CN111144831B - Accurate selection screening system and method suitable for recruitment - Google Patents
Accurate selection screening system and method suitable for recruitment Download PDFInfo
- Publication number
- CN111144831B CN111144831B CN201911152703.5A CN201911152703A CN111144831B CN 111144831 B CN111144831 B CN 111144831B CN 201911152703 A CN201911152703 A CN 201911152703A CN 111144831 B CN111144831 B CN 111144831B
- Authority
- CN
- China
- Prior art keywords
- information
- module
- person
- sample
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the field of talent recruitment and resume management, in particular to software design by utilizing big data and internet technology. The invention is realized by the following technical scheme: a system for accurately screening person selections suitable for recruitment, comprising: a triplet building module; the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring triple record information, and each group of triple record information comprises three types of data of personnel ID, a relation label and a label value; a knowledge graph construction module; a sample formation module; a similarity calculation module; a matching module; and the system is used for sequencing the personnel information according to the similarity calculation result of the similarity calculation module and pushing the result to the user. The invention aims to provide a precise screening method for person selection suitable for recruitment, which is used for calculating similarity or speaking density of all candidates with sample person selection by analyzing sample person selection information, recommending the candidates by adopting a person-finding search mode and ensuring accurate and efficient search results.
Description
Technical Field
The invention relates to the field of talent recruitment and resume management, in particular to software design by utilizing big data and internet technology.
Background
With the economic development, the refinement of social division and the increase of the number of employment market job seekers and personnel units, the method is more important for the selection and discrimination of suitable talents.
In the traditional operation mode, a human unit carries out personnel screening by reading the resume of talents. The resume records information such as personal calendar, experience, speciality, hobby and the like. And checking talent content through a paper resume or an electronic resume by a personnel unit, and screening the matching degree of talents.
However, this is done by manually screening the human resume with the HR of the human unit. Because the number of resumes received every day may be very large, the existing manual screening method has the defects of high labor cost and low screening efficiency. On this basis, the prior art uses automated software techniques to optimize this process. For example, chinese patent publication No. CN109816325A discloses a resume screening method based on big data analysis, which adopts the technical scheme that a software system is used to automatically score resumes recorded in the system, and HR of a human unit can be automatically scored according to the system as a basis for selection. However, such an operation mode is to score the resume in the later period, and does not involve the precise screening of the initial resume, i.e. the facing number of resumes is still huge.
There is also a resume screening and matching method and system disclosed in chinese patent document No. CN10698090961A, for example, which implement screening resumes of suitable recruiters from a large number of resumes through steps of character search, screening sorting, bidirectional matching, and the like, thereby achieving the effects of reducing personnel cost and increasing work efficiency. However, in practice, especially in the process of performing a set search with keywords or tag information, multiple searches are required due to the absence of some candidate tags. In addition, the condition selection of suitable talents is complex and multidimensional, and can not be deleted simply through filtering operation, namely for the human unit HR, the search condition is often difficult to describe accurately, and the condition of selection omission of suitable talents can be caused by simple keyword screening and filtering.
Disclosure of Invention
The invention aims to provide a precise screening method for person selection suitable for recruitment, which is used for calculating similarity or speaking density of all candidates with sample person selection by analyzing sample person selection information, recommending the candidates by adopting a person-finding search mode and ensuring accurate and efficient search results.
The technical purpose of the invention is realized by the following technical scheme: a system for accurately screening person selections suitable for recruitment, comprising:
a triplet building module; the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring triple record information, and each group of triple record information comprises three types of data of personnel ID, a relation label and a label value;
a knowledge graph construction module; forming a complete knowledge graph based on the plurality of groups of triple record information, wherein the knowledge graph comprises nodes and edges, the personnel ID forms personnel nodes, the label numerical values form label nodes, and all the nodes are connected by the edges;
a sample formation module; appointing a recommended person selection, and forming the information of the recommended person selection into sample data;
a similarity calculation module; putting the sample data into the complete knowledge graph, and calculating the similarity between the data in the knowledge graph and the sample data;
a matching module; and the system is used for sequencing the personnel information according to the similarity calculation result of the similarity calculation module and pushing the result to the user.
Preferably, each person includes multiple sets of the triplet record information, the triplet record information includes common triplet record information and history item triplet record information, and the history item triplet record information is used for recording information confirmed by the person being selected in past history operations.
Preferably, the present invention further includes a history record generating module, where the history record generating module is configured to track confirmation of the user on the result pushed by the matching module, and when the user finally confirms the pushing result, the corresponding person generates a new set of triplet record information, and the triplet record information is reorganized to record confirmation data of the item.
Preferably, the sample forming module comprises a custom sample module, and the custom sample module is used for a user to custom edit sample data.
Preferably, the sample forming module includes a query module, and the query module is configured to input a user ID by a user and search for data information corresponding to the user ID.
Preferably, the algorithm used by the similarity calculation module is an LFM algorithm or a long-short term recommendation algorithm based on a neural network.
Preferably, the algorithm used by the similarity calculation module is a person rank random walk algorithm, and the formula of the algorithm is as follows: ,.
A screening method of a precise screening system for person selection suitable for recruitment is characterized by comprising the following steps:
s01, information collection;
in the step, all the person selection information and the label information in the system are collected, a corresponding ID is created for the person selection information, and a corresponding ID is also created for a label object of the label information;
s02, establishing a knowledge graph;
converting the information collected in the last step into triple records, wherein each triple record comprises three types of data including a person ID, a relationship tag and a tag value, and then constructing a knowledge graph by all the triple record data;
s03, sample specification; a user specifies a sample, wherein the sample comprises personnel information and label information corresponding to the personnel information;
s04, searching a node;
searching nodes similar to the sample information in the whole knowledge graph according to the sample information;
s05, matching and sorting;
calculating the similarity between the sample information and the candidate by using a knowledge graph and a matching algorithm, and sequencing the candidate according to the similarity from high to low;
s06, recommending;
after sorting, the candidate with high similarity is pushed to the user.
Preferably, in the step S03, when sample data exists in the entire knowledge graph, the user only needs to provide user ID information corresponding to the sample; when sample data exists in the middle of the whole knowledge graph, a user needs to define the sample by himself, and the person corresponding to the sample data and the label information corresponding to the person are edited.
Preferably, the present invention further comprises, after the step S06, a step S07 of recording history information; in this step, if the user confirms a candidate, the candidate adds a piece of history item triple record information, and the reorganization history item triple information includes the item tag information and the confirmation result.
In conclusion, the invention has the following beneficial effects:
1. the candidate is screened in a mode of a knowledge graph, so that the tag information is rich, and the search result is efficient.
2. The method abandons the mode that the transmission technology carries out rough screening by keyword filtering, but provides data of sample personnel, calculates the similarity or the speaking density by taking the data as a sample, and recommends the candidate by adopting a search mode of finding people, so that the search result is accurate.
3. The confirmation information of each item can form a new historical data label to reenter the data of the personnel, so that the knowledge map is full.
Description of the drawings:
fig. 1 is a schematic diagram of each node in the first embodiment.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The present embodiment is only for explaining the present invention, and it is not limited to the present invention, and those skilled in the art can make modifications of the present embodiment without inventive contribution as needed after reading the present specification, but all of them are protected by patent law within the scope of the claims of the present invention.
In the embodiment 1, a precise screening system for person selection suitable for recruitment and a screening method thereof, in the step of S01, information collection, electronic establishment of information of all person selections is achieved. In the prior art, the system has an electronic talent database, and in the technical scheme, the database is processed. Each candidate will have a corresponding electronic message. And collecting the information in the database.
In S02, in the knowledge-graph construction information, the information in the database collected above is converted into a triple record. This triplet information has three parts, namely a person ID, a relationship tag and a tag value. Take the candidate Zhang III as an example, zhang III, sex male, age 25, highest scholarly as a researcher, professional direction as finance, intended work place as Shanghai, and work experience as 3 years. Then as shown in fig. 1, A1 in fig. 1 is a node, i.e. a candidate node, and this A1 specifies an ID for zhang san of the candidate, which is unique in the system, for example 000001. A2 and A3 are IDs of candidates lie four and king five, e.g. 000002 and 000003. The electronic information of one third may include several nodes, such as a small node Z1, which is essentially a tag node. This label node contains two pieces of information, namely a relationship label and a label value. The relationship label indicates the category of the label, and the category can also be coded in the actual storage. For example, Z1 has a relationship label of "gender," which may be coded as "01," and a label value of "male. Similarly, Z4 is "highest scholarship, graduate", Z5 is "professional direction, finance", and Z6 is "intention place of work, shanghai". And the large and small nodes are connected by virtue of edges, namely straight lines in the figure 1. Under the technical process, the electronic information of a candidate Zhang III comprises a plurality of triples of information, and each triplet of information comprises the corresponding relation between a candidate and a certain label of the candidate. A1 and Z1, Z4, Z5 and Z6 in the upper left corner of the picture 1 jointly form all the electronized information of Zhang III. In S02, the electronic information is formed into the triple records, which are further constructed into a complete knowledge graph. As in FIG. 1, the three triplet records owned by three candidates are collectively constructed to be a knowledge graph. In actual use, the system has massive candidate information, and the information forms massive triple records and jointly constructs a complex and mutually crossed knowledge map.
In this example, Z5 is connected to both A1 and A2 because Z5 represents data "Pro direction, finance" and candidate Liqu, whose Pro direction is also finance. Z1 is connected to both A1 and A3. Since Z1 is "sex, male" and A3 represents WangWu, also a male applicant.
The storage mode adopted by the scheme is a storage mode of the schema database, and compared with a storage mode of a common relational mapping database in the prior art, the storage and searching efficiency is higher.
Next, S03, a sample specification step, is entered. Compared with the prior art, the method requires the user to search, filter and screen the keywords in a completely different way. In this case, the user may provide one or more sample data. For example, the user feels that Zhao Liu, the candidate in the database is the ideal candidate for the applicant. The specified ID of zhao liu in the system can be entered.
S04, a node searching step and S05, and a matching and sorting step. These two steps are closely coupled. And the system searches out the node corresponding to the ID according to the specified ID input in the third step. I.e. all the small nodes corresponding to the large node in fig. 1, i.e. all the tag information corresponding to the ID. Subsequently, by using a knowledge graph and combining with a recommendation system algorithm, other similar Person selections can be recommended for the selected Person selection IDs, in the embodiment, a Person Rank random walk algorithm is adopted, and an LFM algorithm and a long-short term recommendation algorithm based on a neural network can be replaced; the algorithm can give the similarity between the selections. Taking the Person Rank random walk algorithm as an example, as described above, the knowledge Graph may be regarded as a Graph (Graph) including nodes (V) and edges (E), the nodes include the Person-selected ID and the label object, that is, A1 in fig. 1, and the zhangsan ID is a node. And the corresponding sex, profession, work experience, intention and place, etc. are also one small node, such as Z1, Z4, Z5 and Z6. The edges are nodes and the connection relations between the nodes, for example, industries and functions in the triples are all used as the connection relations between the nodes.
The principle of the Person Rank algorithm is that after a certain node starts to randomly walk to other surrounding nodes and is repeatedly performed for a plurality of times, the probability of other nodes walking from the node can be calculated, the probability indicates the 'intimacy' of other nodes and the node, and the higher the intimacy, the more similar the nodes are.
Specifically, the formula is as follows:
where Pj (uk) is the probability of a hop from node j to node i. adj (i) represents all neighbor nodes of node i. Initializing Pj (uj) to 1, and after a plurality of iterations, calculating the arrival probability of all other nodes, namely Pj = < Pj (u 0), pj (u 2), \8230;, pj (un) >.
And other alternative recommendation algorithms, such as an LFM algorithm, are provided, the principle is that a graph is converted into an adjacent matrix, different edges have different weights, a hidden vector can be obtained through iteration of the LFM algorithm to describe the Person selection, the hidden vectors of the Person selection 1 and the Person selection 2 are used as an inner product, the similarity of the two persons can be obtained, and finally, the effect similar to that of the Person Rank can be obtained.
The system ranks from high to low based on the calculated affinity values.
And S06, outputting the result, and pushing the candidate with the top rank to the user by the system.
Example 2: the difference from embodiment 1 is in the S03 sample specification step.
In this embodiment, the system does not have sample data, and at this time, the user needs to customize one sample data. This is done by creating a new data record and entering corresponding label information, such as age, gender, expertise, intended work site, etc., which also form a plurality of triples as described above. The following steps are the same as the embodiment 1, and the similarity calculation module and the matching module are also adopted to calculate and sort the similarity or the intimacy degree, and then push the similarity or the intimacy degree.
Example 3: the difference from embodiment 1 is that there is a step S07, i.e., a history information recording step, after the step S06. As described above, there are three parts of the triplet information, namely, the person ID, the relationship tag, and the tag value. There are two types of tags, one is a general record tag and one is a history item record tag. The former is the label reflecting the objective information of job seeker, such as age, sex, graduation school, specialty, etc. The latter is the record of the confirmed selection.
Specifically, when the user obtains the list of candidates pushed by the system in the recommendation step of S06, confirmation is started. At this time, the user will create a new project, reflecting the location of the required talents, for example, to find a high-level software engineer. At this point, the "item" is the relationship label, and the "advanced software engineer" is the label value. If the user finally confirms the pushing result of Zhang III and clicks the confirmation button, the system adds a small node such as Z10 to A1, and the relationship label and the label value of Z10 are the 'project, advanced software engineer'.
Such operation is more beneficial to the fullness of the whole knowledge graph and the high efficiency of later-period personnel searching.
Claims (10)
1. A system for accurately screening person selections suitable for recruitment is characterized by comprising: a triplet building module; the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring triple record information, and each group of triple record information comprises three types of data of personnel ID, a relation label and a label value; a knowledge graph construction module; forming a complete knowledge graph based on the plurality of groups of triple record information, wherein the knowledge graph comprises nodes and edges, the personnel ID forms personnel nodes, the label numerical values form label nodes, and all the nodes are connected by the edges; a sample formation module; appointing a recommended person selection, and forming the information of the recommended person selection into sample data; a similarity calculation module; putting the sample data into the complete knowledge graph, and calculating the similarity between the data in the knowledge graph and the sample data; the similarity calculation depends on a Person Rank algorithm, the Person Rank algorithm is probability calculation, namely the probability calculation is carried out on other nodes around from a certain node at random, and after the probability calculation is carried out for a plurality of times, the probability calculation can be carried out on other nodes which walk from the node; a matching module; and the system is used for sequencing the personnel information according to the similarity calculation result of the similarity calculation module and pushing the result to the user.
2. The accurate screening system for person selection suitable for recruitment according to claim 1, wherein: each person comprises a plurality of groups of triple record information, the triple record information comprises common triple record information and historical item triple record information, and the historical item triple record information is used for recording information which is selected and confirmed by the person in past historical operation.
3. The accurate screening system for the selection of the person for recruitment according to claim 2, wherein: the system further comprises a history record generation module, wherein the history record generation module is used for tracking the confirmation condition of the user on the result pushed by the matching module, when the user finally confirms the pushing result, the corresponding personnel generate a group of new triple record information, and the confirmation data of the item is recorded in the reorganization triple record information.
4. The accurate screening system for person selection suitable for recruitment according to claim 1, 2 or 3, wherein: the sample forming module comprises a user-defined sample module, and the user-defined sample module is used for user-defined editing of sample data.
5. The accurate screening system for person selection suitable for recruitment according to claim 1, 2 or 3, wherein: the sample forming module comprises a query module, and the query module is used for inputting a user ID by a user and searching data information corresponding to the user ID.
6. The accurate screening system for person selection suitable for recruitment according to claim 1, wherein: the algorithm used by the similarity calculation module is an LFM algorithm or a long-short term recommendation algorithm based on a neural network.
7. The accurate screening system for person selection suitable for recruitment according to claim 1, wherein: the algorithm used by the similarity calculation module is a person rank random walk algorithm, and the formula of the algorithm is as follows:
，
。
8. the screening method of the selection precision screening system for recruitment according to any one of claims 1 to 7, characterized by comprising the following steps: s01, information collection; in the step, all the person selection information and the label information in the system are collected, corresponding IDs are created for the person selection information, and corresponding IDs are also created for label objects of the label information; s02, establishing a knowledge graph; converting the information collected in the last step into triple records, wherein each triple record comprises three types of data including a person ID, a relationship tag and a tag value, and then constructing a knowledge graph by all the triple record data; s03, sample specification; a user designates a sample, wherein the sample comprises personnel information and label information corresponding to the personnel information; s04, searching a node; searching nodes similar to the sample information in the whole knowledge graph according to the sample information; s05, matching and sorting; calculating the similarity between the sample information and the candidate by using a knowledge graph and a matching algorithm, and sequencing the candidate according to the similarity from high to low; s06, recommending; after sorting, the candidate with high similarity is pushed to the user.
9. The screening method of the accurate screening system for selection of people for recruitment according to claim 8, wherein the screening method comprises the following steps: in the step S03, when sample data exists in the entire knowledge graph, the user only needs to provide user ID information corresponding to the sample; when sample data exists in the middle of the whole knowledge graph, a user needs to define the sample by himself, and the person corresponding to the sample data and the label information corresponding to the person are edited.
10. The screening method of the accurate screening system for selection of people for recruitment according to claim 8, wherein the screening method comprises the following steps: after the step S06, further comprising step S07, a history information recording step; in this step, if the user confirms a candidate, the candidate adds a piece of history item triple record information, and the reorganization history item triple information includes the item tag information and the confirmation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911152703.5A CN111144831B (en) | 2019-11-22 | 2019-11-22 | Accurate selection screening system and method suitable for recruitment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911152703.5A CN111144831B (en) | 2019-11-22 | 2019-11-22 | Accurate selection screening system and method suitable for recruitment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111144831A CN111144831A (en) | 2020-05-12 |
| CN111144831B true CN111144831B (en) | 2023-03-24 |
Family
ID=70516604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911152703.5A Active CN111144831B (en) | 2019-11-22 | 2019-11-22 | Accurate selection screening system and method suitable for recruitment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144831B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111737486B (en) * | 2020-05-28 | 2023-06-02 | 广东轩辕网络科技股份有限公司 | Person post matching method and storage device based on knowledge graph and deep learning |
| CN113240400A (en) * | 2021-06-02 | 2021-08-10 | 北京金山数字娱乐科技有限公司 | Candidate determination method and device based on knowledge graph |
| CN115526590B (en) * | 2022-09-16 | 2023-08-04 | 深圳今日人才信息科技有限公司 | Efficient person post matching and re-pushing method combining expert knowledge and algorithm |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106384230A (en) * | 2016-10-21 | 2017-02-08 | 北京搜前途科技有限公司 | Method of matching work experience in resume with recruitment job and method of matching resume with recruitment information |
| CN109241341A (en) * | 2018-05-09 | 2019-01-18 | 上海大学 | A kind of video display of knowledge based map preferentially recommender system and method |
| CN109191281A (en) * | 2018-08-21 | 2019-01-11 | 重庆富民银行股份有限公司 | A kind of group's fraud identifying system of knowledge based map |
| CN109684441A (en) * | 2018-12-21 | 2019-04-26 | 义橙网络科技(上海)有限公司 | Matched method, system, equipment and medium are carried out to position and resume |
| CN109800354B (en) * | 2019-01-09 | 2021-06-08 | 考拉征信服务有限公司 | Resume modification intention identification method and system based on block chain storage |
| CN110020913A (en) * | 2019-02-20 | 2019-07-16 | 中国人民财产保险股份有限公司 | Products Show method, equipment and storage medium |
-
2019
- 2019-11-22 CN CN201911152703.5A patent/CN111144831B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111144831A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100583804C (en) | Method and system for processing social network expert information based on expert value propagation algorithm | |
| CN111144831B (en) | Accurate selection screening system and method suitable for recruitment | |
| CN101223525B (en) | Relationship networks | |
| US10157218B2 (en) | Author disambiguation and publication assignment | |
| US20130159325A1 (en) | Bi-model recommendation engine for recommending items and peers | |
| US10133807B2 (en) | Author disambiguation and publication assignment | |
| CN104573130B (en) | The entity resolution method and device calculated based on colony | |
| CN103620590B (en) | Associated system and method for image to text and text to image | |
| CN109918563B (en) | Book recommendation method based on public data | |
| CN107895303B (en) | Personalized recommendation method based on OCEAN model | |
| US10387805B2 (en) | System and method for ranking news feeds | |
| CN112966091B (en) | Knowledge map recommendation system fusing entity information and heat | |
| CN109408578A (en) | One kind being directed to isomerous environment monitoring data fusion method | |
| CN110737805B (en) | Method and device for processing graph model data and terminal equipment | |
| CN111475625A (en) | News manuscript generation method and system based on knowledge graph | |
| Goncalves et al. | Gathering alumni information from a web social network | |
| CN111159559A (en) | Method for constructing recommendation engine according to user requirements and user behaviors | |
| CN112784049B (en) | Text data-oriented online social platform multi-element knowledge acquisition method | |
| CN111078859B (en) | Author recommendation method based on reference times | |
| Wijayanti et al. | K-means cluster analysis for students graduation: case study: STMIK Widya Cipta Dharma | |
| CN112395508A (en) | Artificial intelligence talent position recommendation system and processing method thereof | |
| CN109299368B (en) | Method and system for intelligent and personalized recommendation of environmental information resources AI | |
| Gunawan et al. | C4. 5, K-Nearest Neighbor, Naïve Bayes, and Random Forest Algorithms Comparison to Predict Students' on TIME Graduation | |
| US20160217216A1 (en) | Systems, methods, and devices for implementing a referral search | |
| US20170004200A1 (en) | Author disambiguation and publication assignment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230712 Address after: 313200 No. 2-30, Building 4, No. 10, Keyuan Road, Wuyang Street, Deqing County, Huzhou, Zhejiang Province (Mount Mogan National High tech Zone) Patentee after: Zhejiang alpha Human Resources Co.,Ltd. Address before: Room 1058, Floor 1, Nanxun Technology Innovation Park, No. 666 Chaoyang Road, Nanxun Town, Nanxun District, Huzhou City, Zhejiang Province, 313000 Patentee before: Zhejiang Weiyuan Intelligent Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |