CN116562837A - Person post matching method, device, electronic equipment and computer readable storage medium - Google Patents
Person post matching method, device, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN116562837A CN116562837A CN202310849537.4A CN202310849537A CN116562837A CN 116562837 A CN116562837 A CN 116562837A CN 202310849537 A CN202310849537 A CN 202310849537A CN 116562837 A CN116562837 A CN 116562837A
- Authority
- CN
- China
- Prior art keywords
- post
- information
- job seeker
- features
- implicit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 239000013598 vector Substances 0.000 claims abstract description 90
- 230000003068 static effect Effects 0.000 claims abstract description 16
- 238000003062 neural network model Methods 0.000 claims description 29
- 230000006399 behavior Effects 0.000 claims description 22
- 238000012545 processing Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000003058 natural language processing Methods 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 7
- 230000004048 modification Effects 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims 1
- 239000000758 substrate Substances 0.000 claims 1
- 238000013527 convolutional neural network Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000011176 pooling Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The application relates to the technical field of computers, and provides a person post matching method, a device, electronic equipment and a computer readable storage medium. The method comprises the following steps: acquiring job seeker information and post information; respectively acquiring explicit characteristics of job seeker information and explicit characteristics of post information, wherein the explicit characteristics are used for representing static characteristics of the job seeker information and the post information; respectively acquiring implicit characteristics of job seekers and implicit characteristics of post information, wherein the implicit characteristics are used for representing dynamic characteristics of the job seekers and the posts; splicing the explicit features and the implicit features of the job seeker information to obtain a job seeker feature vector, and splicing the explicit features and the implicit features of the post information to obtain a post feature vector; and performing post matching based on the job seeker feature vector and the post feature vector. The method can improve the matching precision and efficiency of the person post.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a person post matching method, a device, an electronic device, and a computer readable storage medium.
Background
The Person-Job Fit (PJF) task is a bilateral scene task, and is different from the traditional recommendation task in that only attention is paid to user interest preference, and both recommendation parties have active behaviors and self preference. For example, a job seeker has its own target position, and a job post also has a capability requirement for the job seeker. How to extract effective features from job seeker information and post information so as to match job seekers with posts is a technical problem to be solved.
Disclosure of Invention
In view of this, the embodiments of the present application provide a person post matching method, apparatus, electronic device, and computer readable storage medium, so as to solve the problem of insufficient person post matching precision in the prior art.
In a first aspect of an embodiment of the present application, a person post matching method is provided, including:
acquiring job seeker information and post information;
respectively acquiring explicit characteristics of job seeker information and explicit characteristics of post information, wherein the explicit characteristics are used for representing static characteristics of the job seeker information and the post information;
respectively acquiring implicit characteristics of job seekers and implicit characteristics of post information, wherein the implicit characteristics are used for representing dynamic characteristics of the job seekers and the posts;
Splicing the explicit features and the implicit features of the job seeker information to obtain a job seeker feature vector, and splicing the explicit features and the implicit features of the post information to obtain a post feature vector;
and performing post matching based on the job seeker feature vector and the post feature vector.
In a second aspect of the embodiments of the present application, a person post matching device is provided, including:
the information acquisition module is configured to acquire job seeker information and post information;
the first feature acquisition module is configured to acquire explicit features of job seeker information and explicit features of post information respectively, wherein the explicit features are used for representing static features of the job seeker information and the post information;
the second feature acquisition module is configured to acquire implicit features of job seekers and implicit features of post information respectively, wherein the implicit features are used for representing dynamic features of the job seekers and the posts;
the splicing module is configured to splice the explicit feature and the implicit feature of the job seeker information to obtain a job seeker feature vector, and splice the explicit feature and the implicit feature of the post information to obtain a post feature vector;
and the matching module is configured to perform post matching based on the job seeker feature vector and the post feature vector.
In a third aspect of the embodiments of the present application, there is provided an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect of the embodiments of the present application, there is provided a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above method.
Compared with the prior art, the embodiment of the application has the beneficial effects that: the explicit features of static features representing job seeker information and post information are respectively obtained, the implicit features of dynamic features representing job seeker information and post information are respectively obtained, the explicit features and the implicit features of the job seeker information are spliced to obtain job seeker feature vectors, the explicit features and the implicit features of the post information are spliced to obtain post feature vectors, and further, the person post matching is carried out based on the job seeker feature vectors and the post feature vectors, so that the person post matching precision is improved, and the person post matching efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a person post matching method based on PJFNN.
FIG. 2 is a flow chart of a person post matching method provided in an embodiment of the present application.
FIG. 3 is a flow chart of a method for post matching based on job seeker feature vectors and post feature vectors according to an embodiment of the present application.
Fig. 4 is a flowchart of a method for obtaining explicit features of job seekers and posts according to an embodiment of the present application.
Fig. 5 is a flowchart of a method for obtaining implicit characteristics of a job seeker and a post according to an embodiment of the present application.
FIG. 6 is a schematic diagram of a person post matching device provided in an embodiment of the present application.
Fig. 7 is a schematic diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
Along with the development of science and technology, many traditional industry enterprises are devoted to digital transformation, and various functions of the enterprises are developing corresponding online products, wherein the manpower products have important roles. For some enterprises with large volumes, in order to realize staff development diversification, the manpower department can provide digital manpower products for completing business and running water among different functions; meanwhile, staff can select the desired post delivery from a plurality of posts through the digital manpower product of the running water. Taking a property enterprise as an example, it has tens of thousands of employees and can offer nearly thousands of posts. Staff select a position expected by the staff from the near thousand positions to deliver, so that the screening difficulty is high, and missed positions are likely to occur; meanwhile, personnel needing to be interviewed are selected from a plurality of received resumes by corresponding personnel resource management personnel, and the personnel most conforming to the post requirements cannot be determined quickly and accurately.
On the basis, the person post matching task is derived. In the related art, person post matching can be achieved based on a Person post matching convolutional neural network model (Person-Job Fit NueralNetwork, PJFNN). FIG. 1 is a flow chart of a person post matching method based on PJFNN. As shown in fig. 1, the method comprises the steps of:
In step S101, the resume text and the post text are preprocessed.
In one example, the original resume text of the job seeker and the post text of the job post may be preprocessed, including chinese word segmentation, stop word filtering, word vector conversion, and the like, to obtain the preprocessed resume text and post text.
In step S102, the preprocessed resume text and post text are input into the PJFNN model.
In one example, the pre-processed resume text and post text may be input to the PJFNN model for subsequent processing.
In step S103, feature extraction is performed on the input data to obtain feature vectors of the resume text and feature vectors of the post text.
In an example, the PJFNN model may be a Convolutional neural network (Convolutional NeuralNetwork, CNN) model, and features in the resume text and the post text may be extracted through operations such as rolling and pooling in the CNN model, and feature vectors of the resume text and feature vectors of the post text may be respectively constructed based on the extracted features. Wherein, the characteristics of the resume text and the post text are used for representing the semantics and importance of the text. In some embodiments, different pooling processes may be used for the resume text and the post text, such as a Mean-pooling (Mean-pooling) process for the resume text and a Max-pooling (Max-pooling) process for the post text.
In step S104, the feature vector of the resume text and the feature vector of the post text are matched based on the similarity algorithm, so as to obtain the similarity of the resume text and the post text.
In an example, the feature vector of the resume text and the feature vector of the post text may be matched by using a cosine similarity calculation method, a euclidean distance calculation method, and the like, so as to calculate and obtain the similarity of the resume text and the post text.
In step S105, the similarity is ranked, and post recommendation or job seeker recommendation is performed based on the ranking result.
In an example, the calculated similarities may be ranked from high to low, and one or more posts with highest similarities may be recommended to job seekers, or one or more job seekers with highest similarities may be recommended to job owners.
In step S103, when extracting features of the input data, the features are usually implemented by using a traditional Word2Vec model, and the extracted features can only reflect the semantics in the content recorded in the resume text or the post text, and cannot give more accurate semantics in combination with information such as the background and the field. Meanwhile, since post description texts tend to be well formatted, different requirements often independently represent different aspects of expertise. In contrast, in the resume text of the job seeker, each work experience generally contains various expertise, so that high-precision matching cannot be realized only according to text content.
Furthermore, the content recorded by the resume text or the post text is static, that is, when the related technology performs post matching, only the static features of the job seeker and the post are extracted for matching. However, dynamic information such as historical post browsing conditions, resume delivery conditions, interview conditions of job seekers, historical clicked amount of posts, received resume conditions and the like can also be used as characteristics of job seekers and posts for matching the human posts.
In view of this, the embodiment of the application provides a person post matching method, by respectively obtaining explicit features representing static features of job seeker information and post information, and respectively obtaining implicit features representing dynamic features of job seeker information and post information, and splicing the explicit features and the implicit features of the job seeker information to obtain job seeker feature vectors, splicing the explicit features and the implicit features of the post information to obtain post feature vectors, and further performing person post matching based on the job seeker feature vectors and the post feature vectors, the person post matching precision is improved, and the person post matching efficiency is improved.
FIG. 2 is a flow chart of a person post matching method provided in an embodiment of the present application. As shown in FIG. 2, the person post matching method comprises the following steps:
In step S201, job seeker information and post information are acquired.
In step S202, an explicit feature of job seeker information and an explicit feature of post information are acquired, respectively.
Wherein the explicit features are used to characterize static features of job seeker information and post information.
In step S203, implicit features of job seeker information and implicit features of post information are acquired, respectively.
Wherein the implicit features are used to characterize dynamic features of job seekers and posts.
In step S204, the explicit feature and the implicit feature of the job seeker information are spliced to obtain a job seeker feature vector, and the explicit feature and the implicit feature of the post information are spliced to obtain a post feature vector.
In step S205, post matching is performed based on the job applicant feature vector and the post feature vector.
In the embodiment of the application, the person post matching method can be executed by a terminal device or a server. The terminal device may be hardware or software. When the terminal device is hardware, it may be a variety of electronic devices having a display screen and supporting communication with a server, including but not limited to smartphones, tablet computers, laptop and desktop computers, and the like; when the terminal device is software, it may be installed in the electronic device as described above. The terminal device may be implemented as a plurality of software or software modules, or may be implemented as a single software or software module, which is not limited in this embodiment of the present application. Further, various applications may be installed on the terminal device, such as a data processing application, an instant messaging tool, social platform software, a search class application, a shopping class application, and the like.
The server may be a server that provides various services, for example, a background server that receives a request transmitted from a terminal device with which communication connection is established, and the background server may perform processing such as receiving and analyzing the request transmitted from the terminal device and generate a processing result. The server may be a server, a server cluster formed by a plurality of servers, or a cloud computing service center, which is not limited in this embodiment of the present application.
The server may be hardware or software. When the server is hardware, it may be various electronic devices that provide various services to the terminal device. When the server is software, it may be a plurality of software or software modules that provide various services for the terminal device, or may be a single software or software module that provides various services for the terminal device, which is not limited in this embodiment of the present application.
In the embodiment of the application, job seeker information and post information can be acquired. The job seeker information comprises resume text of the job seeker, historical behaviors of the job seeker and the like, and the job information comprises job description text, job related historical information and the like.
In the embodiment of the application, the explicit characteristics of job seeker information and post information can be acquired. In one example, explicit features of job seeker information may be obtained from resume text of job seekers, and explicit features of job information may be obtained from job description text of a job. Further, the obtained explicit features are used for representing static features of job seeker information and post information. The static features are features which do not change with time in job seeker information and post information. The static features are independent of the historic behavior of the job seeker and the historic information of the posts.
In the embodiment of the application, implicit characteristics of job seeker information and post information can be acquired. In one example, the implicit features of the job seeker information may be obtained from historical behavior of the job seeker, and the implicit features of the job information may be obtained from the job related historical information of the job. Further, the obtained implicit features are used for representing dynamic features of job seeker information and post information. The dynamic characteristics are characteristics of time change in job seeker information and post information. The dynamic characteristics may be determined by historical behavior of job seekers and post history information.
In the embodiment of the application, the explicit feature and the implicit feature of the job seeker information can be spliced to obtain the job seeker feature vector, and the explicit feature and the implicit feature of the post information are spliced to obtain the post feature vector. Further, post matching may be performed based on the obtained job applicant feature vector and post feature vector.
According to the technical scheme provided by the embodiment of the application, the explicit features for representing the job seeker and the post static features are respectively extracted, the implicit features for representing the job seeker and the post dynamic features are respectively extracted, the explicit features and the implicit features of the job seeker are spliced to obtain the feature vectors of the job seeker, the explicit features and the implicit features of the post are spliced to obtain the feature vectors of the post, so that the person post matching is performed based on the feature vectors of the job seeker and the post feature vectors, the person post matching precision can be improved, and the person post matching efficiency is improved.
In the embodiment of the application, the explicit characteristics of the job seeker information may include: text semantic features of job seeker information and associated semantic features of the job seeker information. The text semantic features of the job seeker information comprise semantic features which can be directly determined based on the content recorded in the job seeker resume text. The associated semantic features of the job seeker information comprise semantic features after the content recorded in the job seeker resume text is associated. The association processing of the content recorded in the resume text of the job seeker may be that the content recorded in the resume text of the job seeker is combined with semantic features processed by predefined fields and/or the content recorded in the resume text of the job seeker is combined with semantic features processed by information such as background and field.
In an example, if at least one item is filled in as a working experience column of the resume text of a job seeker and the experience of a certain item is completed by the item responsible person, the characteristics of the information corresponding to the "item responsible person", "leadership capability", "management capability" and the like can be extracted as text semantic characteristics of the job seeker.
Further, if the education experience column of the resume text of a job seeker is filled in the university of XXX, the characteristics of the information corresponding to the key university, the Nth class university and the like can be extracted as the associated semantic characteristics of the job seeker, wherein N is a positive integer. That is, a corresponding interval field can be established for part of the features, and the features in the resume text of the job seeker are converted into the corresponding interval fields to be represented, so that the number of the features can be reduced, and the matching speed can be improved. It is understood that the section field conversion process may be performed for the age, sex, etc. of the job seeker in addition to the educational history. The specific switchable features are set according to actual needs and are not limited herein. That is, the information such as self-introduction, work experience and the like in the job seeker resume text can be extracted, and the information such as historical work posts, ages and the like can be abstracted from the information to form part of explicit characteristics for the processing of the person post matching model.
Furthermore, if the work experience column of the resume text of a job seeker is filled in with XXX items participating in the group, the associated semantic features of the items can be determined by searching for matches in a pre-constructed database. For example, the job seeker may fill in the name of the item, and by retrieving matches in the database to determine that the item is a "commercial property item", features associated with "commercial property" may be built for the job seeker. By adopting the method, the accuracy of the person post matching can be further improved. Meanwhile, when the person post matching method provided by the application is applied to running water in an enterprise, the database is established without difficulty such as difficult data acquisition and the like, and the difficulty that the matching speed is too slow due to overlarge data quantity.
In this embodiment, explicit characteristics of the post information may include: text semantic features of post information and associated semantic features of post information. The post information text semantic features comprise semantic features which can be directly determined based on the content recorded in the post description text. The post information associated semantic features comprise semantic features obtained by carrying out association processing on contents recorded in post description texts. The association processing of the content recorded in the post description text may be that the content recorded in the post description text is combined with semantic features processed by predefined fields, and/or that the content recorded in the post description text is combined with semantic features processed by information such as background and field.
In an example, if a job capability requirement field of a post description text is filled with a requirement for having a leader capability, features corresponding to information such as "leader capability", "project responsible person", "management capability" and the like can be extracted as text semantic features of the post.
Furthermore, if the working experience requirement column of the post description text is filled in, and the job seeker is required to have working experiences for three to five years, the characteristics of the information corresponding to the medium working experience level and the like can be extracted as the associated semantic characteristics of the post. That is, a corresponding interval field can be established for part of the features, and the features in the post description text are converted into the corresponding interval fields to be represented, so that the number of the features can be reduced, and the matching speed can be improved. Likewise, the specific convertible feature is set according to the actual needs, and is not limited herein.
Furthermore, if the working capacity requirement column of the text is described in a certain post and the experience of the commercial property projects is filled in, the names or keywords of the commercial property projects of the group can be determined by searching the matching in the pre-built database, and the names or keywords of the projects are extracted as the associated semantic features of the post. By adopting the method, the accuracy of the person post matching can be further improved. Meanwhile, when the person post matching method provided by the application is applied to running water in an enterprise, the database is established without difficulty such as difficult data acquisition and the like, and the difficulty that the matching speed is too slow due to overlarge data quantity.
In the embodiment of the application, the text semantic features of the job seeker information and the text semantic features of the post information can be obtained through the trained first neural network model. For example, text semantic features of job seeker information and text semantic features of post information can be extracted through a trained CNN model, and the obtained text semantic features are represented by vectors.
In the embodiment of the application, the associated semantic features of the job seeker information and the associated semantic features of the post information can be obtained through a Natural language processing (Natural LanguageProcessing, NLP) algorithm and/or a feature matching algorithm. For example, the associated semantic features of the corresponding interval fields in the job seeker information and the post information can be obtained through an NLP algorithm, and the associated semantic features related to the background and the field in the job seeker information and the post information can be obtained through a feature matching algorithm, such as a lookup table.
In the embodiment of the application, the implicit characteristic of the job seeker information can be obtained through the trained second neural network model, and the implicit characteristic of the post information can be obtained through the trained third neural network model. Wherein the second neural network model and the third neural network model comprise time-series neural network models.
In the embodiment of the application, the implicit characteristic of the job seeker information is used for representing the dynamic characteristic of the job seeker, and the implicit characteristic of the post information is used for representing the dynamic characteristic of the post, so that two trained time series neural networks can be used for respectively modeling the historical behaviors of the job seeker and the post so as to extract the implicit characteristic of the job seeker and the post. Wherein the second neural network model and the third neural network model may be Long short-term memory (LSTM) network models.
In this embodiment of the present application, historical behavior information of a job applicant may be obtained, where the historical behavior information of the job applicant includes at least one of the following: post browsing information, resume delivery information, interview information, resume modification information. And (5) inputting the historical behavior information of the job seeker into a second neural network model to obtain the implicit characteristic of the job seeker information. By modeling and analyzing the historical behaviors of the job seeker, the information such as the position preference, the job seeker communication time period and the frequency of the job seeker can be extracted from the historical behaviors, so that more matched positions can be recommended for the job seeker.
In this embodiment of the present application, the history information of the post may be obtained, where the history information of the post includes at least one of the following: post browsed information, receiving resume information, interview information, post description modification information. And inputting the post history information into a third neural network model to obtain the implicit characteristic of the post information. By modeling and analyzing the historical information of the posts, the information such as the hot degree of the posts, the types of the attracted job seekers and the like can be extracted from the historical information, so that more matched job seekers can be recommended for the posts, and basis can be provided for post management personnel to modify post description texts.
According to the technical scheme provided by the embodiment of the application, the LSTM is used for modeling the historical behavior of the job seeker and the historical information of the posts, so that the implicit characteristics of the two parties are extracted, the fusion of the explicit characteristics and the implicit characteristics is completed after the characteristic processing of the historical behavior sequence, the purpose of comprehensively considering various characteristics of the job seeker and the posts from different angles is achieved, the information of the job seeker and the posts can be more comprehensively described, and the accuracy of matching of the human posts is improved. Meanwhile, the method is an end-to-end framework, not only can different feature representation methods be flexibly introduced, but also the combination modes of different models can be changed according to the needs, so that the flexibility is high, the variable job-seeking market demands can be met, and the model generalization capability is high.
FIG. 3 is a flow chart of a method for post matching based on job seeker feature vectors and post feature vectors according to an embodiment of the present application. As shown in FIG. 3, the person post matching method comprises the following steps:
in step S301, it is determined that the inner product of the job seeker feature vector and the post feature vector is a person post matching value.
In step S302, in response to the person post match value being greater than a preset threshold, it is determined that the job seeker matches the post.
In step S303, the person post matching values are ranked from high to low, and job seekers corresponding to the first K person post matching values are determined to be matched with posts.
Wherein K is a positive integer.
In the embodiment of the disclosure, the inner product of the job seeker feature vector and the post feature vector can be determined to be a person post matching value. The inner product may be calculated by calculating a dot product similarity, a cosine similarity, a euclidean similarity, and the like.
In the embodiment of the disclosure, the determined person post matching value can be compared with a preset threshold value, and in response to the person post matching value being greater than the preset threshold value, the job seeker is determined to be matched with the post. On the other hand, in response to the person post match value being less than or equal to the preset threshold, it is determined that the job seeker does not match the post. The preset threshold may be set as needed, and is not limited herein.
In the embodiment of the disclosure, the person post matching values can be ranked from high to low, and job seekers corresponding to the previous K person post matching values can be determined to be matched with posts.
According to the technical scheme provided by the embodiment of the application, the person post matching value is determined by solving the inner product of the job seeker feature vector and the post feature vector, and whether the job seeker is matched with the post or not is further determined based on the person post matching value, so that the realization is simple and the precision is high.
Fig. 4 is a flowchart of a method for obtaining explicit features of job seekers and posts according to an embodiment of the present application. As shown in fig. 4, semantic entities, such as age, sex, graduation, etc., in resume text or post description text of the job seeker can be extracted through an NLP algorithm, the entities are converted into explicit features, and modeling is completed through a depth factor decomposition machine (Deep Factorization Machine, deep fm), so as to obtain vectors of the explicit features corresponding to the semantic entities. As shown in the left link of fig. 4, the semantic entity extracted by the NLP algorithm may be a coded representation, and the code is input to the splicing module after being processed by the factorizer (Factorization Machine, FM) module and the linear module.
On the other hand, the resume text or the free text in the post description text of the job seeker can be extracted through the convolutional neural network, and the vector of the explicit feature corresponding to the free text is obtained. And combining the vector of the explicit feature corresponding to the semantic entity with the vector of the explicit feature corresponding to the free text to obtain the explicit feature of the job seeker and the post. As shown in the right link of fig. 4, features of the free text field, such as a leader, web, test, etc., are extracted through the convolutional neural network, and the features are processed through the convolutional module, the linear module, etc., to obtain feature vectors, which are also input to the input splicing module. The splicing module can further perform linear processing after splicing the explicit features.
In some cases, semantic entities in resume text or post description text of the job seeker can be extracted, and the extracted semantic entities are matched with features in a pre-established database, so that vectors of explicit features related to the background and the field of the semantic entities are obtained. The combination of the vector of the explicit feature related to the background and the field of the semantic entity with the vector of the explicit feature corresponding to the semantic entity and the vector of the explicit feature corresponding to the free text can obtain the explicit feature of more accurate and comprehensive job seekers and posts.
Fig. 5 is a flowchart of a method for obtaining implicit characteristics of a job seeker and a post according to an embodiment of the present application. As shown in FIG. 5, the LSTM model on the left is centered on a post, and can obtain the history information of the post, including modeling the interaction information of the post with a plurality of job seekers, to extract the implicit characteristics of the post information. The input of the left LSTM model can be a vector obtained by carrying out one-bit effective encoding onehot processing on the explicit characteristics of post information and the post matching result, wherein f E () For job huntingExplicit characteristics of the person, onehot () is a one-bit significant code, g E (p j ) Is an explicit feature of post, p j Represents the j-th post, j is a positive integer. Results g obtained by model extraction I (p j ) Is an implicit feature of the post. The LSTM model on the right side takes the job seeker as the center, can acquire the historical behavior information of the job seeker, and comprises the interaction information of the job seeker and a plurality of posts for modeling so as to extract the implicit characteristics of the job seeker.
The input of the LSTM model on the right side in FIG. 5 may be a vector obtained by performing one-bit efficient encoding one-hot processing on the explicit feature of job seeker information and the person post matching result, wherein f E (r i(k-1) ) For the i-th job seeker's feature of delivering resumes for the (k-1) -th time, onehot (t) i(k-1) ) Recording information for delivering resume for the (k-1) th time of the ith job seeker, onehot (t) i(k-1) ) =0 represents not recorded, onehot (t i(k-1) ) =1 for admission, g E () The result f obtained by model extraction is the explicit feature of the post I (c i ) An implicit feature for job seekers, where c i And representing the ith job seeker, wherein i and k are positive integers.
Implicit feature g of post extracted I (p j ) And implicit feature f of job seeker I (c i ) Solving an inner product, performing S-curve function Sigmoid processing, and further performing back propagation training to obtain an optimal implicit characteristic g I (p j ) And f I (c i )。
When person post matching is performed, the formula f (c) = [ f E (c);f I (c)]And g (p) = [ g E (p);g I (p)]Splicing explicit features of job seekers and posts with implicit features, wherein f (c) is a feature vector of the post, f E (c) Is an explicit feature of post, f I (c) G (p) is the feature vector of the job seeker, g E (p) explicit feature of job seeker, g I (p) is an implicit feature of the job seeker.
Further, v=σ (f (c)) can be obtained by the formula T g (p)) calculates the interior of job seeker feature vector and post feature vectorAnd (5) product, and determining a person post matching value. Wherein V is the person post matching value, sigma is the inner product operation, and T is the transposition operation.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein in detail.
The following are device embodiments of the present application, which may be used to perform method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.
FIG. 6 is a schematic diagram of a person post matching device provided in an embodiment of the present application. As shown in fig. 6, the person post matching device includes:
the information acquisition module 601 is configured to acquire job seeker information and post information.
The first feature acquisition module 602 is configured to acquire explicit features of job seeker information and explicit features of post information, respectively.
Wherein the explicit features are used to characterize static features of job seeker information and post information.
The second feature acquiring module 603 is configured to acquire an implicit feature of job seeker information and an implicit feature of post information respectively.
Wherein the implicit features are used to characterize dynamic features of job seekers and posts.
The splicing module 604 is configured to splice the explicit feature and the implicit feature of the job seeker information to obtain a job seeker feature vector, and splice the explicit feature and the implicit feature of the post information to obtain a post feature vector.
The matching module 605 is configured to perform post matching based on the job applicant feature vector and the post feature vector.
According to the technical scheme provided by the embodiment of the application, the explicit features for representing the job seeker and the post static features are respectively extracted, the implicit features for representing the job seeker and the post dynamic features are respectively extracted, the explicit features and the implicit features of the job seeker are spliced to obtain the feature vectors of the job seeker, the explicit features and the implicit features of the post are spliced to obtain the feature vectors of the post, so that the person post matching is performed based on the feature vectors of the job seeker and the post feature vectors, the person post matching precision can be improved, and the person post matching efficiency is improved.
In this embodiment of the present application, explicit features of job seeker information include: text semantic features of job seeker information and associated semantic features of job seeker information; the text semantic features of the job seeker information comprise semantic features which are directly determined based on the content recorded in the job seeker resume text, and the associated semantic features of the job seeker information comprise semantic features which are obtained by carrying out association processing on the content recorded in the job seeker resume text. Explicit features of post information include: text semantic features of post information and associated semantic features of post information; the text semantic features of the post information comprise semantic features which are directly determined based on the content recorded in the post description text, and the associated semantic features of the post information comprise semantic features after the content recorded in the post description text is subjected to association processing.
In this embodiment of the present application, the obtaining of the explicit feature of the job seeker information and the explicit feature of the post information respectively includes: acquiring text semantic features of job seeker information and text semantic features of post information through a trained first neural network model; and acquiring the associated semantic features of the job seeker information and the associated semantic features of the post information through a natural language processing algorithm and/or a feature matching algorithm.
In this embodiment of the present application, obtaining implicit features of job seeker information and implicit features of post information respectively includes: acquiring implicit characteristics of job seeker information through a trained second neural network model; acquiring implicit characteristics of post information through a trained third neural network model; wherein the second neural network model and the third neural network model comprise time-series neural network models.
In this embodiment of the present application, obtaining implicit features of job seeker information through a trained second neural network model includes: acquiring historical behavior information of job seekers; inputting historical behavior information of the job seeker into a second neural network model to obtain implicit characteristics of the job seeker information; wherein the historical behavior information of the job seeker comprises at least one of the following: post browsing information, resume delivery information, interview information, resume modification information.
In this embodiment of the present application, obtaining implicit characteristics of post information through a trained third neural network model includes: acquiring historical information of posts; inputting the historical information of the post into a third neural network model to obtain the implicit characteristic of the post information; wherein the post history information includes at least one of: post browsed information, receiving resume information, interview information, post description modification information.
In this embodiment of the present application, carry out post matching based on job seeker feature vector and post feature vector, include: determining that the inner product of the job seeker feature vector and the post feature vector is a person post matching value; determining that the job seeker is matched with the post in response to the person post matching value being greater than a preset threshold; or sorting the person post matching values from high to low, and determining that job seekers corresponding to the previous K person post matching values are matched with posts, wherein K is a positive integer.
According to the technical scheme provided by the embodiment of the application, the LSTM is used for modeling the historical behavior of the job seeker and the historical information of the posts, so that the implicit characteristics of the two parties are extracted, the fusion of the explicit characteristics and the implicit characteristics is completed after the characteristic processing of the historical behavior sequence, the purpose of comprehensively considering various characteristics of the job seeker and the posts from different angles is achieved, the information of the job seeker and the posts can be more comprehensively described, and the accuracy of matching of the human posts is improved. Meanwhile, the method is an end-to-end framework, not only can different feature representation methods be flexibly introduced, but also the combination modes of different models can be changed according to the needs, so that the flexibility is high, the variable job-seeking market demands can be met, and the model generalization capability is high.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present application in any way.
Fig. 7 is a schematic diagram of an electronic device provided in an embodiment of the present application. As shown in fig. 7, the electronic device 7 of this embodiment includes: a processor 701, a memory 702 and a computer program 703 stored in the memory 702 and executable on the processor 701. The steps of the various method embodiments described above are implemented by the processor 701 when executing the computer program 703. Alternatively, the processor 701, when executing the computer program 703, performs the functions of the modules/units of the apparatus embodiments described above.
The electronic device 7 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 7 may include, but is not limited to, a processor 701 and a memory 702. It will be appreciated by those skilled in the art that fig. 7 is merely an example of the electronic device 7 and is not limiting of the electronic device 7 and may include more or fewer components than shown, or different components.
The processor 701 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application SpecificIntegrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.
The memory 702 may be an internal storage unit of the electronic device 7, for example, a hard disk or a memory of the electronic device 7. The memory 702 may also be an external storage device of the electronic device 7, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like provided on the electronic device 7. The memory 702 may also include both internal storage units and external storage devices of the electronic device 7. The memory 702 is used to store computer programs and other programs and data required by the electronic device.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present application implements all or part of the flow in the methods of the above embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program may implement the steps of the respective method embodiments described above when executed by a processor. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (10)
1. A person post matching method, comprising:
acquiring job seeker information and post information;
respectively acquiring the explicit characteristics of the job seeker information and the explicit characteristics of the post information, wherein the explicit characteristics are used for representing static characteristics of the job seeker information and the post information;
acquiring implicit features of the job seeker information and implicit features of the post information respectively, wherein the implicit features are used for representing dynamic features of the job seeker and the post;
splicing the explicit features and the implicit features of the job seeker information to obtain a job seeker feature vector, and splicing the explicit features and the implicit features of the post information to obtain a post feature vector;
And performing post matching based on the job seeker feature vector and the post feature vector.
2. The method of claim 1, wherein the step of determining the position of the substrate comprises,
the explicit features of the job seeker information include: text semantic features of the job seeker information and associated semantic features of the job seeker information; the text semantic features of the job seeker information comprise semantic features which are directly determined based on the content recorded in the job seeker resume text, and the associated semantic features of the job seeker information comprise semantic features after the content recorded in the job seeker resume text is associated;
explicit characteristics of the post information include: text semantic features of the post information and associated semantic features of the post information; the text semantic features of the post information comprise semantic features which are directly determined based on the content recorded in the post description text, and the associated semantic features of the post information comprise semantic features which are obtained by carrying out association processing on the content recorded in the post description text.
3. The method of claim 2, wherein the separately obtaining the explicit feature of the job seeker information and the explicit feature of the post information comprises:
Acquiring text semantic features of the job seeker information and text semantic features of the post information through a trained first neural network model; and
and acquiring the associated semantic features of the job seeker information and the associated semantic features of the post information through a natural language processing algorithm and/or a feature matching algorithm.
4. The method of claim 1, wherein the separately obtaining the implicit characteristic of the job seeker information and the implicit characteristic of the post information comprises:
acquiring implicit characteristics of the job seeker information through a trained second neural network model;
acquiring implicit characteristics of the post information through a trained third neural network model;
wherein the second and third neural network models comprise time-series neural network models.
5. The method of claim 4, wherein the obtaining implicit features of the job seeker information via the trained second neural network model comprises:
acquiring historical behavior information of the job seeker;
inputting the historical behavior information of the job seeker into the second neural network model to obtain the implicit characteristic of the job seeker information;
Wherein the historical behavior information of the job seeker comprises at least one of the following:
post browsing information, resume delivery information, interview information, resume modification information.
6. The method of claim 4, wherein the obtaining implicit features of the post information via the trained third neural network model comprises:
acquiring history information of the posts;
inputting the post history information into the third neural network model to obtain implicit characteristics of the post information;
wherein the post history information includes at least one of:
post browsed information, receiving resume information, interview information, post description modification information.
7. The method of any of claims 1-6, wherein the post matching based on the job applicant feature vector and the post feature vector comprises:
determining that the inner product of the job seeker feature vector and the post feature vector is a person post matching value;
determining that the job seeker is matched with the post in response to the person post matching value being greater than a preset threshold; or alternatively
And sequencing the person post matching values from high to low, and determining that job seekers corresponding to the previous K person post matching values are matched with posts, wherein K is a positive integer.
8. A person post matching device, comprising:
the information acquisition module is configured to acquire job seeker information and post information;
the first feature acquisition module is configured to acquire the explicit features of the job seeker information and the explicit features of the post information respectively, wherein the explicit features are used for representing static features of the job seeker information and the post information;
the second feature acquisition module is configured to acquire implicit features of the job seeker information and implicit features of the post information respectively, wherein the implicit features are used for representing dynamic features of the job seeker and the post;
the splicing module is configured to splice the explicit feature and the implicit feature of the job seeker information to obtain a job seeker feature vector, and splice the explicit feature and the implicit feature of the post information to obtain a post feature vector;
and the matching module is configured to perform post matching based on the job seeker feature vector and the post feature vector.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310849537.4A CN116562837A (en) | 2023-07-12 | 2023-07-12 | Person post matching method, device, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310849537.4A CN116562837A (en) | 2023-07-12 | 2023-07-12 | Person post matching method, device, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116562837A true CN116562837A (en) | 2023-08-08 |
Family
ID=87503992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310849537.4A Pending CN116562837A (en) | 2023-07-12 | 2023-07-12 | Person post matching method, device, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116562837A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| CN111460813A (en) * | 2020-03-04 | 2020-07-28 | 北京网聘咨询有限公司 | Method and system for matching recruitment information and job hunting resume |
| WO2021169111A1 (en) * | 2020-02-28 | 2021-09-02 | 平安国际智慧城市科技股份有限公司 | Resume screening method and apparatus, computer device and storage medium |
| WO2021174919A1 (en) * | 2020-03-06 | 2021-09-10 | 平安科技（深圳）有限公司 | Method and apparatus for analysis and matching of resume data information, electronic device, and medium |
| CN114117222A (en) * | 2021-11-26 | 2022-03-01 | 北京金山数字娱乐科技有限公司 | Resume document matching method and device, computing device and storage medium |
| CN115392877A (en) * | 2022-08-31 | 2022-11-25 | 杭州君云信科商业管理有限公司 | System and method for post matching and recruitment |
| CN115619364A (en) * | 2022-08-03 | 2023-01-17 | 广州红海云计算股份有限公司 | Recruitment information publishing method, device and system based on artificial intelligence |
| CN115841316A (en) * | 2021-09-17 | 2023-03-24 | 上海大岂网络科技有限公司 | Method and system for matching human posts, electronic equipment and storage medium |
| CN116401464A (en) * | 2023-06-02 | 2023-07-07 | 深圳市一览网络股份有限公司 | Professional user portrait construction method, device, equipment and storage medium |
-
2023
- 2023-07-12 CN CN202310849537.4A patent/CN116562837A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110378544A (en) * | 2018-04-12 | 2019-10-25 | 百度在线网络技术（北京）有限公司 | A kind of personnel and post matching analysis method, device, equipment and medium |
| WO2021169111A1 (en) * | 2020-02-28 | 2021-09-02 | 平安国际智慧城市科技股份有限公司 | Resume screening method and apparatus, computer device and storage medium |
| CN111460813A (en) * | 2020-03-04 | 2020-07-28 | 北京网聘咨询有限公司 | Method and system for matching recruitment information and job hunting resume |
| WO2021174919A1 (en) * | 2020-03-06 | 2021-09-10 | 平安科技（深圳）有限公司 | Method and apparatus for analysis and matching of resume data information, electronic device, and medium |
| CN115841316A (en) * | 2021-09-17 | 2023-03-24 | 上海大岂网络科技有限公司 | Method and system for matching human posts, electronic equipment and storage medium |
| CN114117222A (en) * | 2021-11-26 | 2022-03-01 | 北京金山数字娱乐科技有限公司 | Resume document matching method and device, computing device and storage medium |
| CN115619364A (en) * | 2022-08-03 | 2023-01-17 | 广州红海云计算股份有限公司 | Recruitment information publishing method, device and system based on artificial intelligence |
| CN115392877A (en) * | 2022-08-31 | 2022-11-25 | 杭州君云信科商业管理有限公司 | System and method for post matching and recruitment |
| CN116401464A (en) * | 2023-06-02 | 2023-07-07 | 深圳市一览网络股份有限公司 | Professional user portrait construction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460513B (en) | Method and apparatus for generating click rate prediction model | |
| US20180336193A1 (en) | Artificial Intelligence Based Method and Apparatus for Generating Article | |
| US20180174037A1 (en) | Suggesting resources using context hashing | |
| US10452702B2 (en) | Data clustering | |
| CN110069698B (en) | Information pushing method and device | |
| CN112434151A (en) | Patent recommendation method and device, computer equipment and storage medium | |
| US11556851B2 (en) | Establishing a communication session between client terminals of users of a social network selected using a machine learning model | |
| US10956469B2 (en) | System and method for metadata correlation using natural language processing | |
| CN108121699B (en) | Method and apparatus for outputting information | |
| WO2020020287A1 (en) | Text similarity acquisition method, apparatus, device, and readable storage medium | |
| CN107798622B (en) | Method and device for identifying user intention | |
| CN113627797B (en) | Method, device, computer equipment and storage medium for generating staff member portrait | |
| CN112163081A (en) | Label determination method, device, medium and electronic equipment | |
| CN113343091A (en) | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program | |
| CN111078849B (en) | Method and device for outputting information | |
| CN111723180A (en) | Interviewing method and device | |
| CN116049379A (en) | Knowledge recommendation method, knowledge recommendation device, electronic equipment and storage medium | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| CN113268560A (en) | Method and device for text matching | |
| US11694029B2 (en) | Neologism classification techniques with trigrams and longest common subsequences | |
| CN116562837A (en) | Person post matching method, device, electronic equipment and computer readable storage medium | |
| CN115309865A (en) | Interactive retrieval method, device, equipment and storage medium based on double-tower model | |
| CN113934612A (en) | User portrait updating method and device, storage medium and electronic equipment | |
| CN114357242A (en) | Training evaluation method and device based on recall model, equipment and storage medium | |
| CN107657035B (en) | Method and apparatus for generating directed acyclic graph |
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 |