CN115455205B - Occupational development planning method based on time sequence knowledge graph - Google Patents
Occupational development planning method based on time sequence knowledge graph Download PDFInfo
- Publication number
- CN115455205B CN115455205B CN202211152160.9A CN202211152160A CN115455205B CN 115455205 B CN115455205 B CN 115455205B CN 202211152160 A CN202211152160 A CN 202211152160A CN 115455205 B CN115455205 B CN 115455205B
- Authority
- CN
- China
- Prior art keywords
- knowledge
- candidate
- professional
- development planning
- knowledge graph
- 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.)
- Active
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Abstract
The invention discloses a occupational development planning method based on a time sequence knowledge graph, which comprises the following steps: s1: analyzing and extracting mass information, and constructing nodes and relations of the knowledge graph; s2: mapping each node into a high-dimensional vector according to the constructed knowledge graph, constructing a graph neural network, inputting the graph neural network into a multi-layer fully-connected neural network for classification, and constructing a professional development planning model; s3: and extracting professional development planning candidate information, mapping the professional development planning candidate information into a high-dimensional vector according to a graph neural network of a knowledge graph, inputting the high-dimensional vector into the professional development planning model, and outputting a professional development path and a target of which background experiences are similar to those of the professional development planning candidate. The career planning analysis method based on the time sequence knowledge graph of the mass data can comprehensively and rapidly give career development suggestions of related candidates.
Description
Technical Field
The invention relates to the field of computer software, in particular to a professional development planning method based on a time sequence knowledge graph.
Background
The university graduates of ten millions of China go to society every year, and a good career planning has important guiding significance for individuals, is beneficial to macroscopic regulation of talents for society, and promotes healthy and stable development of national economy. Because of the complexity of the person, career planning for the person is a very complex problem, and candidates can easily lead to a large number of mismatches in the market if they do not have a clear system of knowledge and planning for their career development. The data report shows that more than 2/3 of staff have remorsed in the first occupation, and a large number of middle and high-end staff cannot find proper work, such as the design of universities in the family of the Gramineae and the universities in the seven years, finally, no design work is done or communication is learned, but programming related work is done following the hot spot at that time, and finally, how to promote related skills or competence related work is not known. Therefore, it is necessary for the staff at the job site or the students about to get into the job site to help them form the correct professional knowledge, complete the professional planning of the system and design the scientific development path.
However, current implementations of professional planning services fall into three main categories:
the first category is mainly based on the off-line traditional professional development planning mode based on expert knowledge. The method is characterized in that the evaluation and planning are performed in an offline manual docking mode by experts, and the defects of high price, low efficiency and the like exist, so that the method is difficult to popularize quickly due to the fact that the method always plays a role in a small range. Meanwhile, the professional planning service is subject to the artificial knowledge range and the own professional level, even due to the influence of subjective factors, a certain planning deviation is easily caused, and the influence is amplified to cause bad experience when reflected to individuals, so that the extreme sample is prevented from having strong practical significance by deeply exploring the characteristics of personal personality, education, skills and the like.
The second category is that the key word groups extracted by the position library are combined with the key word groups input by the user to perform position recommendation. The technology mainly considers the matching degree of the user and a certain position at the moment, does not consider the professional growth of the user, the character characteristics of the user and the soft characteristics of the unreacted character on the resume, and can not well support the relatively long-term planning problem of professional development.
The third category is professional planning recommendation using big data or deep learning. This technique is limited mainly in that only information of isolated positions is entered, and associated transitions and changes between positions are not considered. Therefore, this approach only guides the fitness of a single node employment or requires additional skills and capabilities, but does not take into account the dynamic changes in professional development transitions, which is not sufficient to form a comprehensive professional development plan.
The massive resume data naturally has information of diversified professional development paths, if the professional development evolution information provided by the massive data can be based on the professional development evolution information provided by the massive data, common characteristics and attributes of related professional development of different user groups are obtained, the specific professional planning suggestions are extracted, and the information of related academies, skills, capabilities and the like which should be possessed is induced, so that the method is efficient and accurate.
Accordingly, the prior art has drawbacks and needs improvement.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the career planning analysis method based on the time sequence knowledge graph can comprehensively and rapidly give the career development advice of the related candidate.
The technical scheme of the invention is as follows: a professional development planning method based on a time sequence knowledge graph comprises the following steps: s1: analyzing and extracting mass information, and constructing nodes and relations of the knowledge graph; s2: mapping each node into a high-dimensional vector according to the constructed knowledge graph, constructing a graph neural network, inputting the graph neural network into a multi-layer fully-connected neural network for classification, and constructing a professional development planning model; s3: and extracting professional development planning candidate information, mapping the professional development planning candidate information into a high-dimensional vector according to a graph neural network of a knowledge graph, inputting the high-dimensional vector into the professional development planning model, and outputting a professional development path and a target of which background experiences are similar to those of the professional development planning candidate.
In the method for professional development planning based on the time sequence knowledge graph, in the step S1, the construction of the nodes and the relations of the knowledge graph includes: s11: constructing skill knowledge nodes and relations; s12: constructing probability knowledge nodes and relations; s13: constructing knowledge nodes and relations of a company school; s14: and constructing talent time sequence knowledge nodes and relations.
The technical scheme is applied to the method for planning the professional development based on the time sequence knowledge graph, wherein the skill knowledge is the skill knowledge of all the posts in the whole industry, including the first-level industry, the second-level function, the third-level post, the professional skill and the soft skill; the probability knowledge is the probability of various features; the school knowledge of the company comprises logos, income, websites, properties, people, organization structures, departments, teams and posts of the company, and levels, creation time, official networks, department systems and professions of the school; the talent time sequence knowledge comprises a resume of a large number of candidate talents in the mass information and the time of adding the large number of candidate talents into the knowledge graph.
In the method for professional development planning based on the time sequence knowledge graph, in step S14, according to the new addition of the massive candidate talent resume or the update of the massive candidate talent resume, the talent time sequence knowledge nodes and relations are updated in real time.
The method is applied to the technical schemes, and the node and the relationship of the knowledge graph comprise characteristics of each node, similarity among the nodes and implicit relationship among the nodes in the occupational development planning method based on the time sequence knowledge graph.
In the method for professional development planning based on the time sequence knowledge graph, in step S2, each node is mapped into a high-dimensional vector by using a notice mechanism through a plurality of layers of GATs, so as to construct a graph neural network of the knowledge graph.
In the method for professional development planning based on the time-series knowledge graph, in step S2, talent time-series knowledge nodes mapped into high-dimensional vectors are input into a multi-layer fully-connected neural network for classification, and a professional development planning model is constructed.
In the method for professional development planning based on the time-series knowledge graph, in step S3, the professional development planning model automatically analyzes and fuses professional experiences of a plurality of massive candidate talents, and outputs a professional development path and a target with background experiences most similar to those of the professional development planning candidates.
The method is applied to the technical schemes, and in the method for professional development planning based on the time sequence knowledge graph, the output professional development path and the target are professional development planning reports in a preset format.
The method applied to the technical schemes, based on the time sequence knowledge graph, for professional development planning further comprises the step S4: and (3) monitoring the change of the information of the candidate for professional development planning in real time, and repeating the step (S3).
The beneficial effects of the invention are as follows:
according to the invention, the nodes and the relations of the knowledge graph are constructed by analyzing and extracting massive information, and the graph neural network and the career development planning model are constructed by analyzing and extracting the massive information, so that career development suggestions of related candidates can be comprehensively and rapidly given out based on career planning analysis of the time sequence knowledge graph of massive data, and a career post with a similar background is also given out for the candidates to refer to. The method is different from the traditional method based on the occupational development proposal of offline manual work, can not be limited to the manual knowledge boundary, and avoids subjective factors and deviation of different professional levels; compared with other modes based on the existing position library or single-point matching degree, the method considers dynamic position transition, can dynamically depict position development trend by combining with a time sequence map, and synthesizes professional development and growth process to push out professional paths; moreover, due to the real-time performance and the rapidity of the method, the follow-up professional selection of the candidate can be tracked, and the related suggestions can be dynamically adjusted; more effective and professional development of the assistance candidate.
Drawings
FIG. 1 is a flow chart of knowledge graph updating according to the present invention;
FIG. 2 is a flow chart of professional development planning prediction in accordance with the present invention;
FIG. 3 is a professional development planning model diagram of the present invention;
fig. 4 is a professional development planning proposal diagram of the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the specific embodiments.
The embodiment provides a method for professional development planning based on a time sequence knowledge graph, which comprises the following steps: first, step S1: and analyzing and extracting massive information, and constructing nodes and relations of the knowledge graph.
Before the nodes and the relations of the knowledge graph are constructed, mass information is collected, analyzed and extracted, and the method comprises the following steps: resume information extraction, network information extraction and user information collection, and particularly relates to resume analysis, OCR, named entity recognition and other technologies. The resume information can describe the information of a candidate most directly, the resume content is analyzed and automatically classified and added into a knowledge graph, the method comprises schools, companies and the like of the candidate, webpage information extraction is also an important way for obtaining cattle, most people with built trees for self work can actively or passively leave marks in the Internet environment, the most direct way is that the candidate has public papers, the source codes of the github, blogs of the CSDN and the like, and the information can further improve the information of the candidate.
Moreover, the user data can be collected in real time, which specifically comprises: real-time dynamic capturing is performed on public information on a network through a data capture tool, such as company information: industry, scale, organization architecture, service area, location, etc., institutional information: school, specialty, and grade, job information: company, recruitment information, demand, etc. In addition to these hard information, soft metrics are also important, so we gather user information, i.e. evaluation information obtained after contact with the candidate, such as communication capacity, expression capacity, etc., by the user using our recruitment platform (e.g. hunter or HR).
And, the node and the relation for constructing the knowledge graph specifically comprise: s11: constructing skill knowledge nodes and relations; s12: constructing probability knowledge nodes and relations; s13: constructing knowledge nodes and relations of a company school; s14: and constructing talent time sequence knowledge nodes and relations.
The skill knowledge is skill knowledge of all industries and all posts, including primary industries, secondary functions, tertiary posts, professional skills and soft skills; the probability knowledge is the probability of various features; the school knowledge of the company comprises logos, income, websites, properties, people, organization structures, departments, teams and posts of the company, and levels, creation time, official networks, department systems and professions of the school; the talent time sequence knowledge comprises a resume of a large number of candidate talents in the mass information and the time of adding the large number of candidate talents into the knowledge graph.
Thus, the method combines a great deal of information of the candidate and the current market environment and other information, including educational background, classmate information, colleague information, company information, industry, project experience and basic information such as city, income curve and position information. And forming a knowledge graph structure according to the mass information content.
Wherein, the first stage: skills knowledge graph; and integrating according to the network information and adding expert consultants to carry out manual arrangement. And generating a skill knowledge graph covering all posts in the whole industry. The nodes comprise a first-level industry, a second-level function, a third-level post and skills, wherein the skills comprise professional skills and soft skills.
And a second stage: probability knowledge graph, i.e. under skill knowledge graph, we add more features such as gender, age, academic, working experience, etc. in the second stage. Meanwhile, under the corresponding post, the probability of various characteristics, such as male and female proportion, is calculated.
And a third stage: and (3) a company school knowledge graph, which constitutes a static company knowledge graph. Including but not limited to the company: logo, income, address, nature, number of people, organization architecture, department, team, post, etc., school: level, time of creation, official network, department, specialty, etc.
Fourth stage: talent time sequence knowledge graph; at this stage, various information of talents and time are added. And constructing a talent time sequence diagram. The part is a dynamic knowledge graph; the flow of the knowledge graph update is shown in fig. 1; in step S14, according to the new addition of the massive candidate talent resume or the update of the massive candidate resume, the talent time sequence knowledge nodes and relations are updated in real time; and the nodes and the relations of the knowledge graph comprise characteristics of each node, similarity among the nodes and implicit relations among the nodes. Thus, each time a candidate resume is added or each time a candidate resumes, the corresponding node and edge are added and stored in the corresponding time node. Additional information may be added at the same time, such as interview evaluations, personality tests, and events. And meanwhile, other nodes and edges can be supplemented, perfected and updated.
After the knowledge graph is constructed, step S2 is performed: mapping each node into a high-dimensional vector according to the constructed knowledge graph, constructing a graph neural network, inputting the graph neural network into a multi-layer fully-connected neural network for classification, and constructing a professional development planning model; and each node is mapped into a high-dimensional vector by using a multi-layer GAT and by using an attention mechanism of the multi-layer GAT, so as to construct a graph neural network of a knowledge graph; and inputting talent time sequence knowledge nodes mapped into high-dimensional vectors into a multi-layer fully-connected neural network for classification, and constructing a professional development planning model.
When the knowledge graph is constructed and used, each node in the knowledge graph is an entity, such as a candidate, a school, a company and the like, and tag information from websites, such as 211/985/double first-class information and the like, and behavior and evaluation information of users on recruitment systems, such as information complement of the softness of a certain candidate are also included in the graph. Construction includes, but is not limited to, corporate information: industry, scale, service area, location, etc. Candidate information: salary, school, profession, post, etc., school: places, professions, 211/985/double-first class etc. tags, website homepage: talent dynamic knowledge maps of legal information channels such as github, CSDN, knowledge network, patent network and the like are disclosed. In addition, new entities or new entity attributes are discovered through the network information, and the coverage rate of the knowledge graph is continuously improved. And then, calculating data in the knowledge graph in a timing and full-quantity and increment mode, wherein the data comprise characteristics of extracted nodes, similarity among the nodes, implicit relation among the nodes and the like, and finally mapping each candidate node into a high-dimensional vector to be used as downstream model prediction. Based on the method, dynamic updating of talent knowledge maps is realized, and instantaneity and accuracy are guaranteed.
When the professional development planning model is constructed, the professional development planning model is shown in fig. 3, nodes in a map are mapped into high-dimensional vectors through multiple layers GAT (Graph Attention Network) firstly, the attention mechanism of GAT is utilized to aggregate and abstract rich relevant information, and then all 'people' nodes, namely talent time sequence knowledge nodes, are selected and input into a lower-layer multi-layer fully-connected neural network for classification, and the main purpose of classification is to find one or more target characters, and the relevant experience, skill and other multidimensional information of the target characters serve as targets of the professional development planning candidates to be predicted. Fig. 3 is a schematic diagram, in which "company", "person" and "school" (from deep to shallow) can be represented by dots with different shades of gray, and the actual diagram includes a plurality of nodes, so that the examples are not given.
Finally, step S3: and extracting professional development planning candidate information, mapping the professional development planning candidate information into a high-dimensional vector according to a graph neural network of a knowledge graph, inputting the high-dimensional vector into the professional development planning model, and outputting a professional development path and a target of which background experiences are similar to those of the professional development planning candidate. The professional development planning model automatically analyzes and fuses professional experiences of a plurality of massive candidate talents, and outputs a professional development path and a target, wherein the background experience of the professional development path is most similar to that of the professional development planning candidate. And outputting the job development path and the job development planning report with a target of a preset format.
When the graphic neural network and the professional development planning model are applied to perform the professional development planning prediction, the flow steps are as follows, wherein the professional development planning prediction flow chart is shown in fig. 2.
Firstly, inputting all information of a candidate for professional development planning, including past histories and expected position information, wherein the information format obtained in the step is diversified, and the technology of resume analysis, OCR, named entity recognition and the like applied in the construction of a knowledge graph is used.
Further, the information of the candidate of the job development planning is mapped into a high-dimensional vector by combining with a mapping neural network mapping scheme of the latest knowledge graph, further, the latest job planning of the candidate is predicted in a job development planning model of the multi-layer neural network input to the fine-tune, and the model automatically analyzes and fuses a plurality of job development paths with the most similar job experience output background experiences with the candidate for reference.
After the professional development planning model outputs a plurality of target tasks, the information of a plurality of target characters is aggregated and used as the final professional planning through a complex fusion model integrating expert knowledge and natural language processing. The result is output as a professional development planning report, and information of relevant academies, skills, capabilities, professions and the like which should be possessed is summarized, and the information includes how much time is needed to learn which skills, and in which direction the next work should be searched for more suitable. More particularly, a professional development path in the database most similar to the candidate's background is presented, wherein the professional development path may be real or abstract for reference by the candidate. And we can track the dynamics of the candidate in real time, and the suggested professional development planning can be correspondingly adjusted along with the professional development change of the candidate. The output of the advice part in the final occupational planning is shown in fig. 4, fig. 4 is an example of a radar chart of a occupational planning of a certain industry, which contains a plurality of indexes, polygon 1 in the radar chart is the result to be achieved, and middle deep line 2 is the current state of a candidate for the occupational development planning, so that the difference point between the candidate for the occupational development planning and the target result can be well shown through the chart, the comprehensive analysis result can be provided for the candidate for the occupational development planning, the candidate can be helped to purposefully supplement corresponding short plates, and the target state can be quickly reached.
In conclusion, the talent dynamic knowledge graph constructed through the mass data can provide the most timely and effective career planning data for the candidate for career development planning, the development dynamics of the industry can be rapidly mastered, and the candidate can clearly know the direction and mode of the talent. It may be specific to what skills (including professional skills and soft skills) need to be mastered at what point in time, what class of company is more suitable for itself, what level can be reached by itself according to the existing planning, etc.
Thus, after having a time sequence knowledge graph supported by a huge amount of resume, we combine the time sequence graph neural network embedding scheme of the latest knowledge graph to map all information of the candidate of the professional development plan into a high-dimensional vector, the vector comprises all information (company, school and other candidates) in the graph, the information is input into the trained neural network to predict the latest professional plan of the candidate, the information of relevant academic, skill, ability, industry and the like which is supposed to be possessed is summarized, including how much time is needed, which skill is learned, which direction the next job should find more suitable, and more particularly, the professional development path (which may be real or abstract) of the professional standard in the database and most similar to the background of the candidate is given for the candidate to refer to. The dynamic state of the candidate can be tracked in real time, and the suggested professional development planning can be correspondingly adjusted along with the professional development change of the candidate; the change of the information of the candidate for professional development planning can be monitored in real time, and the step S3 is repeated.
In short, this scheme can be summarized in two phases:
1. knowledge graph construction stage: collecting massive information (resume, public information and user information), analyzing and extracting the information, enriching nodes and relations, constructing a knowledge graph, and updating at random;
2. occupation planning stage: given candidate information, nodes where the candidates are located are segmented into high-dimensional vectors through a graph neural network, the vectors are input into a trained neural network model to predict other multiple candidates possibly similar to the candidates in the future, and the information of the current occupational experience, skills and the like of the multiple candidates is automatically analyzed and fused to serve as the occupational development path and target of the given candidates.
In this way, the present embodiment is directed to a method for mining a corresponding professional development path for each candidate in a time-series knowledge graph with massive information. The occupation planning problem is very complex, the current work has a lot of crossovers, and transition between occupation also needs more data and technical support, so that a perfect time sequence dynamic knowledge graph is constructed by combining multiple factors and the history information of the current candidate; the knowledge graph may contain information about each candidate, such as educational background, selection of work experience, city change, interview experience, and evaluation, etc., as well as information about the company, including the company's scale, nature, industry, etc., job position information, institution information, etc. Because the knowledge graph can change the relationship between entities along with the time of the professional transition or the time development change of the candidate, in order to comprehensively acquire knowledge, we build a dynamic knowledge graph, add time dimension into the knowledge graph data, analyze the change and trend of the professional career of the candidate with different backgrounds along with time by using a time sequence analysis technology and a graph neural network technology, and therefore, summarize the suggestion of the key professional planning for the candidate to refer to.
Compared with the traditional professional development planning scheme based on expert knowledge, the method provided by the invention considers more information dimensions, more comprehensive information and more objective market analysis results, and is faster and more personalized. A single expert experience-based solution is often not objective enough, and the directions of the hunting of different experts are different, so that a very comprehensive solution cannot be given.
The foregoing description of the preferred embodiment of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (6)
1. The occupational development planning method based on the time sequence knowledge graph is characterized by comprising the following steps of:
s1: analyzing and extracting mass information, and constructing nodes and relations of the knowledge graph;
s2: mapping each node into a high-dimensional vector according to the constructed knowledge graph, constructing a graph neural network, inputting the graph neural network into a multi-layer fully-connected neural network for classification, and constructing a professional development planning model;
s3: extracting professional development planning candidate information, mapping the professional development planning candidate information into a high-dimensional vector according to a graph neural network of a knowledge graph, inputting the high-dimensional vector into the professional development planning model, and outputting a professional development path and a target of which background experiences are similar to those of the professional development planning candidate;
in step S1, the construction of the nodes and relationships of the knowledge graph includes:
s11: constructing skill knowledge nodes and relations;
s12: constructing probability knowledge nodes and relations;
s13: constructing knowledge nodes and relations of a company school;
s14: constructing talent time sequence knowledge nodes and relations;
the skill knowledge is the skill knowledge of all the posts in the whole industry, including the first-level industry, the second-level function, the third-level post, the professional skill and the soft skill; the probability knowledge is the probability of various features; the school knowledge of the company comprises logos, income, websites, properties, people, organization structures, departments, teams and posts of the company, and levels, creation time, official networks, department systems and professions of the school; the talent time sequence knowledge comprises a resume of a mass of candidate talents in mass information and the time of adding the mass of candidate talents into a knowledge graph;
in step S2, mapping each node into a high-dimensional vector by using a multi-layer GAT and using an attention mechanism thereof to construct a graph neural network of a knowledge graph;
in step S2, talent time sequence knowledge nodes mapped into high-dimensional vectors are input into a multi-layer fully-connected neural network for classification, and a professional development planning model is constructed.
2. The method of claim 1, wherein in step S14, the talent time sequence knowledge nodes and relationships are updated in real time according to the new addition of the massive candidate talent resume or the update of the massive candidate talent resume.
3. The method of claim 2, wherein the nodes and relationships of the knowledge graph include features of each node, similarities between nodes, and implicit relationships between nodes.
4. The method of claim 1, wherein in step S3, the staff development planning model automatically analyzes and fuses the professional experiences of a plurality of massive candidate talents, and outputs a professional development path and a target whose background experience is most similar to that of the professional development planning candidate.
5. The method of claim 4, wherein the job development path and target outputted are job development planning reports in a predetermined format.
6. The method of professional development planning based on time series knowledge graph according to claim 1, further comprising step S4: and (3) monitoring the change of the information of the candidate for professional development planning in real time, and repeating the step (S3).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211152160.9A CN115455205B (en) | 2022-09-21 | 2022-09-21 | Occupational development planning method based on time sequence knowledge graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211152160.9A CN115455205B (en) | 2022-09-21 | 2022-09-21 | Occupational development planning method based on time sequence knowledge graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115455205A CN115455205A (en) | 2022-12-09 |
| CN115455205B true CN115455205B (en) | 2023-06-30 |
Family
ID=84305048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211152160.9A Active CN115455205B (en) | 2022-09-21 | 2022-09-21 | Occupational development planning method based on time sequence knowledge graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115455205B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117371625B (en) * | 2023-12-07 | 2024-02-06 | 中科软股教育科技(北京)股份有限公司 | Occupational development prediction system and method based on big data analysis |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159330A (en) * | 2021-04-30 | 2021-07-23 | 嘉应学院 | Professional learning path system and method based on hierarchical task network planning model learning |
| 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 |
| CN114331380A (en) * | 2021-12-31 | 2022-04-12 | 北京百度网讯科技有限公司 | Method, system, equipment and storage medium for predicting occupational flow relationship |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100082356A1 (en) * | 2008-09-30 | 2010-04-01 | Yahoo! Inc. | System and method for recommending personalized career paths |
| CA3030878A1 (en) * | 2018-01-22 | 2019-07-22 | Kliq.Ca Inc. | Systems and methods for decision modelling of a temporal path |
| US11062240B2 (en) * | 2018-03-30 | 2021-07-13 | Accenture Global Solutions Limited | Determining optimal workforce types to fulfill occupational roles in an organization based on occupational attributes |
| US11113324B2 (en) * | 2018-07-26 | 2021-09-07 | JANZZ Ltd | Classifier system and method |
| CN109460479A (en) * | 2018-11-19 | 2019-03-12 | 广州合摩计算机科技有限公司 | A kind of prediction technique based on reason map, device and system |
| CN112417165B (en) * | 2020-11-18 | 2022-04-26 | 杭州电子科技大学 | Method and system for constructing and inquiring lifetime planning knowledge graph |
| CN114691892A (en) * | 2022-04-21 | 2022-07-01 | 君之福(北京)科技有限公司 | Retired soldier occupation planning method and retired soldier occupation planning system based on big data |
-
2022
- 2022-09-21 CN CN202211152160.9A patent/CN115455205B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159330A (en) * | 2021-04-30 | 2021-07-23 | 嘉应学院 | Professional learning path system and method based on hierarchical task network planning model learning |
| 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 |
| CN114331380A (en) * | 2021-12-31 | 2022-04-12 | 北京百度网讯科技有限公司 | Method, system, equipment and storage medium for predicting occupational flow relationship |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115455205A (en) | 2022-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107230174B (en) | Online interactive learning system and method based on network | |
| Karthikeyan et al. | Towards developing hybrid educational data mining model (HEDM) for efficient and accurate student performance evaluation | |
| CN104318340B (en) | Information visualization methods and intelligent visible analysis system based on text resume information | |
| CN106663230A (en) | Career analytics platform | |
| Asanbe et al. | Teachers’ performance evaluation in higher educational institution using data mining technique | |
| He et al. | Clustering sequential navigation patterns in multiple‐source reading tasks with dynamic time warping method | |
| Almgerbi et al. | A systematic review of data analytics job requirements and online-courses | |
| CN115455205B (en) | Occupational development planning method based on time sequence knowledge graph | |
| Hassan et al. | Leveraging deep learning and big data to enhance computing curriculum for industry-relevant skills: A Norwegian case study | |
| Thakral et al. | Trends in the thematic landscape of HR analytics research: a structural topic modeling approach | |
| Darko et al. | Service quality in football tourism: an evaluation model based on online reviews and data envelopment analysis with linguistic distribution assessments | |
| Wang | Analysis of students’ behavior in english online education based on data mining | |
| Oreshin et al. | Implementing a Machine Learning Approach to Predicting Students’ Academic Outcomes | |
| Shaheen | Decision tree for PLOs of undergraduate computing program based on CLO of computer programming | |
| Ajgaonkar et al. | EduKrishnaa: A Career Guidance Web Application Based on Multi-intelligence Using Multiclass Classification Algorithm | |
| Khan et al. | Measuring economic resilience of manufacturing organization leveraging integrated data envelopment analysis (DEA)-machine learning approach | |
| Ngo et al. | Exploration and integration of job portals in Vietnam | |
| Gehlhaus et al. | China’s AI Workforce | |
| Wankhede et al. | ANALYZING & PREDICTING STUDENTS’PERFORMANCES USING MACHINE LEARNING | |
| Verdon‐Kidd et al. | Bridging the gap between researchers and decision‐makers | |
| Lee et al. | Synthetic Longitudinal Education Database: Linking National Datasets for K-16 Education and College Readiness. | |
| Raju | Predicting student graduation in higher education using data mining models: A comparison | |
| Biggs et al. | How to use this handbook | |
| Mikhnev et al. | Digital technologies for searching and processing unstructured Information in modern higher education | |
| Hassan et al. | Identification of Technical and Vocational Education and Training (TVET) trainee’s personality attributes which impact skills learning |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |