CN115841316A - Method and system for matching human posts, electronic equipment and storage medium - Google Patents
Method and system for matching human posts, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115841316A CN115841316A CN202111091116.7A CN202111091116A CN115841316A CN 115841316 A CN115841316 A CN 115841316A CN 202111091116 A CN202111091116 A CN 202111091116A CN 115841316 A CN115841316 A CN 115841316A
- Authority
- CN
- China
- Prior art keywords
- resume
- post
- candidate
- matching
- matching degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, electronic equipment and a storage medium for matching a sentry, wherein the method for matching the sentry comprises the following steps: s1, screening initial candidate resumes based on the post description information to determine candidate resumes matched with the post description information from the initial candidate resumes; wherein the post description information comprises a plurality of post characteristics; s2, sorting the candidate resumes according to the matching degree; and S3, displaying the candidate resume and the explanation information of the candidate resume according to the sequencing result, wherein the explanation information comprises resume contents matched with the position characteristics in the candidate resume. According to the method and the device, the matching degree of the resume and the post description can be output and interpreted at the same time, so that the HR can be conveniently consulted and screened, the time consumption of the HR in the reviewing process is reduced, the screening speed is increased, and the comprehensive judgment of the resume of a candidate can be considered.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method and a system for people matching, an electronic device, and a storage medium.
Background
On a recruitment management platform (ATS), after a post is released by a personnel (HR), a large number of resume deliveries applying for the post are collected. In general, HR requires a look-up of incoming posts on the platform one by one to select the appropriate candidate, but this takes a lot of time. The post matching is an important function in the ATS system, most of the existing post matching methods are black box modes, and resumes need to be checked and compared one by one after the HR obtains the result of the post matching.
Disclosure of Invention
The invention aims to overcome the defects that the resume delivery amount is large and a large amount of time is spent for looking up in the prior art, and provides a method and a system for matching the human posts, electronic equipment and a storage medium.
The invention solves the technical problems through the following technical scheme:
the invention provides a method for matching a human sentry, which comprises the following steps:
s1, screening initial candidate resumes based on the post description information to determine candidate resumes matched with the post description information from the initial candidate resumes; wherein the post description information comprises a plurality of post characteristics;
s2, sorting the candidate resumes according to the matching degree;
and S3, displaying the candidate resume and the explanation information of the candidate resume according to the sequencing result, wherein the explanation information comprises resume contents matched with the position characteristics in the candidate resume.
Preferably, step S1 includes:
for each initial candidate resume, extracting resume contents corresponding to each post characteristic from the initial candidate resume;
and under the condition that the extracted resume contents all accord with the characteristic conditions of the corresponding post characteristics, determining the initial candidate resume as the candidate resume.
Preferably, step S2 includes:
inputting the candidate resume into a pre-trained resume matching model, and outputting a first matching degree of the candidate resume and the post description information and a second matching degree of the candidate resume and each post characteristic by the resume matching model;
and sorting the candidate resumes according to the first matching degree and the second matching degree.
Preferably, the resume matching model is obtained by training through the following steps:
acquiring a large number of positive samples and negative samples as training samples, wherein the positive samples are resumes matched with the post description information, and the negative samples are resumes unmatched with the post description information;
and adjusting parameters of the neural network according to the training samples to obtain the resume matching model.
Preferably, step S2 includes:
converting the resume content corresponding to each post characteristic in the candidate resume into a structured field containing an order relation;
and determining the matching degree of the candidate resume according to the structured field, and sequencing the candidate resume according to the matching degree.
Preferably, step S2 includes:
determining a post position function corresponding to the post description information;
sequencing the post characteristics of the post description information according to a characteristic sequencing model based on an attention mechanism;
setting weights for resume contents corresponding to all the post characteristics in the candidate resumes, wherein the weights are related to the sequencing of the post characteristics;
and determining the matching degree of the candidate resume according to the resume content after the weight is set, and sequencing the candidate resume according to the matching degree.
The invention also provides a people's post matching system, which comprises:
the screening module is used for screening the initial candidate resumes based on the post description information so as to determine candidate resumes matched with the post description information from the initial candidate resumes;
the sorting module is used for sorting the candidate resumes according to the matching degree;
and the interpretation module is used for displaying the candidate resume and the interpretation information of the candidate resume according to the sequencing result, wherein the interpretation information comprises resume contents matched with the position characteristics in the candidate resume.
Preferably, the screening module comprises:
a content extraction unit, configured to, for each initial candidate resume, extract resume content corresponding to each post feature from the initial candidate resume;
and the resume determining unit is used for determining the initial candidate resume as the candidate resume under the condition that the extracted resume contents all accord with the characteristic conditions of the corresponding post characteristics.
Preferably, the sorting module comprises:
the matching degree calculation unit inputs the candidate resume into a resume matching model trained in advance, and outputs a first matching degree of the candidate resume and the post description information and a second matching degree of the candidate resume and each post characteristic through the resume matching model;
and the matching degree sorting unit sorts the candidate resumes according to the first matching degree and the second matching degree.
Preferably, the people post matching system further comprises:
the model training module is used for acquiring a large number of positive samples and negative samples as training samples, wherein the positive samples are resumes matched with the post description information, and the negative samples are resumes unmatched with the post description information;
and the model training module is also used for adjusting parameters of the neural network according to the training samples so as to obtain the resume matching model.
Preferably, the sorting module comprises:
a field structuring unit, configured to convert resume contents corresponding to each post feature in the candidate resume into a structured field containing an order relationship;
and the field matching degree sorting unit is used for determining the matching degree of the candidate resume according to the structured field and sorting the candidate resume according to the matching degree.
Preferably, the sorting module comprises:
a position function determining unit for determining the position function corresponding to the position description information;
the post characteristic sorting unit is used for sorting the post characteristics of the post description information according to a characteristic sorting model based on an attention mechanism;
the weight setting unit is used for setting weights for resume contents corresponding to all post characteristics in the candidate resumes, and the weights are related to the sequencing of the post characteristics;
and the function matching degree sorting unit is used for determining the matching degree of the candidate resume according to the resume content with the weight set and sorting the candidate resume according to the matching degree.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the human-job matching method.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the inventive method of human job matching.
The positive progress effects of the invention are as follows:
according to the method, the post characteristics in the post description are extracted and are compared with the corresponding contents in the resume, so that a large number of resumes which do not meet the standard are screened out; and then, the matching degrees of the resume and the post description are sorted according to the model, so that the candidate can be more effectively evaluated according to the post characteristics in the post description. Meanwhile, the matching degree of the resume and the post description can be output and interpreted at the same time, so that the HR can be conveniently consulted and screened, the time consumption of the HR in the reviewing process is reduced, the screening speed is increased, and the comprehensive judgment of the resume of a candidate can be considered.
Drawings
Fig. 1a is a flowchart of a method for matching a human sentry according to an exemplary embodiment of the present invention;
fig. 1b is a schematic view of a scene of resume content extraction used in a method for matching human posts according to an exemplary embodiment of the present invention;
FIG. 1c is a schematic diagram of a parser used in a human sentry matching method according to an exemplary embodiment of the present invention;
fig. 1d is a scene schematic diagram of setting weights corresponding to respective post features used by a people post matching method according to an exemplary embodiment of the present invention;
FIG. 2 is a block diagram of a human sentry matching system according to an exemplary embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Fig. 1a is a flowchart of a method for matching a human sentry according to an exemplary embodiment of the present invention, where the method for matching a human sentry includes the following steps:
s101, screening the initial candidate resumes based on the post description information to determine candidate resumes matched with the post description information from the initial candidate resumes; wherein the post description information comprises a plurality of post characteristics;
the system can directly screen out resumes which do not meet the standard according to the minimum requirement in the position description information so as to save the workload and time of the HR.
S102, sorting the candidate resumes according to the matching degree;
and sorting the candidate resumes based on the resume matching model. And training a neural network by using history data and position description information screened by the resumes, determining the trained neural network as a resume matching model, wherein the resume matching model has a function of judging whether the human posts are matched, and the system sorts the candidate resumes according to the matching degree returned by the model and arranges the resumes with high matching degree in front.
S103, displaying the candidate resume and the explanation information of the candidate resume according to the sorting result, wherein the explanation information comprises resume contents matched with the position characteristics in the candidate resume.
The system can correspond the post characteristics in the post description information with the content matched with the post characteristics in the resume and display the matching degree of each candidate in the sequencing list, and the HR can know matched and unmatched items in the post requirements corresponding to each candidate while checking the sequencing list and the matching degree, so that the steps of reading the resume one by one and comparing the resume one by the HR are simplified or even omitted.
The first step in HR screening resumes is actually determining whether the candidate meets the basic requirements of the post, and then the HR will peruse each segment of the working experience of the candidate while also considering whether the skill ability of the candidate matches the post. Steps S101 and S102 in this embodiment are simulations of the HR screening and matching process. Most of the existing technologies are in a black box mode, and a model is difficult to obtain an effective comment, but in the embodiment, resume contents of a post characteristic corresponding to each candidate can be displayed while sequencing is output, so that a reasonable explanation can be provided for a matching result through the step S103 in the embodiment.
To facilitate the human-job matching, in one embodiment, the job description information and/or the resume may be vectorized, that is, a vector is used to represent the job description information and/or the resume. For example, referring to fig. 1b, for the station description information: "need to recruit a C + + development engineer. Familiar with embedded development. Having product awareness "perform text vectorization processing. Similarly, for resumes: ' fond basketball. A 3D game engine was developed at game a. The text vectorization processing is performed using C + + and C languages. Matching the resume text after the text vectorization processing with the position description information to obtain the part of the position description information which is most matched with the resume. For example: one part of post description information is as follows: "need to recruit a C + + development engineer. Familiarizes with embedded development. Has product consciousness, and one resume is a favorite basketball. A 3D game engine was developed at game a. Using C + + and C language "after matching, get the interpretation information" using C + + and C language ". By the steps of corresponding the post characteristics in the post description information with the content matched with the post characteristics in the resume, screening and displaying, the HR can know matched and unmatched items in the post requirements corresponding to each candidate, and therefore the steps of reading resumes and comparing resumes one by the HR are simplified and even omitted.
In one embodiment, step S101 includes:
s101-1, extracting resume contents corresponding to each post characteristic from each initial candidate resume.
Wherein, the post characteristics contained in one post description information are: the resume also comprises contents such as a study, a school, an industry, a work experience and the like, but the resume also comprises a large amount of useless information while comprising the contents, so that the resume contents need to be extracted according to the post characteristics in the post description information, and the contents meeting the post requirements set by the HR are obtained.
S101-2, under the condition that the extracted resume contents all accord with the characteristic conditions of the corresponding post characteristics, determining the initial candidate resume as the candidate resume.
The corresponding post characteristics feature conditions are the minimum standard set by HR, and the resume can become a candidate resume only if resume contents corresponding to the post characteristics all reach the minimum standard; for example, in a post information description, the characteristic condition of the resume is the subject, and the corresponding characteristic condition of the resume must be screened from the subject or above.
In one embodiment, step S101 is implemented based on a parser, see in particular fig. 1 c. For example, the system inputs the position description information and the resume content into an analyzer, extracts the position characteristics and the corresponding content in the resume through the analyzer, sends the extracted result to a judging module to judge whether the corresponding content in the resume meets the condition of the position characteristics, and finally classifies the resumes which pass and fail screening respectively through a classifying module to determine candidate resumes. In fig. 1c, taking a school as an example, the parser extracts the school grade in the position description information and the school name in the resume, and sends the school grade and the school name in the resume to the judgment module for judgment, if the school in the resume does not meet the school grade requirement in the position description information, the resume does not meet the standard, and cannot become a candidate resume.
In one embodiment, step S102 includes:
s102-1, inputting the candidate resume into a pre-trained resume matching model, and outputting a first matching degree of the candidate resume and the position description information and a second matching degree of the candidate resume and each position characteristic by the resume matching model.
The first matching degree is the matching degree of comprehensive evaluation on all the post characteristics in the post description information and can reflect the comprehensive quality of corresponding post candidates; the second matching degree is the matching degree of the resume corresponding to each post characteristic, and different post matching degrees can be obtained corresponding to different post characteristics; the HR can have a more comprehensive understanding of the combined abilities and traits of each candidate.
S102-2, sorting the candidate resumes according to the first matching degree and the second matching degree.
The system arranges all the candidates into a table according to the matching degrees from large to small and outputs the table, and generates a sorting table related to the second matching degree while generating a first matching degree sorting table. The first sorting table is used for displaying the comprehensive matching degree of each candidate, and the second sorting table is used for displaying the matching degree of each candidate corresponding to each post characteristic.
And obtaining the matching degree of all candidate resumes and the post description information through the matching model. And ranking the resumes according to the high matching degree from large to small, so that the HR can preferentially see the resumes with high matching degree, and the workload generated in the manual screening process is reduced. HR can sort and check the comprehensive matching degree of each candidate in the first matching degree of the resume of the position candidate, and can also check the sorting table of the second matching degree to comprehensively consider the characteristics of each employee.
In one embodiment, the resume matching model is trained by:
s102-1-1, obtaining a large number of positive samples and negative samples as training samples.
The positive sample is the resume matched with the post description information, and the negative sample is the resume not matched with the post description information; the positive and negative samples both contain original text information, post features extracted from the text and corresponding fields in the resume.
S102-1-2, adjusting parameters of the neural network according to the training samples to obtain a resume matching model.
The resume matching model can return the matching degree of the resume and the post description information after operation only by inputting the resume and the post description information in the using process.
In one embodiment, step S102 includes:
s'102-1, converting the resume content corresponding to each post characteristic in the candidate resume into a structured field containing an order relation.
In which, the schools in the post characteristics are taken as examples for grade classification. Converting the graduates of the candidate into an ordered category according to the grade of the school, namely 985>211> common one > common two; the embodiment also converts the company name into an ordered category according to the industry popularity-international popularity > domestic popularity > industry popularity. Compared with the school name and the organization name which cannot be understood by a computer, the ordered category enables the model to effectively process the information.
S'102-2, determining the matching degree of the candidate resume according to the structured field, and sequencing the candidate resume according to the matching degree.
In one embodiment, step S102 includes:
s'102-1, determining the position function corresponding to the position description information.
Wherein, each post has the post function corresponding to the post. For example, a product manager corresponds to a job function of "product aware", and a research and development engineer corresponds to a job function of "proficient programming language". Therefore, we need to distinguish the post description information of different posts and determine the function information in the post description information.
S'102-2, sorting the post characteristics of the post description information according to a characteristic sorting model based on an attention mechanism.
Wherein the importance of each post characteristic is different for different posts. For example, for a product manager, the importance of the "product aware" job is greater than the importance of the "proficient programming language" job, and vice versa for a development engineer; the most important post characteristic for a post is the post function of the post, so that the post characteristics of the post information need to be sorted according to the importance degree of the post characteristics according to different posts.
S' 102-3, setting weights for resume contents corresponding to the position characteristics in the candidate resumes.
Wherein the weights are related to the ordering of the post features; the requirements for each station characteristic are different according to the different stations. In order to make the resume content weight corresponding to the position feature larger the position feature is ranked more forward.
S' 102-4, determining the matching degree of the candidate resume according to the resume content after the weight is set, and sequencing the candidate resume according to the matching degree.
In this embodiment, in order to better screen resume contents of candidates, not only can weights of paragraph vectors be automatically adjusted according to the role categories of the posts and importance of post features, but also different working experiences in the resume are weighted according to importance degrees and correlations of the different working experiences, specifically, as shown in fig. 1d, different working experiences are imported into an attention mechanism (feature sorting model based on the attention mechanism), and a system can distinguish more important working experiences in the resume and the post description.
In one embodiment, the method for matching the human sentry further comprises the following steps:
and displaying the initial candidate resume and the interpretation information of the initial candidate resume according to the screening result.
In this embodiment, the system locates the key sentences and paragraphs in the post description and the key sentences and paragraphs corresponding to them in the resume through the attention mechanism in the neural network, and interprets and outputs the corresponding fields for reference by the HR.
Corresponding to the embodiment of the people's post matching method, the invention also provides an embodiment of a people's post matching system.
Fig. 2 is a schematic block diagram of a people's post matching system according to an exemplary embodiment of the present invention, where the people's post matching system includes:
the screening module 21 is configured to screen initial candidate resumes based on the post description information to determine candidate resumes matched with the post description information from the initial candidate resumes;
a sorting module 22, configured to sort the candidate resumes according to the matching degrees;
and the interpretation module 23 is configured to display the candidate resume and the interpretation information of the candidate resume according to the sorting result, where the interpretation information includes resume contents matched with each position feature in the candidate resume.
Preferably, the screening module comprises:
a content extraction unit, configured to, for each initial candidate resume, extract resume content corresponding to each post feature from the initial candidate resume;
and the resume determining unit is used for determining the initial candidate resume as the candidate resume under the condition that the extracted resume contents all accord with the characteristic conditions of the corresponding post characteristics.
Preferably, the sorting module comprises:
the matching degree calculation unit inputs the candidate resume into a pre-trained resume matching model, and outputs a first matching degree of the candidate resume and the position description information and a second matching degree of the candidate resume and each position characteristic by the resume matching model;
and the matching degree sorting unit sorts the candidate resumes according to the first matching degree and the second matching degree.
Preferably, the people post matching system further comprises:
the model training module is used for acquiring a large number of positive samples and negative samples as training samples, wherein the positive samples are resumes matched with the post description information, and the negative samples are resumes unmatched with the post description information;
and the model training module is also used for adjusting parameters of the neural network according to the training samples so as to obtain the resume matching model.
Preferably, the sorting module comprises:
a field structuring unit, configured to convert resume contents corresponding to each post feature in the candidate resume into a structured field containing an order relationship;
and the field matching degree sorting unit is used for determining the matching degree of the candidate resume according to the structured field and sorting the candidate resume according to the matching degree.
Preferably, the sorting module comprises:
a position function determining unit for determining the position function corresponding to the position description information;
the post characteristic sorting unit is used for sorting the post characteristics of the post description information according to a characteristic sorting model based on an attention mechanism;
the weight setting unit is used for setting weights for resume contents corresponding to all the post characteristics in the candidate resumes, and the weights are related to the sequencing of the post characteristics;
and the function matching degree sorting unit is used for determining the matching degree of the candidate resume according to the resume content after the weight is set, and sorting the candidate resume according to the matching degree.
For the system embodiment, since it basically corresponds to the method embodiment, reference may be made to the partial description of the method embodiment for relevant points. The above-described system embodiments are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the invention. One of ordinary skill in the art can understand and implement it without inventive effort.
Fig. 3 is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present invention.
The electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the human-job matching method in the embodiment. The electronic device 30 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
The electronic device 30 may be embodied in the form of a general purpose computing device, which may be, for example, a server device. The components of the electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, and a bus 33 that couples various system components including the memory 32 and the processor 31.
The bus 33 includes a data bus, an address bus, and a control bus.
The memory 32 may include volatile memory, such as Random Access Memory (RAM) 321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
The processor 31 executes various functional applications and data processing, such as a human job matching method in the present embodiment, by executing the computer program stored in the memory 32.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through input/output (I/O) interfaces 35. Also, model-generating device 30 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via network adapter 36. As shown, the network adapter 26 communicates with the other modules of the model-generating device 30 over a bus 33. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the model-generating device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the human job matching method in the embodiment of the present invention.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation manner, the present invention may also be implemented in the form of a program product, which includes program code for causing a terminal device to execute the steps of implementing the people matching method in this embodiment when the program product runs on the terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device, partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (14)
1. A people post matching method is characterized by comprising the following steps:
s1, screening initial candidate resumes based on the post description information to determine candidate resumes matched with the post description information from the initial candidate resumes; wherein the post description information comprises a plurality of post characteristics;
s2, sorting the candidate resumes according to the matching degree;
and S3, displaying the candidate resume and the explanation information of the candidate resume according to the sequencing result, wherein the explanation information comprises resume contents matched with the position characteristics in the candidate resume.
2. The human-job matching method according to claim 1, wherein step S1 comprises:
for each initial candidate resume, extracting resume content corresponding to each post characteristic from the initial candidate resume;
and under the condition that the extracted resume contents all accord with the characteristic conditions of the corresponding post characteristics, determining the initial candidate resume as the candidate resume.
3. The people post matching method according to claim 1, wherein the step S2 comprises:
inputting the candidate resume into a pre-trained resume matching model, and outputting a first matching degree of the candidate resume and the post description information and a second matching degree of the candidate resume and each post characteristic by the resume matching model;
and sorting the candidate resumes according to the first matching degree and the second matching degree.
4. The human sentry matching method of claim 3, wherein the resume matching model is trained by the following steps:
acquiring a large number of positive samples and negative samples as training samples, wherein the positive samples are resumes matched with the post description information, and the negative samples are resumes unmatched with the post description information;
and adjusting parameters of the neural network according to the training samples to obtain the resume matching model.
5. The human-job matching method according to claim 1, wherein the step S2 comprises:
converting the resume content corresponding to each post characteristic in the candidate resume into a structured field containing an order relation;
and determining the matching degree of the candidate resume according to the structured field, and sequencing the candidate resume according to the matching degree.
6. The human-job matching method according to claim 1, wherein the step S2 comprises:
determining a post role corresponding to the post description information;
sequencing the post characteristics of the post description information according to a characteristic sequencing model based on an attention mechanism;
setting weights for resume contents corresponding to all the post characteristics in the candidate resumes, wherein the weights are related to the sequencing of the post characteristics;
and determining the matching degree of the candidate resume according to the resume content after the weight is set, and sequencing the candidate resume according to the matching degree.
7. A people post matching system, characterized in that the people post matching system comprises:
the screening module is used for screening the initial candidate resumes based on the post description information so as to determine candidate resumes matched with the post description information from the initial candidate resumes;
the sorting module is used for sorting the candidate resumes according to the matching degree;
and the interpretation module is used for displaying the candidate resume and the interpretation information of the candidate resume according to the sequencing result, wherein the interpretation information comprises resume contents matched with the position characteristics in the candidate resume.
8. The human job matching system of claim 7, wherein the screening module comprises:
a content extraction unit, configured to, for each initial candidate resume, extract resume content corresponding to each post feature from the initial candidate resume;
and the resume determining unit is used for determining the initial candidate resume as the candidate resume under the condition that the extracted resume contents all accord with the characteristic conditions of the corresponding post characteristics.
9. The human job matching system of claim 7, wherein the ranking module comprises:
the matching degree calculation unit inputs the candidate resume into a resume matching model trained in advance, and outputs a first matching degree of the candidate resume and the post description information and a second matching degree of the candidate resume and each post characteristic through the resume matching model;
and the matching degree sorting unit sorts the candidate resumes according to the first matching degree and the second matching degree.
10. The human sentry matching system of claim 9, wherein the human sentry matching system further comprises:
the model training module is used for acquiring a large number of positive samples and negative samples as training samples, wherein the positive samples are resumes matched with the post description information, and the negative samples are resumes unmatched with the post description information;
the model training module is further used for adjusting parameters of the neural network according to the training samples to obtain the resume matching model.
11. The human job matching system of claim 7, wherein the ranking module comprises:
a field structuring unit, configured to convert resume contents corresponding to each post feature in the candidate resume into a structured field containing an order relationship;
and the field matching degree sorting unit is used for determining the matching degree of the candidate resume according to the structured field and sorting the candidate resume according to the matching degree.
12. The human job matching system of claim 7, wherein the ranking module comprises:
a position function determining unit for determining the position function corresponding to the position description information;
the post characteristic sorting unit is used for sorting the post characteristics of the post description information according to a characteristic sorting model based on an attention mechanism;
the weight setting unit is used for setting weights for resume contents corresponding to all post characteristics in the candidate resumes, and the weights are related to the sequencing of the post characteristics;
and the function matching degree sorting unit is used for determining the matching degree of the candidate resume according to the resume content after the weight is set, and sorting the candidate resume according to the matching degree.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the people matching method of any one of claims 1-6 when executing the computer program.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for people matching according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111091116.7A CN115841316A (en) | 2021-09-17 | 2021-09-17 | Method and system for matching human posts, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111091116.7A CN115841316A (en) | 2021-09-17 | 2021-09-17 | Method and system for matching human posts, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115841316A true CN115841316A (en) | 2023-03-24 |
Family
ID=85574192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111091116.7A Pending CN115841316A (en) | 2021-09-17 | 2021-09-17 | Method and system for matching human posts, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115841316A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116562837A (en) * | 2023-07-12 | 2023-08-08 | 深圳须弥云图空间科技有限公司 | Person post matching method, device, electronic equipment and computer readable storage medium |
-
2021
- 2021-09-17 CN CN202111091116.7A patent/CN115841316A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116562837A (en) * | 2023-07-12 | 2023-08-08 | 深圳须弥云图空间科技有限公司 | Person post matching method, device, electronic equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9165254B2 (en) | Method and system to predict the likelihood of topics | |
| US8781989B2 (en) | Method and system to predict a data value | |
| US20200193382A1 (en) | Employment resource system, method and apparatus | |
| US9720912B2 (en) | Document management system, document management method, and document management program | |
| CN103123633A (en) | Generation method of evaluation parameters and information searching method based on evaluation parameters | |
| Aher et al. | Course recommender system in E-learning | |
| CN113887930B (en) | Question-answering robot health evaluation method, device, equipment and storage medium | |
| CN105677902A (en) | Resume display method | |
| CN113378970A (en) | Sentence similarity detection method and device, electronic equipment and storage medium | |
| CN115563271A (en) | Artificial intelligence accounting data entry method, system, equipment and storage medium | |
| CN115841316A (en) | Method and system for matching human posts, electronic equipment and storage medium | |
| US20240070188A1 (en) | System and method for searching media or data based on contextual weighted keywords | |
| CN116777692A (en) | Online learning method, device, equipment and storage medium based on data analysis | |
| Klosterman | Data Science Projects with Python: A case study approach to gaining valuable insights from real data with machine learning | |
| CN114722280A (en) | User portrait based course recommendation method, device, equipment and storage medium | |
| CN114861104A (en) | Webpage display method, system, equipment and storage medium based on intention identification | |
| CN111078972A (en) | Method and device for acquiring questioning behavior data and server | |
| US20140236940A1 (en) | System and method for organizing search results | |
| CN117493210B (en) | Micro-service tool evaluation method and system | |
| Sangeetha et al. | Feedback and recommendation system using natural language processing | |
| CN113486266B (en) | Page label adding method, device, equipment and storage medium | |
| CN117875330B (en) | Emotion analysis method, device and storage medium based on natural language processing | |
| CN114239595B (en) | Intelligent return visit list generation method, device, equipment and storage medium | |
| CN118095270B (en) | Construction method and device of logic analysis graph, electronic equipment and storage medium | |
| Sodiq et al. | Sentiment Analysis of BMKG Weather Information Service Using K-Nearest Neighbor Method |
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 |