score of the selected resume and the post, and obtaining the optimal reasoning model according to the matching score.
In this embodiment, the extracted effective information is added to the knowledge graph, and the information such as entities, relationships, attributes, and the like included in the effective information is represented by a relationship connection line through the knowledge graph.
In this embodiment, the step of processing the knowledge-graph information and the first basic data information and inputting the processed knowledge-graph information into the inference model specifically includes: and respectively coding the information of the knowledge graph and the first basic data information and inputting the information into the inference model.
In a specific embodiment, the information of the knowledge graph is input into the inference model after being encoded and processed by using a pre-trained model such as TransE or TransX. And coding the first basic data information, namely the resume text of the selected resume data and the like by using a bert model and then inputting the coded resume text into an inference model.
In the embodiment, the inference model is a neural network, and the neural network utilizes the text coding of bert and the knowledge embedding technology of the knowledge map, namely a map neural network, and converts the selected resume and recruitment text information into text knowledge characteristics and facts and structural knowledge characteristics of the knowledge map and then fuses the text knowledge characteristics and the knowledge map into the neural network. The neural network calculates the selected resume data to obtain the characteristics of the selected resume data, and then performs matching calculation on the characteristics and the recruitment requirement of the post to obtain a matching score.
In a specific embodiment, the number of the selected resumes is 10, the inference model outputs a matching score or a matching grade of the selected resumes and the post, outputs a plurality of competitive analysis values of the selected resumes, and optimizes the resumes according to the matching score or the matching grade and the competitive analysis data.
In this embodiment, the step of obtaining the optimal inference model according to the matching score specifically includes: and judging the accuracy of the reasoning model according to the matching score, and optimizing the reasoning model according to the accuracy to obtain the optimal reasoning model.
In this embodiment, the tenserflow-based framework optimizes the parameters of the inference model multiple times to obtain the best inference model. The framework is provided with codes of an optimizer, and the objective function is optimized through gradient reduction of the codes, so that the inference model is optimized to the target through data learning.
And after the optimal reasoning model is obtained, storing the optimal reasoning model.
S103: acquiring knowledge map information of second basic data information, processing the second basic data information and the knowledge map information, inputting the processed second basic data information and the processed knowledge map information into an optimal reasoning model, and acquiring matching scores of resume data to be selected and positions through the optimal reasoning model, wherein the second basic data information comprises the first basic data information, the resume data to be selected and recruitment information of the positions corresponding to the resume data to be selected.
In this embodiment, the resume data to be selected is resume data delivered to the post and not screened or interviewed.
In this embodiment, the effective information of the second basic data information is extracted and added to the knowledge-graph to obtain the effective information of the second basic data information. The effective information extraction method of the second basic data information and the method of adding the effective information into the knowledge graph are the same as the above-mentioned method of obtaining the effective information of the first basic data information, and the method of inputting the second basic data information and the knowledge graph information into the optimal inference model after processing is also the same as the above-mentioned method of inputting the knowledge graph information formed by the effective information of the first basic data information and the first basic data information into the inference model, which is not described herein again.
In this embodiment, the step of obtaining the matching score between the resume data to be selected and the post through the optimal inference model further includes: and recommending the resume to be selected according to the matching score, and collecting feedback information.
In this embodiment, the feedback information includes information related to the recommended resume to be selected, such as an admission result, a recommendation suggestion, and feedback on the matching score. And further optimizing the optimal inference model according to the feedback information.
The method is further explained by the learning and application of the method for the personnel matching based on the knowledge map and the deep learning in the universal recruitment and the personalized recruitment respectively.
Universal recruitment:
1. in the universal post recruitment stage, the inference model needs to learn the matching conditions of all selected resumes in a certain class of posts.
Training:
(1) all selected resume data, recruitment information and recruitment interaction records (collectively referred to as first basic data information, including whether to take a picture or not, whether to invite a trial, and the like) from the same delivery post of different companies need to be acquired first.
(2) Effective information (the effective information refers to keywords in the study calendar, the working age and the most important project experience in the resume) is extracted from the data and added into the knowledge graph. (knowledge graph is a proper noun, which means a graph database, which stores a large amount of extracted effective information such as entities, relations, attributes and the like.A relation connecting line exists between the entities, and attributes such as Mingming (relation) classmate-floret (attribute: male) exist in the entities, Mingming (relation) graduation is in North.
(3) The knowledge graph information and the first basic data information are input to the inference model after being processed by data processing service (the knowledge graph information is coded and processed into the input of the subsequent inference model by using a pre-trained model such as TransE or TransX, and the first basic data information, namely, the resume text and the like, is coded by using a bert model into the input of the subsequent inference model).
(4) And obtaining the matching scores of all the selected resumes and the position requirements.
(5) Judging the accuracy, iteratively optimizing the model (optimization is deep learning a noun, which means parameter optimization of the model. develop a framework based on tenserflow. the code of the optimizer is arranged in the framework, and is specially used for optimizing the objective function by gradient descent. the function is to enable the inference model to optimize towards the objective through data learning.)
(6) And saving the optimal reasoning model.
2. An application stage:
(1) and taking out the optimal reasoning model corresponding to the post according to the post.
(2) All resume data to be selected, the recruitment information of the post, the selected resume data, the corresponding recruitment information and the recruitment interaction record (second basic data information) from the same delivery post of different companies are acquired.
(3) And extracting effective information from the second basic data information, and adding the effective information into the knowledge graph.
(4) And inputting the information of the knowledge graph and the second basic data information into the optimal reasoning model after the data processing service.
(5) And obtaining the matching scores of all resumes to be selected and post positions for delivery through the optimal reasoning model.
(6) Recommending appropriate resumes and performing feedback collection.
Personalized recruitment:
1. training:
(1) the method comprises the steps of firstly acquiring all selected resume data, recruitment information and recruitment interaction records (first basic data information) of the same delivery post of a certain company.
(2) And extracting effective information from the first basic data information, and adding the effective information into the knowledge graph.
(3) And inputting the information of the knowledge graph and the first basic data information into the inference model after data processing service.
(4) And calculating by the inference model to obtain matching scores of all resumes to be selected and the post requirements.
(5) Judging accuracy and repeatedly optimizing model
(6) And saving the optimal reasoning model.
An application stage:
1. and taking out the corresponding optimal reasoning model for the post to be matched.
(1) The method comprises the steps of firstly obtaining all resume data to be selected, recruitment information of a post and selected resume data and corresponding recruitment information and recruitment interaction records (second basic data information) of a certain company on the same delivery post.
(2) And extracting effective information from the data, and adding the effective information into a knowledge graph.
(3) And inputting the information of the knowledge graph and the second basic data information into the optimal reasoning model after the data processing service.
(4) And calculating to obtain the matching scores of all resumes to be selected and the post requirement.
(5) Recommending appropriate resumes and performing feedback collection.
In the embodiment, the inference model adopts partial network structure updating when the data volume is small, and all parameters of the whole model are updated when a large amount of data exists, so that the model can quickly correspond to the change of the recruitment requirement of the post.
Has the advantages that: the invention relates to a human-post matching method based on knowledge graph and deep learning, which describes the relationship between selected resume data and posts by using the knowledge graph, integrates a reasoning model according to the relationship and first basic data to carry out reasoning to obtain an optimal reasoning model, obtains the matching score between the resume data to be selected and the posts by using the optimal reasoning model, can carry out matching accurately, efficiently and rapidly, obtains the matching result between the resume and the posts, has high efficiency of resume screening and matching, greatly reduces the time and energy of personnel and job seekers, and improves the overall management level of enterprise personnel recruitment.
Based on the same inventive concept, the invention further provides a sentry matching system, please refer to fig. 4, and fig. 4 is a structural diagram of an embodiment of the inventor sentry matching system. The post matching system of the present invention is specifically described with reference to fig. 4.
In this embodiment, the people's post matching system includes a processor and a memory, the processor is connected with the memory: the memory stores first basic data, second basic data and a computer program, and the processor executes the human-sentry matching method based on the knowledge-graph and the deep learning according to the embodiment.
Has the advantages that: the people's post matching system of the invention uses the knowledge map to describe the relationship between the selected resume data and the post, the inference model is merged into the inference model according to the relationship and the first basic data to perform inference to obtain the optimal inference model, the matching score between the resume data to be selected and the post is obtained through the optimal inference model, the matching can be performed rapidly and accurately and efficiently, the matching result between the resume and the post is obtained, the efficiency of the resume screening and matching is high, the time and the energy of a user unit and a job seeker are greatly reduced, and the overall management level of enterprise personnel recruitment is improved.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. A human-sentry matching method based on knowledge graph and deep learning is characterized by comprising the following steps:
s101: acquiring first basic data information of a post to be matched, and extracting effective information related to the post to be matched from the first basic data information, wherein the first basic data information comprises selected resume data, recruitment information of the post and recruitment interaction records;
s102: adding the effective information into a knowledge graph, processing the information of the knowledge graph and first basic data information, inputting the processed information into an inference model, obtaining a matching score of the selected resume and the post, and obtaining an optimal inference model according to the matching score;
s103: acquiring knowledge graph information of second basic data information, processing the second basic data information and the knowledge graph information, inputting the processed second basic data information and the processed knowledge graph information into the optimal reasoning model, and acquiring matching scores of resume data to be selected and the post through the optimal reasoning model, wherein the second basic data information comprises the first basic data information, the resume data to be selected and the recruitment information of the post corresponding to the resume data to be selected.
2. The method of claim 1, wherein the effective information comprises a scholarship, a working age and keywords in project experience.
3. The method of knowledge-graph-based, deep-learning human job matching of claim 1, wherein the recruitment interaction records include whether to enroll, interview, and offer.
4. The method for matching human posts based on knowledge graph and deep learning as claimed in claim 1, wherein the step of inputting the processed knowledge graph information and first basic data information into the inference model specifically comprises:
and respectively coding the information of the knowledge graph and the first basic data information and inputting the information into the reasoning model.
5. The method of claim 1, wherein the selected resume data is data of a recorded resume matched with the position to be matched.
6. The human-sentry matching method based on knowledge-graph and deep learning according to claim 1, wherein the step of obtaining the optimal inference model according to the matching score specifically comprises:
and judging the accuracy of the reasoning model according to the matching score, and optimizing the reasoning model according to the accuracy to obtain the optimal reasoning model.
7. The method of human-sentry matching based on knowledge-graph, deep learning according to claim 6, characterized in that the inference model is optimized several times based on the framework of tenserflow to obtain the best inference model.
8. The human-sentry matching method based on knowledge-graph and deep learning according to claim 1, wherein the step of obtaining the first basic data information of the posts to be matched specifically comprises:
and acquiring first basic data information of the same post to be matched of different companies or acquiring first basic data information of the same post to be matched of the same company.
9. The human-sentry matching method based on knowledge-graph and deep learning of claim 1, wherein the step of obtaining the matching score of the resume data to be selected and the position through the optimal inference model further comprises:
and recommending the resume to be selected according to the matching score, and collecting feedback information.
10. The people's post matching system is characterized by comprising a processor and a memory, wherein the processor is connected with the memory:
the memory stores first base data, second base data, and a computer program, and the processor executes the method for matching human posts based on knowledge-graph and deep learning according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010468710.2A CN111737485A (en) | 2020-05-28 | 2020-05-28 | Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010468710.2A CN111737485A (en) | 2020-05-28 | 2020-05-28 | Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111737485A true CN111737485A (en) | 2020-10-02 |
Family
ID=72647931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010468710.2A Pending CN111737485A (en) | 2020-05-28 | 2020-05-28 | Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111737485A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200153A (en) * | 2020-11-17 | 2021-01-08 | 平安数字信息科技(深圳)有限公司 | Method, device and equipment for matching human posts based on history matching result |
| CN113240400A (en) * | 2021-06-02 | 2021-08-10 | 北京金山数字娱乐科技有限公司 | Candidate determination method and device based on knowledge graph |
| CN113434687A (en) * | 2021-07-22 | 2021-09-24 | 高向咨询(深圳)有限公司 | Automatic resume finding method, automatic recruitment system and computer storage medium |
| CN115098791A (en) * | 2022-08-24 | 2022-09-23 | 中建电子商务有限责任公司 | Real-time post recommendation method and system |
| CN115526590A (en) * | 2022-09-16 | 2022-12-27 | 深圳今日人才信息科技有限公司 | Efficient human-sentry matching and re-pushing method combining expert knowledge and algorithm |
| CN116362699A (en) * | 2023-03-15 | 2023-06-30 | 国信蓝桥教育科技股份有限公司 | Post matching report generation method |
| CN116562838A (en) * | 2023-07-12 | 2023-08-08 | 深圳须弥云图空间科技有限公司 | Person post matching degree determination method and device, electronic equipment and storage medium |
| CN116596496A (en) * | 2023-07-18 | 2023-08-15 | 金现代信息产业股份有限公司 | Person post matching method, system, medium and equipment based on labeling |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5965557B1 (en) * | 2016-01-29 | 2016-08-10 | 株式会社リクルートホールディングス | Similarity learning system and similarity learning method |
| CN108563653A (en) * | 2017-12-21 | 2018-09-21 | 清华大学 | A kind of construction method and system for knowledge acquirement model in knowledge mapping |
| CN108920544A (en) * | 2018-06-13 | 2018-11-30 | 桂林电子科技大学 | A kind of personalized position recommended method of knowledge based map |
| CN110443571A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The method, device and equipment of knowledge based map progress resume assessment |
| CN111192024A (en) * | 2019-12-31 | 2020-05-22 | 广东轩辕网络科技股份有限公司 | Method and device for matching human posts based on reinforcement learning |
-
2020
- 2020-05-28 CN CN202010468710.2A patent/CN111737485A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5965557B1 (en) * | 2016-01-29 | 2016-08-10 | 株式会社リクルートホールディングス | Similarity learning system and similarity learning method |
| CN108563653A (en) * | 2017-12-21 | 2018-09-21 | 清华大学 | A kind of construction method and system for knowledge acquirement model in knowledge mapping |
| CN108920544A (en) * | 2018-06-13 | 2018-11-30 | 桂林电子科技大学 | A kind of personalized position recommended method of knowledge based map |
| CN110443571A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The method, device and equipment of knowledge based map progress resume assessment |
| CN111192024A (en) * | 2019-12-31 | 2020-05-22 | 广东轩辕网络科技股份有限公司 | Method and device for matching human posts based on reinforcement learning |
Non-Patent Citations (2)
| Title |
|---|
| 张俊峰;魏瑞斌;: "国内招聘类网站的数据类岗位人才需求特征挖掘", 情报杂志 * |
| 李妍霏;: "人工智能助力企业人才选拔数字化变革", 中国国情国力 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112200153A (en) * | 2020-11-17 | 2021-01-08 | 平安数字信息科技(深圳)有限公司 | Method, device and equipment for matching human posts based on history matching result |
| CN112200153B (en) * | 2020-11-17 | 2023-09-05 | 深圳平安智汇企业信息管理有限公司 | Person post matching method, device and equipment based on history matching result |
| CN113240400A (en) * | 2021-06-02 | 2021-08-10 | 北京金山数字娱乐科技有限公司 | Candidate determination method and device based on knowledge graph |
| CN113434687A (en) * | 2021-07-22 | 2021-09-24 | 高向咨询(深圳)有限公司 | Automatic resume finding method, automatic recruitment system and computer storage medium |
| CN115098791A (en) * | 2022-08-24 | 2022-09-23 | 中建电子商务有限责任公司 | Real-time post recommendation method and system |
| CN115526590A (en) * | 2022-09-16 | 2022-12-27 | 深圳今日人才信息科技有限公司 | Efficient human-sentry matching and re-pushing method combining expert knowledge and algorithm |
| CN115526590B (en) * | 2022-09-16 | 2023-08-04 | 深圳今日人才信息科技有限公司 | Efficient person post matching and re-pushing method combining expert knowledge and algorithm |
| CN116362699A (en) * | 2023-03-15 | 2023-06-30 | 国信蓝桥教育科技股份有限公司 | Post matching report generation method |
| CN116562838A (en) * | 2023-07-12 | 2023-08-08 | 深圳须弥云图空间科技有限公司 | Person post matching degree determination method and device, electronic equipment and storage medium |
| CN116562838B (en) * | 2023-07-12 | 2024-03-15 | 深圳须弥云图空间科技有限公司 | Person post matching degree determination method and device, electronic equipment and storage medium |
| CN116596496A (en) * | 2023-07-18 | 2023-08-15 | 金现代信息产业股份有限公司 | Person post matching method, system, medium and equipment based on labeling |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111737485A (en) | Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning | |
| CN110765257B (en) | Intelligent consulting system of law of knowledge map driving type | |
| CN111737495B (en) | Middle-high-end talent intelligent recommendation system and method based on domain self-classification | |
| Squicciarini et al. | Demand for AI skills in jobs: Evidence from online job postings | |
| CN108920544A (en) | A kind of personalized position recommended method of knowledge based map | |
| CN110597988A (en) | Text classification method, device, equipment and storage medium | |
| WO2019068253A1 (en) | Machine learning system for job applicant resume sorting | |
| Rodriguez et al. | Feature selection for job matching application using profile matching model | |
| CN114819924B (en) | Enterprise information push processing method and device based on portrait analysis | |
| CN113934868A (en) | Government affair big data management method and system | |
| US20150347489A1 (en) | Information retrieval system and method based on query and record metadata in combination with relevance between disparate items in classification systems | |
| CN111737486B (en) | Person post matching method and storage device based on knowledge graph and deep learning | |
| CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
| CN110727852A (en) | Method, device and terminal for pushing recruitment recommendation service | |
| CN115564393A (en) | Recruitment requirement similarity-based job recommendation method | |
| CN101203847B (en) | System and method for managing listings | |
| CN117114514B (en) | Talent information analysis management method, system and device based on big data | |
| CN111696656B (en) | Doctor evaluation method and device of Internet medical platform | |
| CN110033191B (en) | Business artificial intelligence analysis method and system | |
| Wang et al. | Analysing CV corpus for finding suitable candidates using knowledge graph and BERT | |
| CN116304035A (en) | Multi-notice multi-crime name relation extraction method and device in complex case | |
| CN109299007A (en) | A kind of defect repair person's auto recommending method | |
| CN115455205A (en) | Time sequence knowledge graph-based occupational development planning method | |
| Trinh et al. | Automatic process resume in talent pool by applying natural language processing | |
| CN113742495A (en) | Rating characteristic weight determination method and device based on prediction model and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |