CN112417280A - Recommendation method and system based on virtual reality moderator system - Google Patents
Recommendation method and system based on virtual reality moderator system Download PDFInfo
- Publication number
- CN112417280A CN112417280A CN202011309342.3A CN202011309342A CN112417280A CN 112417280 A CN112417280 A CN 112417280A CN 202011309342 A CN202011309342 A CN 202011309342A CN 112417280 A CN112417280 A CN 112417280A
- Authority
- CN
- China
- Prior art keywords
- recommendation
- recruitment
- job seeker
- job
- target
- 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.)
- Withdrawn
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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Mathematical Optimization (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a recommendation method based on a virtual reality moderator system, which comprises the following steps: acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter; establishing a host matrix, and when a real host and a digital host in the host matrix jointly log in a recruitment website (the recruitment website refers to a PC recruitment website, a mobile phone recruitment APP and an Internet recruitment platform, the same is true), performing recommendation guidance based on the first target requirement and the second target requirement; and sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule. The method solves the problem that virtual hosts and real hosts in various industries jointly guide and recommend job seekers or recruiters, meanwhile, the job hunting positions in the most important recruiting companies in the day are recommended to the job seekers in an audio and video mode, the most important job seekers in the day are recommended to the job seekers in the audio and video mode, and the recommendation is convenient to perform recommendation according to the preset proportion based on the fuzzy and precision recommendation algorithm analysis.
Description
Technical Field
The invention relates to the technical field of website & ap job hunting and recruitment recommendation, in particular to a recommendation method and a recommendation system based on a virtual reality host system.
Background
With the falling of the idea of big data, the recommendation method and system are gradually popular in the industry, and the benefit brought to the internet is immeasurable. Not only the e-commerce, various internet industries have slowly introduced recommendation technologies such as: movie websites, music players, social platforms, job hiring, dining services, and the like. For a recommendation system, the quality of a recommendation result seriously affects the service evaluation of a user.
However, the recommendation function established in most of the current small and medium-sized applications is inaccurate in recommendation result due to unreasonable algorithm strategy selection and design, particularly in job position recruitment, a job seeker cannot timely and fully know about a job hunting post, and a recruiter cannot comprehensively and objectively know about the job seeker, so that the two parties cannot efficiently solve the self-demand, and therefore, the invention provides the recommendation method and the recommendation system based on the virtual reality host system.
Disclosure of Invention
The invention provides a recommendation method and a recommendation system based on a virtual reality host system, which are used for conveniently guiding and recommending job seekers or recruiters through the joint login of a virtual host and a real host.
The invention provides a recommendation method based on a virtual reality moderator system, which comprises the following steps:
acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter;
establishing a host matrix, and performing recommendation guidance based on the first target requirement and the second target requirement when a real host and a digital host in the host matrix jointly log in a recruitment website;
and sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule.
Preferably, the recommendation method based on the virtual reality moderator system obtains the first target requirement of the job seeker, and includes:
acquiring resume information of a job seeker, wherein the resume information comprises identity attributes, job hunting positions, target salaries and professional directions of the job seeker, and receiving pending intention positions determined by the job seeker in a plurality of positions;
performing weight sequencing according to the job hunting post, target salaries and the requirement degree of the job hunting post of the intention to be decided by the job hunter and the professional direction by constructing a job hunter demand space model to obtain a final target post;
wherein the final target post is the first target requirement.
Preferably, after acquiring the second target requirement of the recruiter, the recommendation method based on the virtual reality host system further includes:
acquiring a position index associated with the recruiting position, wherein the position index comprises the number of required persons of the position, the position capacity and the minimum academic requirement;
and calling a test question corresponding to the recruitment position from a test database based on the position index, generating a post recruitment test paper, and presenting the post recruitment test paper to the job seeker.
Preferably, the recommendation method based on the virtual reality moderator system further includes the specific process of establishing a moderator matrix:
establishing a host guidance mode and a job target association table based on the first target requirement of the job seeker and the second target requirement of the recruiter, calling host data in a preset host database, and establishing an association matrix;
the server constructs a fuzzy relation model for the identity attribute of the job seeker and the corresponding relation of the host needing to be guided, and obtains a fuzzy relation matrix through preset rule conversion;
after the incidence matrix and the fuzzy matrix are subjected to elementary change, a host matrix is obtained;
the moderator matrix includes: social recruitment, campus recruitment, overseas recruitment, hunting, mechanic recruitment, handicapped recruitment, retired soldier recruitment, maritime recruitment, foreign membership recruitment, team creation, recruitment, training of a host and the like.
Preferably, the recommendation method based on the virtual reality moderator system performs a recommendation guidance process based on the first target requirement and the second target requirement, and further includes:
acquiring the first target requirement and the second target requirement, and inputting the first target requirement and the second target requirement into a data conversion model, wherein the data conversion model converts the first target requirement and the second target requirement into corresponding first data information and second data information according to a preset rule;
constructing an expert data analysis model based on the first target requirement and the second target requirement, and inputting the first data information and the second data information into the expert data analysis model for classification processing, wherein the method specifically comprises the following steps:
identifying keywords in the first data information and the second data information, and transmitting the keywords into the expert data analysis model;
searching a position or a recruitment position with the highest relevance from the preset position library according to the received keyword, and transmitting the position or the recruitment position to a host terminal through a background;
the host terminal comprises a virtual host terminal and a real host terminal;
the host terminal performs big data analysis on the positions or the recruitment positions through a preset capability analysis model to obtain position guidance data information, and screens the guidance data information through preset judgment conditions to obtain target guidance data;
converting target guidance data obtained by analysis of a host into corresponding audio and video data according to a standardized protocol;
constructing a communication link between the host and the job seeker or the recruiter;
and transmitting the audio and video data to a target end corresponding to a job seeker or a recruiter based on the communication link, receiving a problem proposed by the job seeker or the recruiter based on the communication link, converting the problem into a corresponding digital signal through a digital-to-analog conversion database in the communication link, and carrying out coding transmission on the digital signal, thereby realizing the joint communication guidance between the job seeker or the recruiter and the virtual supporters and among real person presenters.
Preferably, the recommendation method based on the virtual reality host system sends the corresponding recommendation guidance result to the target terminals corresponding to the job seeker and the recruiter, and includes:
acquiring intention position information of the job seeker and first evaluation corresponding to the intention position information, and recommending a first recommended position associated with the intention position according to the first evaluation;
acquiring other post information delivered by the job seeker within a preset time period and second evaluation corresponding to the post information, and recommending a second recommended post associated with the intention post according to the second evaluation;
comparing the relevance of the first recommended position and the intention position and the relevance of the second recommended position and the intention position, and recommending the position with high relevance to the job seeker;
meanwhile, capturing the job seeker application information in the recruitment website through a web crawler to form an application information set, removing job seekers which are not matched with the indispensable items of the recruitment post requirement information in the application information set, and taking the rest job seekers as a first recommended job seeker set;
eliminating the job seekers of which the capability information of the job seekers in the first set of recommended job seekers does not meet the necessary item of the requirement information of the recruitment post, and taking the rest job seekers as a second job seeker recommendation set;
and calculating the similarity between the capability information of each job seeker in the second job seeker recommendation set and the recruitment position information, screening the first N job seekers with the highest similarity to the recruitment position to generate a job seeker recommendation list, and recommending the job seeker recommendation list to the recruiters.
Preferably, the recommendation method based on the virtual reality moderator system further includes, when recommending to the job seeker or the recruiter:
constructing a fuzziness and precision recommendation algorithm, and recommending the recruitment website according to a preset proportion of the fuzziness and precision recommendation algorithm when the recruitment website recommends to the job seeker or the recruiter;
acquiring user attribute information of the job seeker and the recruiter, wherein the user attribute information comprises a minimum deadline allowed for a recruitment position in the job seeker or the recruiting company and an urgency level of a demand for the recruitment position in the job seeker or the recruiting company;
determining the weight of the urgency degree of the demand of the job seeker or the recruitment position in the recruitment company, and sorting the job seekers on the same day and the recruitment position in the recruitment company according to the minimum deadline to generate an importance degree sorting table;
and recommending the job seeker with the top rank in the importance ranking list to the recruiter in an audio and video mode based on the preset proportion of the ambiguity and precision recommendation algorithm, and simultaneously recommending the recruitment position in the recruitment company with the top rank to the job seeker in an audio and video mode to complete bidirectional recommendation.
Preferably, the method for recommending based on the virtual reality host system, according to a preset recommendation rule, in the process of sending the corresponding recommendation guidance result to the target ends corresponding to the job seeker and the recruiter, further includes:
calculating the recommendation weight adopting the ambiguity recommendation algorithm according to the following formula:
wherein eta is1Representing a recommendation weight using the digital fuzzy recommendation algorithm; alpha represents the number of the first indexes of the corresponding job seekers or recruiters when the digital fuzzy recommendation algorithm is adopted for recommendation, wherein the first indexes comprise basic conditions, and the value range is [0,8 ]](ii) a Delta represents an important indicator in the job seeker or recruiter requirement information; e represents a very important index in the requirement information of the job seeker or the recruiter; mu represents a very important index in the request information of the job seeker or the recruiter; beta represents the number of the second indexes of the job seeker or the recruiter containing the necessary conditions when the digital fuzzy recommendation algorithm is adopted for recommendation, and the value range is [0, 4 ]]；
Calculating the weight of the accuracy recommendation algorithm according to the recommendation weight of the ambiguity recommendation algorithm:
wherein eta is2Representing the recommendation weight when the accurate recommendation algorithm is adopted for recommendation; sigma represents a weight coefficient of the precise recommendation algorithm; eta1Representing the recommendation weight when the digital fuzzy recommendation algorithm is adopted for recommendation;
a weighted average coefficient representing the accuracy recommendation algorithm;
calculating the fault tolerance rate of the recruitment website during recommendation according to the following formula:
wherein p represents the fault tolerance of the recruitment website during recommendation; theta represents a fault tolerance coefficient when the recruitment website is recommended; eta2Representing the recommendation weight when the accurate recommendation algorithm is adopted for recommendation; eta1Representing the recommendation weight when the digital fuzzy recommendation algorithm is adopted for recommendation; gamma represents the number of times of errors in recommendation in the recruitment website recommendation period; k represents the total number of recommendations within the recruitment website recommendation period; tau represents the maximum number of times of errors allowed in the total number of times of recommendation in the recruitment website recommendation period; ζ represents a correction coefficient of the recruiting website;
comparing the calculated fault tolerance with a preset fault tolerance;
and if the fault tolerance rate is lower than the preset fault tolerance rate, the recruitment website reminds the job seeker or the recruiter to modify the importance degree index in the information.
Preferably, a recommendation system based on a virtual reality moderator system:
the acquisition module is used for acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter;
the recommendation guidance module is used for establishing a host matrix, and performing recommendation guidance based on the first target requirement and the second target requirement when a real host and a digital host in the host matrix jointly log in a recruitment website;
and the result pushing module is used for sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart of a recommendation method based on a virtual reality presenter architecture in an embodiment of the present invention;
fig. 2 is a structural diagram of a recommendation system based on a virtual reality presenter architecture in an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The invention provides a recommendation method based on a virtual reality moderator system, which comprises the following steps as shown in figure 1:
acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter;
establishing a host matrix, and performing recommendation guidance based on the first target requirement and the second target requirement when a real host and a digital host in the host matrix jointly log in a recruitment website;
and sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule.
In this embodiment, the first target requirement refers to an ideal recruiting position of the job seeker, and the ideal recruiting position includes salary treatment, academic requirement, and the like.
In this embodiment, the second target requirement refers to a target requirement of the recruiter for the job seeker to apply the recruiting position, and the target requirement includes job-taking ability, work experience, and the like.
In this embodiment, the host matrix is to enable the website to receive hosts of a plurality of industries and different identity attributes, so that the website can select corresponding hosts according to conditions of job seekers and recruiters.
In the embodiment, the recommendation rules are preset, and recommendation is performed by constructing a fuzzy recommendation algorithm and a precision recommendation algorithm in the website according to the proportion of the two recommendation algorithms.
In this embodiment, the recommendation guidance result refers to that the host recommends the most important recruitment information to the job seeker on the same day, and recommends the most important job seeker information to the recruiter.
The beneficial effects of the above technical scheme are: the virtual host and the real host in various industries jointly log in, so that guidance and recommendation can be conveniently performed on job seekers or recruiters.
The invention provides a recommendation method based on a virtual reality host system, which is used for acquiring a first target requirement of a job seeker and comprises the following steps:
acquiring resume information of a job seeker, wherein the resume information comprises identity attributes, job hunting positions, target salaries and professional directions of the job seeker, and receiving pending intention positions determined by the job seeker in a plurality of positions;
performing weight sequencing according to the job hunting post, target salaries and the requirement degree of the job hunting post of the intention to be decided by the job hunter and the professional direction by constructing a job hunter demand space model to obtain a final target post;
wherein the final target post is the first target requirement.
In this embodiment, the identity attribute refers to the group to which the job seeker belongs, for example: disabled, retired military, due graduate, etc.
In this embodiment, the intended positions refer to positions that the job seeker prefers to select, as some of the alternatives.
In this embodiment, the job seeker demand space model is used to compare different treatments of the same aspect in the job seeker's intent to treat, and then delete the treatments according to the importance degree to obtain the final selected post.
The beneficial effects of the above technical scheme are: the resume information of the job seeker is obtained, the job hunting post, the target salary and the like in the resume of the job seeker are determined, the post is screened according to the requirements of the job seeker, the post to be determined is obtained, different treatments on the same side are compared in the post to be determined, the target post most suitable for the job seeker is obtained, and the job post most suitable for the job seeker is screened out from a large number of job hunting posts.
The invention provides a recommendation method based on a virtual reality host system, which comprises the following steps of after acquiring a second target requirement of a recruiter:
acquiring a position index associated with the recruiting position, wherein the position index comprises the number of required persons of the position, the position capacity and the minimum academic requirement;
and calling a test question corresponding to the recruitment position from a test database based on the position index, generating a post recruitment test paper, and presenting the post recruitment test paper to the job seeker.
In this embodiment, the job indicator refers to a line of basic condition definition, such as the required number of people and the minimum scholarship, made by the recruiter for the job seeker who applies the job.
The beneficial effects of the above technical scheme are: the recruitment post is limited, so that screening from massive job seekers is facilitated, meanwhile, the position indexes are called from the test database from the test questions corresponding to the recruitment post, all the test questions are collected to generate a recruitment test paper, so that the job seekers can screen again according to the answer result of the test paper, the job seekers most suitable for the post are selected, and the relevance of the post job recruiters is improved.
The invention provides a recommendation method based on a virtual reality moderator system, which is a specific process for establishing a moderator matrix and further comprises the following steps:
establishing a host guidance mode and a job target association table based on the first target requirement of the job seeker and the second target requirement of the recruiter, calling host data in a preset host database, and establishing an association matrix;
the server constructs a fuzzy relation model for the identity attribute of the job seeker and the corresponding relation of the host needing to be guided, and obtains a fuzzy relation matrix through preset rule conversion;
after the incidence matrix and the fuzzy matrix are subjected to elementary change, a host matrix is obtained;
the moderator matrix includes: social recruitment, campus recruitment, overseas recruitment, hunting, mechanic recruitment, handicapped recruitment, retired soldier recruitment, maritime recruitment, foreign membership recruitment, team creation, recruitment, training of a host and the like.
In this embodiment, the moderator guidance mode refers to a method for a moderator to guide recommendation after a job seeker enters a corresponding job hunting interface.
In this embodiment, the moderator category data refers to a moderator category including all preset industries and preset different identity attributes.
In this embodiment, the identity attribute of the candidate refers to the category of the crowd to which the candidate belongs, such as: haizui, disabled, etc.
In this embodiment, the fuzzy relation matrix is used to represent the correspondence between the job seeker and the host, and includes that one job seeker may correspond to multiple hosts at the same time, for example: the job seeker may be a disabled person and a homed, and the corresponding host is of two types.
In this embodiment, the moderator matrix is obtained by combining the incidence matrix and the fuzzy relation matrix to perform an elementary change.
The beneficial effects of the above technical scheme are: the method comprises the steps of establishing a target association table of a host and positions through a first target requirement and a second target requirement, facilitating one-to-one correspondence of the host and the positions, establishing an association matrix according to the correspondence of the host and the positions and called host category data, completing establishment of a relationship between the positions and the host, determining identity attributes of job seekers, establishing a fuzzy relationship between the job seekers and the host according to the identity attributes, wherein the fuzzy relationship can comprise one-to-one and one-to-many, finally performing elementary change through combination of the association matrix and the fuzzy relationship matrix to determine a host matrix, and ensuring that the host matrix comprises hosts corresponding to various job seekers.
The invention provides a recommendation method based on a virtual reality moderator system, which carries out a recommendation guidance process based on a first target requirement and a second target requirement and also comprises the following steps:
acquiring the first target requirement and the second target requirement, and inputting the first target requirement and the second target requirement into a data conversion model, wherein the data conversion model converts the first target requirement and the second target requirement into corresponding first data information and second data information according to a preset rule;
constructing an expert data analysis model based on the first target requirement and the second target requirement, and inputting the first data information and the second data information into the expert data analysis model for classification processing, wherein the method specifically comprises the following steps:
identifying keywords in the first data information and the second data information, and transmitting the keywords into the expert data analysis model;
searching a position or a recruitment position with the highest relevance from the preset position library according to the received keyword, and transmitting the position or the recruitment position to a host terminal through a background;
the host terminal comprises a virtual host terminal and a real host terminal;
the host terminal performs big data analysis on the positions or the recruitment positions through a preset capability analysis model to obtain position guidance data information, and screens the guidance data information through preset judgment conditions to obtain target guidance data;
converting target guidance data obtained by analysis of a host into corresponding audio and video data according to a standardized protocol;
constructing a communication link between the host and the job seeker or the recruiter;
and transmitting the audio and video data to a target end corresponding to a job seeker or a recruiter based on the communication link, receiving a problem proposed by the job seeker or the recruiter based on the communication link, converting the problem into a corresponding digital signal through a digital-to-analog conversion database in the communication link, and carrying out coding transmission on the digital signal, thereby realizing the joint communication guidance between the job seeker or the recruiter and the virtual supporters and among real person presenters.
In this embodiment, the preset rule refers to a conversion algorithm obtained through multiple training inside the website, and can convert the customer requirement information into data information that can be analyzed by the website.
In this embodiment, the first data information and the second data information refer to another expression form corresponding to the target needs of the job seeker and the recruiter, and the expression form is convenient for the website to analyze the user information.
In this embodiment, the keyword refers to some characteristic value representative of information required by the job seeker or the recruiter and capable of representing an intended post of the job seeker or an intended employee of the recruiter.
In this embodiment, the relevance degree refers to the matching degree between the basic information filled by the job seeker and the recruiting position, that is, the relevance degree is used for judging whether the job seeker is suitable for the position and whether the position is matched with the capability of the job seeker.
In this embodiment, the target guidance data refers to removing data that is not related to influence from the obtained guidance data to obtain final valuable guidance data, for example, mailbox addresses are removed from the guidance data, and the final remaining valuable data is the target guidance data.
In this embodiment, the standardized protocol refers to a series of specifications, terms, procedures and constraint indexes used to specify conversion of constant data into audio-video information.
In this embodiment, the expert degree in the expert degree data analysis model refers to performing professional processing on input data through the model, so as to ensure that a processing result is accurate and professional.
The beneficial effects of the above technical scheme are: the first target requirement and the second target requirement are converted into corresponding data information, so that a website can analyze and process the target requirements conveniently, the converted data information is input into an expert analysis model to search a position or a recruitment position with the highest relevance, the speed and the accuracy of quickly searching the relevant position are improved, meanwhile, a host analyzes big data of the obtained position or the recruitment position to obtain guidance data for a job seeker or a recruiter, the step is convenient for the host to obtain the guidance data suitable for the host according to the condition of each person and remove irrelevant variables in the guidance data to obtain final target guidance data, the target guidance data are converted into corresponding audio and video information, and the audio and video information is transmitted to the job seeker or the recruiter based on a constructed communication link to realize bidirectional communication, so that the situation can be known by the host on line, and provides constructive guide opinions according to self conditions.
The invention provides a recommendation method based on a virtual reality host system, which is used for sending corresponding recommendation guidance results to target terminals corresponding to job seekers and recruiters, and comprises the following steps:
acquiring intention position information of the job seeker and first evaluation corresponding to the intention position information, and recommending a first recommended position associated with the intention position according to the first evaluation;
acquiring other post information delivered by the job seeker within a preset time period and second evaluation corresponding to the post information, and recommending a second recommended post associated with the intention post according to the second evaluation;
comparing the relevance of the first recommended position and the intention position and the relevance of the second recommended position and the intention position, and recommending the position with high relevance to the job seeker;
meanwhile, capturing the job seeker application information in the recruitment website through a web crawler to form an application information set, removing job seekers which are not matched with the indispensable items of the recruitment post requirement information in the application information set, and taking the rest job seekers as a first recommended job seeker set;
eliminating the job seekers of which the capability information of the job seekers in the first set of recommended job seekers does not meet the necessary item of the requirement information of the recruitment post, and taking the rest job seekers as a second job seeker recommendation set;
and calculating the similarity between the capability information of each job seeker in the second job seeker recommendation set and the recruitment position information, screening the first N job seekers with the highest similarity to the recruitment position to generate a job seeker recommendation list, and recommending the job seeker recommendation list to the recruiters.
In this embodiment, the application information set includes a plurality of basic information suitable for job hunting on the post.
In this embodiment, the requirement information must item mismatch means that the requirement set by the recruiter in the recruiting process for applying the post has a requirement, and the requirement that the requirement does not match needs to be removed.
The beneficial effects of the above technical scheme are: the method comprises the steps of obtaining a first recommended position by obtaining intention position information of a job seeker and a first evaluation corresponding to the intention position information, obtaining a second recommended position according to other position information delivered by the job seeker within a preset time period and a corresponding second evaluation, comparing the correlation degree of the two positions, recommending the job seeker with the highest correlation degree, ensuring that the job seeker is most suitable for the capability of the job seeker when the job seeker is recommended, obtaining the application information of the job seeker at the same time, forming an application information set of the job seeker, removing people not matched with necessary items by screening the application information set, calculating the similarity between the rest staff and the positions, recommending the job seeker with the highest similarity degree, ensuring that the staff recruited by the job seeker meets the capability requirement of the position on the staff, and improving the accuracy and efficiency of recommendation.
The invention provides a recommendation method based on a virtual reality host system, which further comprises the following steps when recommending to a job seeker or a recruiter:
constructing a fuzziness and precision recommendation algorithm, and recommending the recruitment website according to a preset proportion of the fuzziness and precision recommendation algorithm when the recruitment website recommends to the job seeker or the recruiter;
acquiring user attribute information of the job seeker and the recruiter, wherein the user attribute information comprises a minimum deadline allowed for a recruitment position in the job seeker or the recruiting company and an urgency level of a demand for the recruitment position in the job seeker or the recruiting company;
determining the weight of the urgency degree of the demand of the job seeker or the recruitment position in the recruitment company, and sorting the job seekers on the same day and the recruitment position in the recruitment company according to the minimum deadline to generate an importance degree sorting table;
and recommending the job seeker with the top rank in the importance ranking list to the recruiter in an audio and video mode based on the preset proportion of the ambiguity and precision recommendation algorithm, and simultaneously recommending the recruitment position in the recruitment company with the top rank to the job seeker in an audio and video mode to complete bidirectional recommendation.
In this embodiment, the weight of the urgency degree refers to the proportion of the urgency factor in all information of the job seeker or the recruiter in the job hunting or recruitment process.
In the embodiment, the recruitment post in the most important recruitment company on the day is recommended to the job seeker in an audio and video mode, the job seeker most important on the day is recommended to the recruiter in an audio and video mode, and the recommendation is performed conveniently according to the preset proportion based on the fuzzy and accuracy recommendation algorithm analysis.
The beneficial effects of the above technical scheme are: according to the scheme, the most important and most needed job seekers and recruiters on the day are recommended in a bidirectional mode, and the recommendation is carried out in an audio-video mode, so that the job seekers or the recruiters can know the basic condition of the object intuitively, and the success probability is improved.
The invention provides a recommendation method based on a virtual reality host system, which further comprises the following steps of in the process of sending corresponding recommendation guidance results to target ends corresponding to job seekers and recruiters according to preset recommendation rules:
calculating the recommendation weight adopting the ambiguity recommendation algorithm according to the following formula:
wherein eta is1Representing a recommendation weight using the digital fuzzy recommendation algorithm; alpha represents the number of the first indexes of the corresponding job seekers or recruiters when the digital fuzzy recommendation algorithm is adopted for recommendation, wherein the first indexes comprise basic conditions, and the value range is [0,8 ]](ii) a Delta represents an important indicator in the job seeker or recruiter requirement information; e represents a very important index in the requirement information of the job seeker or the recruiter; mu represents a very important index in the request information of the job seeker or the recruiter; beta represents the number of the second indexes of the job seeker or the recruiter containing the necessary conditions when the digital fuzzy recommendation algorithm is adopted for recommendation, and the value range is [0, 4 ]]；
Calculating the weight of the accuracy recommendation algorithm according to the recommendation weight of the ambiguity recommendation algorithm:
wherein eta is2Representing the recommendation weight when the accurate recommendation algorithm is adopted for recommendation; sigma represents a weight coefficient of the precise recommendation algorithm; eta1Representing the recommendation weight when the digital fuzzy recommendation algorithm is adopted for recommendation;
a weighted average coefficient representing the accuracy recommendation algorithm;
calculating the fault tolerance rate of the recruitment website during recommendation according to the following formula:
wherein p represents the fault tolerance of the recruitment website during recommendation; theta represents a fault tolerance coefficient when the recruitment website is recommended; eta2Representing the recommendation weight when the accurate recommendation algorithm is adopted for recommendation; eta1Representing the recommendation weight when the digital fuzzy recommendation algorithm is adopted for recommendation; gamma represents the number of times of errors in recommendation in the recruitment website recommendation period; k represents the total number of recommendations within the recruitment website recommendation period; tau represents the maximum number of times of errors allowed in the total number of times of recommendation in the recruitment website recommendation period; ζ represents a correction coefficient of the recruiting website;
comparing the calculated fault tolerance with a preset fault tolerance;
and if the fault tolerance rate is lower than the preset fault tolerance rate, the recruitment website reminds the job seeker or the recruiter to modify the importance degree index in the information.
In this embodiment, the precision recommendation algorithm refers to actions of precisely positioning a user, including job browsing operations, delivery establishing operations, basic information filling operations, and the like, and through some mathematical algorithms, precision prediction and recommendation are performed on a job position or a recruited job position that the user may want to seek a job, for example, a panning recommendation algorithm.
In this embodiment, the ambiguity recommendation algorithm refers to acquiring recent operation information of the user, without remembering previous operations of the user, and recommending a post or employee, such as a talent career network, which may be required to the user through the current operation.
In this embodiment, the first indicator refers to basic conditions set by the job seeker or recruiter in job hunting or recruiting, such as minimum academic requirements, work experience, and the like, which must be satisfied.
In this embodiment, the important indicators, the very important indicators, and the very important indicators refer to positions obtained by comparing the importance level of a certain indicator with the importance levels of other indicators during job hunting or recruitment, and the three indicators are assigned, the important indicator is assigned 3, the very important indicator is assigned 4, and the very important indicator is assigned 5, and the three indicators are respectively assigned 3, 4, and 5 into corresponding positions during calculation, for example, among age, academic calendar, and work experience, age is taken as the important indicator, academic calendar is taken as the very important indicator, and work experience is taken as the very important indicator.
In this embodiment, the second indicator refers to a condition that must be satisfied by the job seeker or recruiter when the job seeker or recruiter is engaged, such as: male, master, etc.
In this embodiment, the job seeker and the recruiter can set important, very important and very important indexes in adjusting the fuzziness and the accuracy recommendation by themselves.
The beneficial effects of the above technical scheme are: calculating the recommendation weight of a fuzzy recommendation algorithm, calculating the weight of a precision recommendation algorithm, calculating the fault tolerance rate of a website during recommendation through the fuzzy recommendation algorithm weight and the precision recommendation algorithm weight, relating to the number of a first index and a second index when calculating the weight of the fuzzy recommendation algorithm, determining the importance degree grade in the indexes, calculating the weight of the fuzzy recommendation algorithm through the proportion of basic conditions in the basic conditions and the essential conditions to enable the calculation result to be more accurate and reliable, calculating the weight of the precision recommendation algorithm through the fuzzy recommendation algorithm, relating to the weight coefficient and the weighted average coefficient of the precision recommendation algorithm to obtain the weight of the precision recommendation algorithm, and designing the proportion of 2 of the fuzzy recommendation algorithm to the precision recommendation algorithm when calculating the fault tolerance rate during recommendation of the website, and error times in the total recommended times in the website recommendation period are limited by the maximum allowable error times, so that the calculation result is more accurate and real.
The invention provides a recommendation system based on a virtual reality moderator system, which is shown in figure 2:
the acquisition module is used for acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter;
the recommendation guidance module is used for establishing a host matrix, and performing recommendation guidance based on the first target requirement and the second target requirement when a real host and a digital host in the host matrix jointly log in a recruitment website;
and the result pushing module is used for sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule.
The beneficial effects of the above technical scheme are: the method solves the problem that virtual hosts and real hosts in various industries jointly guide and recommend job seekers or recruiters, meanwhile, the job hunting positions in the most important recruiting companies in the day are recommended to the job seekers in an audio and video mode, the most important job seekers in the day are recommended to the job seekers in the audio and video mode, and the recommendation is convenient to perform recommendation according to the preset proportion based on the fuzzy and precision recommendation algorithm analysis.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. A recommendation method based on a virtual reality moderator system is characterized by comprising the following steps:
acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter;
establishing a host matrix, and performing recommendation guidance based on the first target requirement and the second target requirement when a real host and a digital host in the host matrix jointly log in a recruitment website;
and sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule.
2. The virtual reality moderator system-based recommendation method of claim 1 wherein obtaining a first target requirement of the candidate comprises:
acquiring resume information of a job seeker, wherein the resume information comprises identity attributes, job hunting positions, target salaries and professional directions of the job seeker, and receiving pending intention positions determined by the job seeker in a plurality of positions;
performing weight sequencing according to the job hunting post, target salaries and the requirement degree of the job hunting post of the intention to be decided by the job hunter and the professional direction by constructing a job hunter demand space model to obtain a final target post;
wherein the final target post is the first target requirement.
3. The virtual reality presenter architecture based recommendation method of claim 1, wherein after acquiring the second target need of the recruiter, further comprising:
acquiring a position index associated with the recruiting position, wherein the position index comprises the number of required persons of the position, the position capacity and the minimum academic requirement;
and calling a test question corresponding to the recruitment position from a test database based on the position index, generating a post recruitment test paper, and presenting the post recruitment test paper to the job seeker.
4. The virtual reality presenter architecture-based recommendation method of claim 1, wherein the specific process of establishing the presenter matrix further comprises:
establishing a host guidance mode and a job target association table based on the first target requirement of the job seeker and the second target requirement of the recruiter, calling host data in a preset host database, and establishing an association matrix;
the server constructs a fuzzy relation model for the identity attribute of the job seeker and the corresponding relation of the host needing to be guided, and obtains a fuzzy relation matrix through preset rule conversion;
after the incidence matrix and the fuzzy matrix are subjected to elementary change, a host matrix is obtained;
the moderator matrix includes: social recruitment, campus recruitment, overseas recruitment, hunting, mechanic recruitment, handicapped recruitment, retired soldier recruitment, maritime recruitment, foreign membership recruitment, team creation, recruitment, training of a host and the like.
5. The virtual reality moderator system-based recommendation method of claim 1, wherein a recommendation guidance process is performed based on the first target requirement and the second target requirement, further comprising:
acquiring the first target requirement and the second target requirement, and inputting the first target requirement and the second target requirement into a data conversion model, wherein the data conversion model converts the first target requirement and the second target requirement into corresponding first data information and second data information according to a preset rule;
constructing an expert data analysis model based on the first target requirement and the second target requirement, and inputting the first data information and the second data information into the expert data analysis model for classification processing, wherein the method specifically comprises the following steps:
identifying keywords in the first data information and the second data information, and transmitting the keywords into the expert data analysis model;
searching a position or a recruitment position with the highest relevance from a preset position library according to the received keyword, and transmitting the position or the recruitment position to a host terminal through a background;
the host terminal comprises a virtual host terminal and a real host terminal;
the host terminal performs big data analysis on the positions or the recruitment positions through a preset capability analysis model to obtain position guidance data information, and screens the guidance data information through preset judgment conditions to obtain target guidance data;
converting target guidance data obtained by analysis of a host into corresponding audio and video data according to a standardized protocol;
constructing a communication link between the host and the job seeker or recruiter;
and transmitting the audio and video data to a target end corresponding to a job seeker or a recruiter based on the communication link, receiving a problem proposed by the job seeker or the recruiter based on the communication link, converting the problem into a corresponding digital signal through a digital-to-analog conversion database in the communication link, and carrying out coding transmission on the digital signal, thereby realizing the joint communication guidance between the job seeker or the recruiter and the virtual supporters and among real person presenters.
6. The virtual reality moderator system-based recommendation method of claim 1, wherein the process of sending the corresponding recommendation guidance results to the target terminals corresponding to the job seeker and the recruiter comprises:
acquiring intention position information of the job seeker and first evaluation corresponding to the intention position information, and recommending a first recommended position associated with the intention position according to the first evaluation;
acquiring other post information delivered by the job seeker within a preset time period and second evaluation corresponding to the post information, and recommending a second recommended post associated with the intention post according to the second evaluation;
comparing the relevance of the first recommended position and the intention position and the relevance of the second recommended position and the intention position, and recommending the position with high relevance to the job seeker;
meanwhile, capturing the job seeker application information in the recruitment website through a web crawler to form an application information set, removing job seekers which are not matched with the indispensable items of the recruitment post requirement information in the application information set, and taking the rest job seekers as a first recommended job seeker set;
eliminating the job seekers of which the capability information of the job seekers in the first set of recommended job seekers does not meet the necessary item of the requirement information of the recruitment post, and taking the rest job seekers as a second job seeker recommendation set;
and calculating the similarity between the capability information of each job seeker in the second job seeker recommendation set and the recruitment position information, screening the first N job seekers with the highest similarity to the recruitment position to generate a job seeker recommendation list, and recommending the job seeker recommendation list to the recruiters.
7. A virtual reality moderator system based recommendation method according to claim 6 further comprising, when recommending to said job seeker or recruiter:
constructing a fuzziness and precision recommendation algorithm, and recommending the recruitment website according to a preset proportion of the fuzziness and precision recommendation algorithm when the recruitment website recommends to the job seeker or the recruiter;
acquiring user attribute information of the job seeker and the recruiter, wherein the user attribute information comprises a minimum deadline allowed for a recruitment position in the job seeker or the recruiting company and an urgency level of a demand for the recruitment position in the job seeker or the recruiting company;
determining the weight of the urgency degree of the demand of the job seeker or the recruitment position in the recruitment company, and sorting the job seekers on the same day and the recruitment position in the recruitment company according to the minimum deadline to generate an importance degree sorting table;
and recommending the job seeker with the top rank in the importance ranking list to the recruiter in an audio and video mode based on the preset proportion of the ambiguity and precision recommendation algorithm, and simultaneously recommending the recruitment position in the recruitment company with the top rank to the job seeker in an audio and video mode to complete bidirectional recommendation.
8. The method as claimed in claim 7, wherein in the process of sending the corresponding recommendation guidance results to the target terminals corresponding to the job seeker and the recruiter according to the preset recommendation rules, the method further comprises:
calculating the recommendation weight adopting the ambiguity recommendation algorithm according to the following formula:
wherein eta is1Representing a recommendation weight using the digital fuzzy recommendation algorithm; alpha represents the number of the first indexes of the corresponding job seekers or recruiters when the digital fuzzy recommendation algorithm is adopted for recommendation, wherein the first indexes comprise basic conditions, and the value range is [0,8 ]](ii) a Delta represents an important indicator in the job seeker or recruiter requirement information; e represents a very important index in the requirement information of the job seeker or the recruiter; mu represents a very important index in the request information of the job seeker or the recruiter; beta represents the number of the second indexes of the job seeker or the recruiter containing the necessary conditions when the digital fuzzy recommendation algorithm is adopted for recommendation, and the value range is [0, 4 ]]；
Calculating the weight of the accuracy recommendation algorithm according to the recommendation weight of the ambiguity recommendation algorithm:
wherein eta is2Representing the recommendation weight when the accurate recommendation algorithm is adopted for recommendation; sigma represents a weight coefficient of the precise recommendation algorithm; eta1Representing the recommendation weight when the digital fuzzy recommendation algorithm is adopted for recommendation;
a weighted average coefficient representing the accuracy recommendation algorithm;
calculating the fault tolerance rate of the recruitment website during recommendation according to the following formula:
wherein p represents the fault tolerance of the recruitment website during recommendation; theta represents a fault tolerance coefficient when the recruitment website is recommended; eta2Representing the recommendation weight when the accurate recommendation algorithm is adopted for recommendation; eta1Representing the recommendation weight when the digital fuzzy recommendation algorithm is adopted for recommendation; gamma represents the number of times of errors in recommendation in the recruitment website recommendation period; k represents the total number of recommendations within the recruitment website recommendation period; tau represents the maximum number of times of errors allowed in the total number of times of recommendation in the recruitment website recommendation period; ζ represents a correction coefficient of the recruiting website;
comparing the calculated fault tolerance with a preset fault tolerance;
and if the fault tolerance rate is lower than the preset fault tolerance rate, the recruitment website reminds the job seeker or the recruiter to modify the importance degree index in the information.
9. A recommendation system based on a virtual reality moderator system is characterized in that:
the acquisition module is used for acquiring a first target requirement of a job seeker and acquiring a second target requirement of a recruiter;
the recommendation guidance module is used for establishing a host matrix, and performing recommendation guidance based on the first target requirement and the second target requirement when a real host and a digital host in the host matrix jointly log in a recruitment website;
and the result pushing module is used for sending corresponding recommendation guidance results to the target ends corresponding to the job seekers and the recruiters according to a preset recommendation rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011309342.3A CN112417280A (en) | 2020-11-20 | 2020-11-20 | Recommendation method and system based on virtual reality moderator system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011309342.3A CN112417280A (en) | 2020-11-20 | 2020-11-20 | Recommendation method and system based on virtual reality moderator system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417280A true CN112417280A (en) | 2021-02-26 |
Family
ID=74773830
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011309342.3A Withdrawn CN112417280A (en) | 2020-11-20 | 2020-11-20 | Recommendation method and system based on virtual reality moderator system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417280A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435841A (en) * | 2021-06-24 | 2021-09-24 | 浙江工贸职业技术学院 | Talent intelligent matching recruitment system based on big data |
| CN113918765A (en) * | 2021-11-04 | 2022-01-11 | 盐城金堤科技有限公司 | Video recommendation method, device, medium and electronic equipment |
-
2020
- 2020-11-20 CN CN202011309342.3A patent/CN112417280A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113435841A (en) * | 2021-06-24 | 2021-09-24 | 浙江工贸职业技术学院 | Talent intelligent matching recruitment system based on big data |
| CN113918765A (en) * | 2021-11-04 | 2022-01-11 | 盐城金堤科技有限公司 | Video recommendation method, device, medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101830834B1 (en) | Online Platform System Using System For Matching Of Experts Matching System. | |
| CN103761254B (en) | Method for matching and recommending service themes in various fields | |
| US20120272164A1 (en) | Interactive peer directory with question router | |
| Seebach | Searching for answers--knowledge exchange through social media in organizations | |
| Rodriguez et al. | Feature selection for job matching application using profile matching model | |
| CN111833019A (en) | Cloud customization recruitment method and system | |
| CN110727852A (en) | Method, device and terminal for pushing recruitment recommendation service | |
| CN111737485A (en) | Human-sentry matching method and human-sentry matching system based on knowledge graph and deep learning | |
| CN112417280A (en) | Recommendation method and system based on virtual reality moderator system | |
| CN112990794B (en) | Video conference quality detection method, system, storage medium and electronic equipment | |
| CN111695084A (en) | Model generation method, credit score generation method, device, equipment and storage medium | |
| Vilakone et al. | Movie recommendation system based on users’ personal information and movies rated using the method of k-clique and normalized discounted cumulative gain | |
| CN110968651A (en) | Data processing method and system based on grey fuzzy clustering | |
| CN114139065B (en) | Talent screening and recommending method and system based on big data and readable storage medium | |
| CN114742520A (en) | Post matching method, device, equipment and storage medium | |
| Appadoo et al. | Job recommendation system, machine learning, regression, classification, natural language processing | |
| CN111552796A (en) | Volume assembling method, electronic device and computer readable medium | |
| US20240127143A1 (en) | Method, device and storage medium for information processing based on data interaction | |
| CN112862641A (en) | Retired soldier training recommendation method, equipment and storage medium | |
| CN111611387B (en) | Civil case consultation method and device, computer equipment and storage medium | |
| CN117522222A (en) | Education assessment software implementation method based on big data | |
| CN111708929A (en) | Information searching method and device, electronic equipment and storage medium | |
| CN116361655A (en) | Model training method, standard problem prediction method, device, equipment and medium | |
| KR101853555B1 (en) | SW Market Information Service System | |
| Szyjewski et al. | A study on existing and actually used capabilities of mobile phones technologies |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210226 |