CN114925287A - Intelligent knowledge management system and method based on big data - Google Patents
Intelligent knowledge management system and method based on big data Download PDFInfo
- Publication number
- CN114925287A CN114925287A CN202210865419.8A CN202210865419A CN114925287A CN 114925287 A CN114925287 A CN 114925287A CN 202210865419 A CN202210865419 A CN 202210865419A CN 114925287 A CN114925287 A CN 114925287A
- Authority
- CN
- China
- Prior art keywords
- information
- work skill
- skill attribute
- attribute information
- case
- 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.)
- Granted
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/105—Human resources
- G06Q10/1053—Employment or hiring
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent knowledge management system and method based on big data, which can be applied to the technical field of information. The intelligent knowledge management system based on big data comprises: the system comprises an information acquisition subsystem, an information recommendation subsystem and an information prediction subsystem. The information acquisition subsystem is used for responding to a job hunting request from the client and acquiring first work skill attribute information and job hunting post information of a job seeker from a job hunting resume; and matching the first work skill attribute information with the information of the job hunting post. The information recommendation subsystem is used for determining a target learning case from the case database according to the first work skill attribute information and the information of the job hunting post; the information prediction subsystem is used for extracting additional work skill attribute information from the target learning case and generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information; and generating loss risk prediction information according to the second work skill attribute information.
Description
Technical Field
The invention relates to the technical field of information, in particular to an intelligent knowledge management system and method based on big data.
Background
The competition among enterprises is often the competition of talents, and for an enterprise, the working skills possessed by the staff are one of the knowledge resources of the enterprise. The knowledge management system is an important means and technical way for managing knowledge resources. However, how to implement the pre-judgment type retention of knowledge resources to reduce the risk of loss of knowledge resources is a common defect of the existing knowledge management system.
In the process of implementing the inventive concept of the present invention, the inventor finds that accurate prediction of the working skills of talents is required to achieve the prejudgment retention of knowledge resources of enterprises, and therefore, a system capable of effectively identifying the working skill diversity of talents and predicting whether talents have a loss risk in advance is urgently needed.
Disclosure of Invention
In view of the above problems, the present invention provides an intelligent knowledge management system and method based on big data.
According to a first aspect of the present invention, there is provided a big data based intelligent knowledge management system, comprising: the information acquisition subsystem is used for responding to a job hunting request from the client and acquiring first work skill attribute information and job hunting post information of a job seeker from a job hunting resume; inputting the first work skill attribute information and the information of job hunting posts into a preset model, and outputting a matching result; sending a recommended case request to the information recommendation subsystem under the condition that the matching result meets the preset condition;
the information recommendation subsystem is used for responding to a recommendation case request from the information acquisition subsystem and acquiring the first work skill attribute information and job hunting post information from the information acquisition subsystem; determining a target learning case from a case database according to the first work skill attribute information and the information of the job hunting post, and sending an information prediction request to an information prediction subsystem;
the information prediction subsystem is used for responding to an information prediction request from the information recommendation subsystem and acquiring a target learning case and first work skill attribute information from the information recommendation subsystem; extracting additional work skill attribute information from the target learning case, wherein the additional work skill attribute information represents work skill attribute information which can be added by a job seeker through learning the target learning case in a preset time period; generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information; generating loss risk prediction information according to the second work skill attribute information, wherein the loss risk prediction information represents the change risk of the job seeker after learning the target learning case; and sending the loss risk prediction information to the client.
According to an embodiment of the present invention, an information acquisition subsystem includes:
the registration login module is used for registering login information so as to obtain the access right of the information acquisition subsystem;
the first display module is used for displaying information of job hunting posts and information of interest selection interfaces;
the resume module is used for editing resume information for job hunting;
the matching module is used for predicting the matching degree of the job seeker and the job hunting post according to the first work skill attribute information and the job hunting post information;
the selection module is used for generating intention learning subject information according to the interest selection interface information;
and the first administrator module is used for managing all the information acquired by the information acquisition subsystem.
According to an embodiment of the invention, the matching module comprises:
the preprocessing unit is used for preprocessing the first work skill attribute information and the information of the job hunting post to obtain first work skill attribute characteristic information and characteristic information of the job hunting post;
and the matching unit is used for inputting the first work skill attribute characteristic information and the characteristic information of the job hunting post into a preset model to obtain the matching degree.
According to an embodiment of the present invention, an information recommendation subsystem includes:
the case recommendation module is used for determining a target learning case from the case database according to the first work skill attribute information and the information of the job hunting post;
the second display module is used for displaying the target learning case, the learning method of the target learning case and the operation description of the information recommendation subsystem;
the investigation module is used for acquiring feedback information of the target learning case recommended by the information recommendation subsystem;
and the second administrator module is used for viewing and updating the case database in the information recommendation subsystem and the operation instruction of the information recommendation subsystem.
According to an embodiment of the present invention, an information prediction subsystem comprises:
the information extraction module is used for extracting additional work skill attribute information from the target learning case;
the information generation module is used for generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information;
the information prediction module is used for generating loss risk prediction information according to the second work skill attribute information;
and the sending module is used for sending the loss risk prediction information to the client.
The second aspect of the present invention provides an intelligent knowledge management method based on big data, which applies the above intelligent knowledge management system based on big data, and includes:
acquiring first work skill attribute information and job hunting position information of job hunters from job hunting resumes in response to job hunting requests from a client;
inputting the first work skill attribute information and the information of job hunting posts into a preset model, and outputting a matching result;
determining a target learning case from a case database according to the first work skill attribute information and the job hunting post information under the condition that the matching result meets the preset condition;
extracting additional work skill attribute information from the target learning case, wherein the additional work skill attribute information represents work skill attribute information which can be increased by a job seeker through learning the target learning case within a preset time period;
generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information;
generating loss risk prediction information according to the second work skill attribute information, wherein the loss risk prediction information represents the change risk of the job seeker after learning the target learning case; and
and sending loss risk prediction information to the client.
According to the embodiment of the invention, the step of inputting the first work skill attribute information and the job hunting post information into a preset model and outputting a matching result comprises the following steps:
preprocessing the first work skill attribute information and the job hunting post information to obtain first work skill attribute characteristic information and job hunting post characteristic information;
and inputting the first work skill attribute characteristic information and the characteristic information of the job hunting post into a preset model, and outputting a matching result.
According to the embodiment of the invention, the determining of the target learning case from the case database according to the first work skill attribute information and the information of the job hunting post comprises the following steps:
determining a target learning theme according to the first work skill attribute information and the job hunting post information;
and determining the target learning case from the case database according to the target learning theme.
According to the embodiment of the invention, the target learning theme is determined according to the first work skill attribute information and the information of job hunting posts, and the method comprises the following steps:
responding to the selection operation of the job seeker on the interest selection interface from the client, and acquiring intention learning subject information of the job seeker;
and determining a target learning theme according to the first work skill attribute information, the intention learning theme information and the job hunting post information.
According to the embodiment of the invention, the step of determining the target learning case from the case database according to the first work skill attribute information and the job hunting post information comprises the following steps:
acquiring a plurality of candidate learning case text messages from a case database according to the first work skill attribute information and the information of job hunting posts;
inputting a plurality of candidate learning case text information into a character vector conversion model, and outputting a plurality of candidate learning case vectors;
and based on a random forest algorithm or a clustering algorithm, screening a vector corresponding to the target learning case from the multiple candidate learning case vectors to determine the target learning case.
According to the embodiment of the invention, the first work skill attribute information and job hunting post information of the job seeker are obtained from the job hunting resume by using the information obtaining subsystem, the job seeker is matched with the job hunting post through the prediction model, and the recommendation case request is sent to the information recommending subsystem under the condition that the matching result meets the preset condition. And then, the information recommendation subsystem determines a target learning case from the case database according to the first work skill attribute information and job hunting post information, and sends an information prediction request to the information prediction subsystem. The information prediction subsystem extracts additional work skill attribute information from the target learning case, generates second work skill attribute information by combining the first work skill attribute information, and predicts the loss risk according to the second work skill attribute information. The information prediction of the whole period from the job hunting stage to the job entering stage of the job seeker is achieved, so that a manager can conveniently make a related talent cultivation strategy according to the information prediction result, and the loss risk of knowledge resources is reduced.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of embodiments of the present invention with reference to the accompanying drawings, in which:
FIG. 1 schematically illustrates an exemplary architecture diagram of a big data based intelligent knowledge management system, according to an embodiment of the present invention;
FIG. 2 schematically illustrates an exemplary architecture diagram of an information acquisition subsystem, according to an embodiment of the invention;
FIG. 3 schematically illustrates an exemplary architecture diagram of an information recommendation subsystem, according to an embodiment of the invention;
FIG. 4 schematically illustrates an exemplary architecture diagram of an information prediction subsystem, according to an embodiment of the present invention;
FIG. 5 schematically illustrates a flow diagram of a big data based intelligent knowledge management method according to an embodiment of the present invention;
fig. 6 schematically shows a flowchart of a method of determining a target learning case according to an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It is to be understood that such description is merely illustrative and not intended to limit the scope of the present invention. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the invention. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
In the technical scheme of the invention, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.
In the technical scheme of the invention, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.
The embodiment of the invention provides an intelligent knowledge management system based on big data, which is characterized in that an information acquisition subsystem is utilized to acquire first work skill attribute information and job hunting post information of a job seeker from a job hunting resume, a prediction model is utilized to match the job seeker with a job hunting post, and a recommendation case request is sent to an information recommendation subsystem under the condition that a matching result meets a preset condition. And then, the information recommendation subsystem determines a target learning case from the case database according to the first work skill attribute information and job hunting post information, and sends an information prediction request to the information prediction subsystem. The information prediction subsystem extracts additional work skill attribute information from the target learning case, generates second work skill attribute information by combining the first work skill attribute information, and predicts the loss risk according to the second work skill attribute information. The information prediction of the whole period from the job hunting stage to the job entering stage of the job seeker is achieved, so that a manager can conveniently make a related talent cultivation strategy according to the information prediction result, and the loss risk of knowledge resources is reduced.
FIG. 1 schematically shows an exemplary architecture of a big data based intelligent knowledge management system, according to an embodiment of the present invention.
As shown in fig. 1, an exemplary architecture 100 according to this embodiment may include an information acquisition subsystem 101, an information recommendation subsystem 102, an information prediction subsystem 103, a network 104, a client 105, and a cloud database 106. The network 104 is used to provide a medium for communication links between the information acquisition subsystem 101, the information recommendation subsystem 102, and the information prediction subsystem 103. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may use the client 105 to interact with the information acquisition subsystem 101, the information recommendation subsystem 102, the information prediction subsystem 103, to receive or send messages, etc., over the network 104. Various messaging client applications may be installed on client 105, such as a shopping-like application, a web browser application, a search-like application, an instant messaging tool, a mailbox client, social platform software, and so forth (by way of example only). The information acquisition subsystem 101 may interact with the client 105, for example: the user can send the recruitment information from the client 105 to the information acquisition subsystem 101 and acquire the matching result of the job seeker and the job hunting post from the information acquisition subsystem 101. The information prediction subsystem 103 may also obtain information on the loss risk prediction, so as to make a talent cultivation strategy for job seekers according to the information on the loss risk prediction.
The information acquisition subsystem 101 can acquire first work skill attribute information and job hunting position information of job seekers from job hunting resumes; inputting the first work skill attribute information and the job hunting post information into a preset model, and outputting a matching result; and sending a case recommendation request to the information recommendation subsystem 102 under the condition that the matching result meets the preset condition.
When the information recommendation subsystem 102 receives a recommendation case request sent by the information acquisition subsystem 101, acquiring first work skill attribute information and job hunting post information from the information acquisition subsystem 101; and determining a target learning case from the case database according to the first work skill attribute information and the job hunting post information, and sending an information prediction request to the information prediction subsystem 103.
When the information prediction subsystem 103 receives an information prediction request sent by the information recommendation subsystem 102, acquiring a target learning case and first work skill attribute information from the information recommendation subsystem; extracting additional work skill attribute information from the target learning case, wherein the additional work skill attribute information represents work skill attribute information which can be increased by the job seeker through learning the target learning case within a preset time period; generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information; and generating loss risk prediction information according to the second work skill attribute information.
According to the embodiment of the invention, the information acquisition subsystem 101, the information recommendation subsystem 102 and the information prediction subsystem 103 can be connected with each other through a Django framework, and can also be connected with the client 105 and the cloud database 106 through the Django framework. The cloud database 106 may be configured to store information in the big data-based intelligent knowledge management system, and may be used for the information acquisition subsystem 101, the information recommendation subsystem 102, and the information prediction subsystem 103 to jointly store information, and the cloud database may include a first database, a second database, and a third database. The first database is used for storing company information and information of matching results of job seekers and post information. The second database may be used to store job seeker information with matching results meeting preset conditions. The third database may be used to store resume information of job seekers whose matching results satisfy preset conditions. The company information may include: company name, main business, company brief introduction and position information. The station information may include: station name, station description, and station requirements. The information of the job seeker can comprise information of a user name, a password, a mailbox and the like of the job seeker.
It should be understood that the number of information acquisition subsystems, information recommendation subsystems, and information prediction subsystems, networks in fig. 1 are merely illustrative. There may be any number of information acquisition subsystems, information recommendation subsystems, and information prediction subsystems, as desired for an implementation.
The intelligent knowledge management system based on big data of the embodiment of the invention is described in detail through fig. 2 to fig. 4 based on the system described in fig. 1.
FIG. 2 schematically illustrates an exemplary architecture diagram of an information acquisition subsystem, according to an embodiment of the present invention.
As shown in fig. 2, the information acquiring subsystem 101 of this embodiment includes a registration login module 210, a first presentation module 220, a resume module 230, a matching module 240, a selection module 250, and a first administrator module 260.
And a registration login module 210, configured to register login information to obtain an access right of the information acquisition subsystem.
According to an embodiment of the present invention, the registration login module 210 may include a registration sub-module 211 and a login sub-module 212. The registration sub-module 211 may be configured to register information when the job seeker uses the big data based intelligent knowledge management system for the first time, where the registration information may include a user name, a password, a mailbox, and a randomly generated verification code. The login sub-module 212 may be used for the job seeker to log in using the username, password, etc. in the registration information. The login submodule can also perform MD5 encryption on the password in the registration information, and store the registration information in the cloud database.
The first display module 220 is configured to display information of the job hunting post and information of the interest selection interface.
According to an embodiment of the present invention, the interest selection interface information may include learning subject words corresponding to cases in the case database. The learning subject words may be obtained from the text information of the case using a subject learning algorithm.
According to an embodiment of the present invention, a method of extracting a learning subject word may include:
carrying out data cleaning on the text information of the target case, and removing symbols without actual meanings to obtain case text characteristic information;
inputting the case text characteristic information into a target function to obtain a TF-IDF value and a word frequency matrix;
and inputting the TF-IDF value and the word frequency matrix into a theme learning algorithm model function to obtain the learning subject words of the target case.
According to an embodiment of the present invention, the objective function may be a tfidvectorer function and a countvectorer function in skearn.
According to an embodiment of the present invention, the subject learning algorithm model function may be a latetdirichletalogation function.
According to the embodiment of the invention, in the process of creating the job-seeking resume, information can be input and resume attachments can be uploaded according to the prompt information of the text box. The prompt for the text box may include a project experience or practice experience, learned work skills, personal ratings, and the like.
According to the embodiment of the invention, the information acquisition subsystem can further comprise a post module for providing post information for the job seeker, so that the job seeker can select a target post from the post module as a job hunting post when creating the job hunting brief. It should be noted that the job seeker only has a viewing right for the post information, and does not have an addition, deletion, or modification right.
The matching module 240 is configured to predict a matching degree between the job seeker and the job hunting post according to the first work skill attribute information and the information of the job hunting post. For example: the first work skill attribute of the job seeker A is that the job seeker A has a marketing experience for many years, the information of the job hunting post is a marketing manager, the matching degree of the job seeker A and the job hunting post can be predicted through calculating the similarity of the work skill attribute information and the information of the job hunting post, and the matching between the job seeker A and the job hunting post is obtained.
And a selection module 250 for generating intention learning subject information according to the interest selection interface information. The interest selection interface may include a plurality of learning subject words, such as: subject A 1 Theme A 2 …, topic A n The job seeker can select the learning subject word that the job seeker is interested in on the interest selection interface, such as: subject A 1 And subject A n Then the intention learning topic information can be the topic A 1 And subject A n 。
And the first administrator module 260 is used for managing all information acquired by the information acquisition subsystem. For example: the information of the job hunting post displayed by the first display module can be added and modified, and when the matching result of the job hunter and the job hunting post meets the preset condition, the information of the user name, the password and the like of the job hunter can be stored in the second database, and the resume is stored in the third database.
According to the embodiment of the invention, the information acquisition subsystem can acquire the work skill attribute information of the job seeker, and the matching prediction of the job seeker and the job hunting post is carried out, so that the matching degree of the current work skill attribute of the job seeker and the job hunting post can be preliminarily determined, and whether the job seeker is to be introduced or not can be conveniently confirmed.
According to an embodiment of the invention, the matching module comprises:
the preprocessing unit is used for preprocessing the first work skill attribute information and the information of the job hunting post to obtain first work skill attribute characteristic information and characteristic information of the job hunting post;
and the matching unit is used for inputting the first work skill attribute characteristic information and the characteristic information of the job hunting post into a preset model to obtain the matching degree.
According to the embodiment of the invention, before matching the job seeker with the job hunting post, disambiguation processing needs to be carried out on job seeker work skill attribute information, such as: implicit information of protected characteristics such as age, region and nationality can be effectively reduced in a resistance training mode.
According to the embodiment of the invention, the preset model can be a human-job matching model, as shown in formulas (1-1, 1-2):
wherein D represents the predicted post matching degree, and tanh () is a hyperbolic function representing the prediction of the matching degree;
representing the logical function prediction tags, sigmoid () function is used for hidden layer neuron output, J represents a work position, R represents a resume of an external knowledge worker,
representing the topic distribution of the external knowledge worker resumes R,
a distribution of topics representing the job position J,
representing an applicant resume capability representation based on a hierarchical topic,
representing a hierarchical theme based job capability representation,
、
、
、
、
、
is a parameter that optimizes the network and,
、
is y ∈ [0,1]]Is determined by the parameters of (a) and (b),
representing the product at the element level.
According to the embodiment of the invention, the capability representation structure based on the hierarchy theme is obtained by inputting a skill label, a position label and an education background label into a long-short term memory network (LSTM). For example: the representation of the resume ability of the applicant based on the hierarchy theme is obtained by inputting a skill label and an education background label into a long-short term memory network (LSTM); the job capability representation based on the hierarchical theme is derived by inputting the job labels into a long short term memory network (LSTM).
According to the embodiment of the invention, the skill label and the education background label are obtained by processing semi-structured and unstructured data of first work skill attribute information such as job seeker skill, education background, project experience, work experience and the like acquired from a job-seeking resume by adopting a natural language processing technology, so that the first work skill attribute information is projected into word-level representation. The post label is obtained by projecting job hunting post information into word level representation by adopting a natural language processing technology.
According to the embodiment of the invention, the resume capability representation of the applicant based on the hierarchy theme and the job position capability representation based on the hierarchy theme are input into the preset model, and the parameters of the optimization network and the parameter values of y belonging to [0,1] are tested and adjusted to obtain the trained personnel matching model.
According to the embodiment of the invention, the disambiguated skill labels, post labels and education background labels are input into the trained personnel post matching model, and the matching result of the job seeker and the job hunting post is output.
According to an embodiment of the present invention, any plurality of the registration login module 210, the first presentation module 220, the resume module 230, the matching module 240, the selection module 250, and the first administrator module 260 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present invention, at least one of the registration login module 210, the first presentation module 220, the resume module 230, the matching module 240, the selection module 250, and the first administrator module 260 may be at least partially implemented as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or implemented by any one of three implementations of software, hardware, and firmware, or by a suitable combination of any of them. Alternatively, at least one of the registration login module 210, the first presentation module 220, the resume module 230, the matching module 240, the selection module 250, and the first administrator module 260 may be at least partially implemented as a computer program module that, when executed, may perform a corresponding function.
According to the embodiment of the invention, the first work skill attribute information and job hunting post information of the job seeker are accurately obtained, the matching result of the job seeker and the job hunting post is output by utilizing the post matching model, whether the job seeker meets the requirement of the job hunting post or not can be preliminarily determined, and the accuracy and the prediction efficiency of information prediction are improved.
FIG. 3 schematically illustrates an exemplary architecture diagram of an information recommendation subsystem, according to an embodiment of the invention.
As shown in fig. 3, the information recommendation subsystem 102 of this embodiment includes: a case recommendation module 310, a second presentation module 320, a research module 330, and a second administrator module 340.
The case recommendation module 310 is configured to determine a target learning case from the case database according to the first work skill attribute information and the job hunting post information;
according to the embodiment of the invention, on the basis of the first work skill attribute information and the information of job hunting posts, the target learning case can be determined from the case database based on the intention learning subject information selected by the job hunter on the interest selection interface of the information acquisition subsystem. And on the basis of the first work skill attribute information and the information of job hunting posts, screening out a target learning case from a case database based on an expert supervision recommendation algorithm which performs sequencing based on an expert supervision machine learning algorithm. And screening out a target learning case from the case database based on a clustering algorithm on the basis of the first work skill attribute information and the information of the job hunting post.
According to the embodiment of the invention, sub-modules corresponding to recommendation algorithms can be arranged in the case recommendation module, for example: the system comprises a personalized recommendation module corresponding to intention learning subject recommendation, an expert recommendation module corresponding to an expert supervision recommendation algorithm, and a clustering recommendation module corresponding to a clustering algorithm. When a case recommendation request of the information acquisition subsystem is received, the information recommendation subsystem can randomly distribute the case recommendation request to any one of the submodules to execute a corresponding case recommendation algorithm.
The second display module 320 is configured to display the target learning case, the learning method of the target learning case, and the operation description of the information recommendation subsystem.
According to the embodiment of the invention, the learning method of the target learning case can comprise a learning guidance part for introducing the learning process of the target learning case and completing the learning task. The operation specification of the information recommendation subsystem can comprise the operation sequence, the notice and the like of the information recommendation subsystem.
The investigation module 330 is configured to obtain feedback information of the target learning case recommended by the information recommendation subsystem.
According to the embodiment of the invention, the second display module can be combined to display the target learning case and simultaneously display the questionnaire, so that the job seeker can conveniently feed back the satisfaction degree of the functionality and the usability of the case recommended by the information recommendation subsystem by filling the questionnaire. The research results may also be obtained in other ways and then entered by the administrator into the research module of the information recommendation subsystem.
The second administrator module 340 is used for viewing and updating the case database in the information recommendation subsystem and the operation instruction of the information recommendation subsystem.
According to the embodiment of the invention, the case database in the information recommendation subsystem can be checked and updated according to the investigation result of the investigation module 330, and the operation description of the information recommendation subsystem can be updated after the version of the information recommendation subsystem is upgraded, and the like.
According to embodiments of the present invention, any of the case recommendation module 310, the second presentation module 320, the research module 330, and the second administrator module 340 may be combined in one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in one module. According to an embodiment of the present invention, at least one of the case recommendation module 310, the second presentation module 320, the research module 330, and the second administrator module 340 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or in any one of three implementations of software, hardware, and firmware, or in any suitable combination of any of them. Alternatively, at least one of the case recommendation module 310, the second presentation module 320, the research module 330, and the second administrator module 340 may be implemented at least in part as a computer program module that, when executed, may perform a corresponding function.
According to the embodiment of the invention, the information recommendation subsystem can provide three different logical case recommendation modes for job seekers, and the recommendation method based on intention learning theme can provide personalized case recommendation service for the job seekers; the recommendation method based on expert supervision can ensure the quality of case recommendation; the recommendation method based on the clustering algorithm can effectively expand the learnable range. By providing diversified target learning cases for the job hunters, the additional working skills which can be increased by the job hunters can be predicted in a diversified manner, and a foundation is laid for accurately predicting the trends of the job hunters.
FIG. 4 schematically illustrates an exemplary architecture diagram of an information prediction subsystem, according to an embodiment of the present invention.
As shown in fig. 4, the information prediction subsystem 103 includes an information extraction module 410, an information generation module 420, an information prediction module 430, and a transmission module 440.
An information extraction module 410 for extracting additional work skill attribute information from the target learning case.
According to the embodiment of the invention, natural language processing technology is adopted to extract additional skill labels which are possibly added by a job seeker from a target learning case, such as: item experience tags, task experience tags, and the like. And (4) carrying out clustering analysis on the additional skill labels by using a Brown clustering algorithm to obtain additional work skill attribute information.
According to the embodiment of the invention, the clustering analysis process of the additional skill labels by using the Brown clustering algorithm is as follows:
selecting the first n high-frequency skill labels from a plurality of additional skill labels as an initial class, and calculating an initial probability p 1 Edge weight w 1 And a loss function L 1 ；
Adding the (n + 1) th high-frequency skill tag into the initial class;
to is directed at
A plurality of different classes including n skill labels, and calculating the probability of each class
Edge weight
And loss function
；
Preserving functions with minimum loss
Forming a new clustering result to form a new initial class;
outputting an optimal clustering result to obtain additional skill attribute information through iterative calculation until all the additional skill tags are added;
and an information generating module 420, configured to generate second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information.
According to an embodiment of the invention, for example: the first work skill attribute information may include a skill attribute a 1 Skills Attribute A 2 And skill attribute A 3 . The additional skill attribute information may include a skill attribute B 1 . The generated second work skill attribute information may include a skill attribute a 1 Skills Attribute A 2 And skill attribute A 3 And skill attribute B 1 。
And the information prediction module 430 is configured to generate loss risk prediction information according to the second work skill attribute information.
According to the embodiment of the invention, the loss risk prediction information can be predicted by using the skill diversity of the second work skill attribute information of the job seeker. The skill diversity can be obtained by the following method:
and (3) calculating the proportion condition of the second working skill attribute information in each category of the optimal clustering result, and calculating the knowledge diversity by using an information entropy formula to obtain the skill diversity, wherein the information entropy formula is shown as a formula (2):
wherein the content of the first and second substances,
the method represents the diversity of the skills of the user,
is the proportion of additional skill labels owned by the internal knowledge workers in each category of the optimal clustering result,
is the weight of each category.
According to the embodiment of the invention, the loss prediction can be carried out by utilizing a Support Vector Machine (SVM) or an AdaBoost classification algorithm, so as to generate loss risk prediction information. For example: the job seeker work skill attribute information is combined into a feature data set A, the post variable worker work skill attribute information is combined into a feature data set B, the feature data set A and the feature data set B are input into a trained classification model, and the classification model can be obtained by optimization based on a Support Vector Machine (SVM) or AdaBoost classification algorithm and combined with a grid cross search method. Training a classification model by a Support Vector Machine (SVM) or an AdaBoost classification algorithm is a mature training method, and is not described herein again.
And a sending module 440, configured to send the attrition risk prediction information to the client.
According to the embodiment of the invention, the loss risk prediction information can be sent to the client, so that a manager can conveniently make a corresponding talent cultivation strategy according to the loss risk prediction information.
According to the embodiment of the present invention, any plurality of the information extraction module 410, the information generation module 420, the information prediction module 430, and the transmission module 440 may be combined into one module to be implemented, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present invention, at least one of the information extraction module 410, the information generation module 420, the information prediction module 430, and the transmission module 440 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or may be implemented in any one of three implementations of software, hardware, and firmware, or in any suitable combination of any of them. Alternatively, at least one of the information extraction module 410, the information generation module 420, the information prediction module 430, and the transmission module 440 may be at least partially implemented as a computer program module that, when executed, may perform a corresponding function.
According to the embodiment of the invention, the skill diversity of the job seeker is obtained by adopting the clustering algorithm and the information entropy algorithm, the loss risk is predicted according to the skill diversity, and the prediction accuracy is improved.
FIG. 5 schematically shows a flow diagram of a big data based intelligent knowledge management method according to an embodiment of the invention.
As shown in FIG. 5, the big-data based intelligent knowledge management method of this embodiment includes operations S510 to S570.
In operation S510, first work skill attribute information of a job seeker and information of a job hunting position are acquired from a job hunting resume in response to a job hunting request from a client.
According to an embodiment of the present invention, the first work skill attribute information may include information of an educational experience, a work experience, and the like. The information of the job hunting post may include post demand information.
In operation S520, the first work skill attribute information and the job hunting post information are input into a preset model, and a matching result is output.
According to the embodiment of the invention, the preset model can be a post matching model in the embodiment of the invention, the first work skill attribute information and the job hunting post information are input into the post matching model, and the output matching result can be the post matching degree.
In operation S530, in the case that the matching result satisfies the preset condition, a target learning case is determined from the case database according to the first work skill attribute information and the information of the job hunting post.
According to the embodiment of the invention, the preset condition can be that the post matching degree meets the preset threshold value, and the skill attribute of the job seeker meets the post requirement of the job hunting post. Under the condition that the job seeker meets the post requirement of the job hunting post, the information recommendation subsystem randomly distributes the related information of the job seeker to the recommendation submodule according to the skill attribute information and the job hunting post information of the job seeker, and recommends the target learning case to the job seeker according to different recommendation algorithms.
In operation S540, additional work skill attribute information is extracted from the target learning case, wherein the additional work skill attribute information represents work skill attribute information that can be added by the candidate through learning the target learning case within a preset time period.
According to an embodiment of the invention, for example: the job seeker is an upcoming graduate, the work experience in the first work skill attribute is empty, and through the learning of the target learning case, the work skill attribute information which can be added after the job seeker learns the experience and practices the target learning case can be determined, such as: can be the project experience corresponding to the target learning case, and so on. The additional work skill attributes may be work skill attribute information that can be learned assuming the job seeker has passed through the learning target learning case.
In operation S550, second work skill attribute information is generated according to the first work skill attribute information and the additional work skill attribute information.
According to the embodiment of the invention, the second work skill attribute information can represent new work skill attribute information obtained by a job seeker after additional work skill attribute information is added through the learning of a target learning case on the basis of the original first work skill attribute information.
In operation S560, loss risk prediction information is generated according to the second work skill attribute information, wherein the loss risk prediction information represents a variation risk of the job seeker after learning the target learning case.
According to the embodiment of the invention, the information prediction subsystem can input the second work skill attribute information of the job seeker and the work skill attribute information of the staff with the position change, which is stored in the system, into the trained classification model according to the second work skill attribute information through the trained classification model, and analyze the risk of the job seeker with the position change in the future from the viewpoint of skill diversity.
In operation S570, attrition risk prediction information is sent to the client.
According to the embodiment of the invention, the loss risk prediction information is sent to the client, so that a manager can make or adjust the talent culture strategy in time, and the retention degree of talent knowledge is improved.
According to the embodiment of the invention, the step of inputting the first work skill attribute information and the job hunting post information into a preset model and outputting a matching result comprises the following steps:
preprocessing the first work skill attribute information and the information of job hunting posts to obtain first work skill attribute characteristic information and job hunting post characteristic information;
and inputting the first work skill attribute characteristic information and job hunting post characteristic information into a preset model, and outputting a matching result.
According to an embodiment of the invention, the pre-processing may be disambiguation processing, such as: by identifying the implicit information of protected characteristics such as gender, age, region, nationality and the like in the first functional skill attribute characteristic information, antagonism training can be adopted, the leakage of the protected attributes is effectively reduced, and the fairness of the post matching result is improved.
Fig. 6 schematically shows a flowchart of a method of determining a target learning case according to an embodiment of the present invention.
According to an embodiment of the present invention, a method of determining a target learning case of the embodiment includes operations S610 to S620.
In operation S610, a target learning theme is determined according to the first work skill attribute information and the job hunting post information;
according to the embodiment of the invention, the target learning theme can be determined according to the first work skill attribute information and the keywords in the post requirements in the information of the job hunting post. For example: the post requirement comprises skill A, but the first work skill attribute information lacks skill A, the keyword can be skill A, and the skill A is taken as a target learning subject.
According to the embodiment of the invention, the target learning theme can be determined by combining the interests of job seekers on the basis of the first work skill attribute information and the information of job hunting posts. The method for determining the target learning theme comprises the following steps:
responding to the selection operation of the job seeker on the interest selection interface from the client, and acquiring intention learning subject information of the job seeker;
and determining a target learning theme according to the first work skill attribute information, the intention learning theme information and the job hunting post information.
According to embodiments of the invention, the target learning skills may also be combined with interests of the job seeker, such as: a job requirement includes skill a, but the lack of skill a in the first work skill attribute information may determine that skill a is the target learning topic. However, the learning case for skill a may include a plurality of candidate learning topics, and in this case, the target learning topic may be determined from the plurality of candidate learning topics according to intention learning topic information of the candidate.
In operation S620, a target learning case is determined from the case database according to the target learning topic.
According to the embodiment of the invention, a plurality of candidate learning case text messages are obtained from a case database according to the first work skill attribute information and the job hunting post information; inputting a plurality of candidate learning case text information into a character vector conversion model, and outputting a plurality of candidate learning case vectors; and based on a random forest algorithm or a clustering algorithm, screening vectors corresponding to the target learning case from the multiple candidate learning case vectors to determine the target learning case.
According to an embodiment of the present invention, an expert supervised recommendation algorithm may be employed to determine target learning cases from a case database, for example: m learning cases can be determined from the case database according to the target learning theme, and the text information of the m learning cases can be input into the character vector conversion model to obtain the vector data of the learning cases. And then dividing the vector data of the learning case into a training data set and a testing data set, and labeling the vector data in the training data set. Training the random forest algorithm model by using the training data set, calling parameters of the random forest algorithm model by using the test data set to obtain a recommendation score of the test data set, and taking a learning case corresponding to vector data with the recommendation score ranked three-first as a target learning case.
According to the embodiment of the invention, a clustering recommendation method can be further adopted to determine the target learning case from the case database, for example: the m learning cases can be determined from the case database according to the target learning theme, and the text information of the m learning cases can be input into the character vector conversion model to obtain the vector data of the learning cases. And then, carrying out clustering analysis on the vector data by using a K-means algorithm to obtain a plurality of groups of clustering case sets, wherein any one group of clustering case sets can be randomly used as a target learning case. And the learning case corresponding to the clustering center in the clustering case set can be used as the target learning case.
It will be appreciated by a person skilled in the art that various combinations and/or combinations of features described in the various embodiments and/or in the claims of the invention are possible, even if such combinations or combinations are not explicitly described in the invention. In particular, the features recited in the various embodiments and/or claims of the invention may be combined and/or coupled in various ways without departing from the invention. All such combinations and/or associations are within the scope of the present invention.
The embodiments of the present invention have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the invention is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the invention, and these alternatives and modifications are intended to fall within the scope of the invention.
Claims (10)
1. An intelligent knowledge management system based on big data, comprising:
the information acquisition subsystem is used for responding to a job hunting request from the client and acquiring first work skill attribute information and job hunting post information of a job seeker from a job hunting resume; inputting the first work skill attribute information and the information of the job hunting post into a preset model, and outputting a matching result; sending a recommended case request to an information recommendation subsystem under the condition that the matching result meets a preset condition;
the information recommendation subsystem is used for responding to the recommended case request from the information acquisition subsystem and acquiring the first work skill attribute information and the information of the job hunting post from the information acquisition subsystem; determining a target learning case from a case database according to the first work skill attribute information and the job hunting post information, and sending an information prediction request to an information prediction subsystem;
the information prediction subsystem is used for responding to the information prediction request from the information recommendation subsystem and acquiring the target learning case and the first work skill attribute information from the information recommendation subsystem; extracting additional work skill attribute information from the target learning case, wherein the additional work skill attribute information represents work skill attribute information which can be added by the job seeker through learning the target learning case within a preset time period; generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information; generating loss risk prediction information according to the second work skill attribute information, wherein the loss risk prediction information represents a change risk of the candidate after learning the target learning case; and sending the loss risk prediction information to the client.
2. The system of claim 1, wherein the information acquisition subsystem comprises:
the registration login module is used for registering login information so as to acquire the access authority of the information acquisition subsystem;
the first display module is used for displaying the information of the job hunting post and the interest selection interface information;
the resume module is used for editing resume information for job hunting;
the matching module is used for predicting the matching degree of the job seeker and the job hunting post according to the first work skill attribute information and the information of the job hunting post;
the selection module is used for generating intention learning subject information according to the interest selection interface information;
and the first administrator module is used for managing all the information acquired by the information acquisition subsystem.
3. The system of claim 2, wherein the matching module comprises:
the preprocessing unit is used for preprocessing the first work skill attribute information and the information of the job hunting post to obtain first work skill attribute characteristic information and characteristic information of the job hunting post;
and the matching unit is used for inputting the first work skill attribute characteristic information and the characteristic information of the job hunting post into the preset model to obtain the matching degree.
4. The system of claim 1, wherein the information recommendation subsystem comprises:
the case recommendation module is used for determining a target learning case from a case database according to the first work skill attribute information and the information of the job hunting post;
the second display module is used for displaying a target learning case, a learning method of the target learning case and an operation description of the information recommendation subsystem;
the investigation module is used for acquiring feedback information of the target learning case recommended by the information recommendation subsystem;
and the second administrator module is used for viewing and updating the case database in the information recommendation subsystem and the operation instruction of the information recommendation subsystem.
5. The system of claim 1, wherein the information prediction subsystem comprises:
the information extraction module is used for extracting additional work skill attribute information from the target learning case;
the information generation module is used for generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information;
the information prediction module is used for generating loss risk prediction information according to the second work skill attribute information;
and the sending module is used for sending the loss risk prediction information to the client.
6. An intelligent knowledge management method based on big data, which applies the intelligent knowledge management system based on big data of any one of claims 1 to 5, and is characterized by comprising the following steps:
acquiring first work skill attribute information and job hunting position information of job hunters from job hunting resumes in response to job hunting requests from a client;
inputting the first work skill attribute information and the information of the job hunting post into a preset model, and outputting a matching result;
determining a target learning case from a case database according to the first work skill attribute information and the job hunting post information under the condition that the matching result meets a preset condition;
extracting additional work skill attribute information from the target learning case, wherein the additional work skill attribute information represents work skill attribute information which can be added by the job seeker through learning of the target learning case within a preset time period;
generating second work skill attribute information according to the first work skill attribute information and the additional work skill attribute information;
generating loss risk prediction information according to the second work skill attribute information, wherein the loss risk prediction information represents a change risk of the candidate after learning the target learning case; and
and sending the loss risk prediction information to the client.
7. The method according to claim 6, wherein inputting the first work skill attribute information and the job hunting position information into a preset model and outputting a matching result comprises:
preprocessing the first work skill attribute information and the information of the job hunting post to obtain first work skill attribute characteristic information and characteristic information of the job hunting post;
and inputting the first work skill attribute characteristic information and the characteristic information of the job hunting post into the preset model, and outputting the matching result.
8. The method of claim 6, wherein determining a target learning case from a database of cases based on the first work skill attribute information and the job hunting position information comprises:
determining a target learning theme according to the first work skill attribute information and the information of the job hunting posts;
and determining a target learning case from the case database according to the target learning theme.
9. The method of claim 8, wherein determining a target learning topic based on the first work skill attribute information and the job hunting post information comprises:
responding to the selection operation of the job seeker on an interest selection interface from a client, and acquiring intention learning subject information of the job seeker;
and determining a target learning theme according to the first work skill attribute information, the intention learning theme information and the job hunting post information.
10. The method of claim 6, wherein determining a target learning case from a database of cases based on the first work skill attribute information and the job hunting position information comprises:
acquiring a plurality of candidate learning case text messages from a case database according to the first work skill attribute information and the job hunting post information;
inputting the text information of the multiple alternative learning cases into a character vector conversion model, and outputting multiple alternative learning case vectors;
and based on a random forest algorithm or a clustering algorithm, screening vectors corresponding to the target learning case from the multiple candidate learning case vectors to determine the target learning case.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210865419.8A CN114925287B (en) | 2022-07-22 | 2022-07-22 | Intelligent knowledge management system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210865419.8A CN114925287B (en) | 2022-07-22 | 2022-07-22 | Intelligent knowledge management system and method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114925287A true CN114925287A (en) | 2022-08-19 |
| CN114925287B CN114925287B (en) | 2022-11-18 |
Family
ID=82815901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210865419.8A Active CN114925287B (en) | 2022-07-22 | 2022-07-22 | Intelligent knowledge management system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114925287B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139108A (en) * | 2015-08-06 | 2015-12-09 | 天津人众和软件开发有限公司 | Talents ability assessment and post matching method and system |
| CN109460976A (en) * | 2018-11-02 | 2019-03-12 | 广州至拓网络科技有限公司 | A kind of personal scheduling and enterprises recruitment comprehensive management platform |
| CN110634018A (en) * | 2019-08-30 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Feature depiction method, recognition method and related device for lost user |
| CN111369044A (en) * | 2020-02-27 | 2020-07-03 | 腾讯云计算（北京）有限责任公司 | Method and device for estimating loss and computer readable storage medium |
| CN111861588A (en) * | 2020-08-06 | 2020-10-30 | 网易（杭州）网络有限公司 | Training method of loss prediction model, player loss reason analysis method and player loss reason analysis device |
| CN112182383A (en) * | 2020-09-28 | 2021-01-05 | 平安数字信息科技(深圳)有限公司 | Recommendation method and device for second post and computer equipment |
| CN112257777A (en) * | 2020-10-21 | 2021-01-22 | 平安科技（深圳）有限公司 | Off-job prediction method based on hidden Markov model and related device |
| CN113780673A (en) * | 2021-09-22 | 2021-12-10 | 湖北天天数链技术有限公司 | Training method and device of job leaving prediction model and job leaving prediction method and device |
| 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 |
| CN114549051A (en) * | 2022-01-19 | 2022-05-27 | 北京百度网讯科技有限公司 | Cross-regional talent flow intention analysis method, device, equipment and storage medium |
-
2022
- 2022-07-22 CN CN202210865419.8A patent/CN114925287B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105139108A (en) * | 2015-08-06 | 2015-12-09 | 天津人众和软件开发有限公司 | Talents ability assessment and post matching method and system |
| CN109460976A (en) * | 2018-11-02 | 2019-03-12 | 广州至拓网络科技有限公司 | A kind of personal scheduling and enterprises recruitment comprehensive management platform |
| CN110634018A (en) * | 2019-08-30 | 2019-12-31 | 阿里巴巴集团控股有限公司 | Feature depiction method, recognition method and related device for lost user |
| CN111369044A (en) * | 2020-02-27 | 2020-07-03 | 腾讯云计算（北京）有限责任公司 | Method and device for estimating loss and computer readable storage medium |
| CN111861588A (en) * | 2020-08-06 | 2020-10-30 | 网易（杭州）网络有限公司 | Training method of loss prediction model, player loss reason analysis method and player loss reason analysis device |
| CN112182383A (en) * | 2020-09-28 | 2021-01-05 | 平安数字信息科技(深圳)有限公司 | Recommendation method and device for second post and computer equipment |
| CN112257777A (en) * | 2020-10-21 | 2021-01-22 | 平安科技（深圳）有限公司 | Off-job prediction method based on hidden Markov model and related device |
| CN113780673A (en) * | 2021-09-22 | 2021-12-10 | 湖北天天数链技术有限公司 | Training method and device of job leaving prediction model and job leaving prediction method and device |
| 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 |
| CN114549051A (en) * | 2022-01-19 | 2022-05-27 | 北京百度网讯科技有限公司 | Cross-regional talent flow intention analysis method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 陈沛光: "基于随机森林模型的电力企业员工离职倾向预测研究", 《化工管理》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114925287B (en) | 2022-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11704677B2 (en) | Customer support ticket aggregation using topic modeling and machine learning techniques | |
| US11507989B2 (en) | Multi-label product categorization | |
| US11188720B2 (en) | Computing system including virtual agent bot providing semantic topic model-based response | |
| US10853697B2 (en) | System and method for monitoring online retail platform using artificial intelligence and fixing malfunction | |
| Zhang et al. | Detection of social network spam based on improved extreme learning machine | |
| Korzh et al. | Methods for forming an informational image of a higher education institution. | |
| CA3052527A1 (en) | Target document template generation | |
| US11249751B2 (en) | Methods and systems for automatically updating software functionality based on natural language input | |
| AU2021229151A1 (en) | Decision support system and methods associated with same | |
| US11900320B2 (en) | Utilizing machine learning models for identifying a subject of a query, a context for the subject, and a workflow | |
| US11694443B2 (en) | Automatic identification of misleading videos using a computer network | |
| Pishgoo et al. | A hybrid distributed batch-stream processing approach for anomaly detection | |
| Zhou et al. | Tagrec: Leveraging tagging wisdom for recommendation | |
| Bhattacharjee et al. | Identifying extremism in social media with multi-view context-aware subset optimization | |
| Darias et al. | Using case-based reasoning for capturing expert knowledge on explanation methods | |
| Al-Rawahnaa et al. | Data mining for Education Sector, a proposed concept | |
| Wang et al. | Skill inference with personal and skill connections | |
| Khaleelullah et al. | A Framework for Design and Development of Message sharing using Open-Source Software | |
| US20210304042A1 (en) | Data Filtering With Fuzzy Attribute Association | |
| Haffar et al. | Explaining image misclassification in deep learning via adversarial examples | |
| CN114925287B (en) | Intelligent knowledge management system and method based on big data | |
| Tseng et al. | Applying a hybrid data-mining approach to prediction problems: a case of preferred suppliers prediction | |
| CN115660695A (en) | Customer service personnel label portrait construction method and device, electronic equipment and storage medium | |
| AU2020101842A4 (en) | DAI- Dataset Discovery: DATASET DISCOVERY IN DATA ANALYTICS USING AI- BASED PROGRAMMING. | |
| Khatun et al. | Machine Learning based Advanced Crime Prediction and Analysis |
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 |