CN109726253B - Talent map and talent portrait construction method, device, equipment and medium - Google Patents
Talent map and talent portrait construction method, device, equipment and medium Download PDFInfo
- Publication number
- CN109726253B CN109726253B CN201811570090.2A CN201811570090A CN109726253B CN 109726253 B CN109726253 B CN 109726253B CN 201811570090 A CN201811570090 A CN 201811570090A CN 109726253 B CN109726253 B CN 109726253B
- Authority
- CN
- China
- Prior art keywords
- talent
- named entities
- map
- layer
- extension
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a talent map construction method, which comprises the steps of segmenting information in a talent information base to obtain a plurality of phrases, wherein the talent information base comprises a plurality of resumes, interview evaluation and/or performance examination tables; identifying and classifying concept layer named entities from the phrases according to predefined categories; extracting verb-object pairs from the information in the talent information base to obtain verbs corresponding to the named entities of each concept layer; and mapping the verbs into the relations among the concept layer named entities by using a pre-trained model to obtain a talent map which takes the concept layer named entities as nodes and the relations among the concept layer named entities as edges. Compared with the prior art, the talent map is constructed through the talent information base, a talent depicting system is established, and a good basis is provided for subsequent talent evaluation and depicting. In addition, the invention also relates to a talent portrait construction method.
Description
Technical Field
The invention relates to a talent map and a method, a device, equipment and a medium for constructing a talent portrait.
Background
In the development process of enterprises, talent competency is a key circle, and with the progress of technology, the quantification of talent competency of enterprises is more important. The model is an important tool in the field of human resource management, is derived from a capability model proposed by Miran, Weinmayama in the last sixties of the century, becomes a popular tool because of describing the effectiveness of the personnel demand of enterprises, and gradually becomes a method widely adopted by large and medium-sized enterprises after being introduced into China.
The knowledge graph as a popular method for knowledge representation breaks through ontology and semantic web research wave in the beginning of the century, has the characteristics of being readable to human and computable to a machine, can fully play the role of various complex knowledge representation scenes, and becomes a standard technology widely adopted by various large search index websites and AI service manufacturers when knowledge reasoning capacity is needed at the present stage. On the basis of knowledge of the knowledge map, effective information is extracted from the resume of talents or interview evaluation and the like, and the range of skills and working capacity of the talents is reasonably deduced from the effective information.
Disclosure of Invention
The invention provides a talent image construction system for deeply reasoning data such as resumes of talents based on a knowledge graph to obtain quantitative data of each dimension of a talent complete competence quality model, so as to quantitatively output the competence quality model of talents and provide support for subsequent talent screening.
In a first aspect of the invention, a talent map construction method is provided, comprising,
segmenting information in a talent information base to obtain a plurality of phrases, wherein the talent information base comprises a plurality of resumes, interview evaluation and/or performance examination tables;
identifying and classifying concept layer named entities from the phrases according to predefined categories;
extracting verb-object pairs from the information in the talent information base to obtain verbs corresponding to the named entities of each concept layer; and
and mapping the verbs into the relationship among the concept layer named entities by using a pre-trained model to obtain a talent map which takes the concept layer named entities as nodes and the relationship among the concept layer named entities as edges.
Compared with the prior art, the talent map is constructed through the talent information base, a talent depicting system is established, and a good basis is provided for subsequent talent evaluation and depicting.
Further, the predefined categories may include any one or more of schools, specialties, industries, companies, functions, skills, projects, work content, and/or certificates.
Further, the model for identifying the concept-level named entity in the phrase can be trained by a Bi-LSTM neural network.
In a second aspect of the invention, there is provided a method for constructing a talent representation using the talent map, comprising,
receiving material, wherein the material comprises any one or more of resumes, interview evaluations and performance review forms;
extracting information in the material, and segmenting the information in the material to obtain a plurality of phrases;
identifying and classifying example layer named entities from the phrases according to predefined categories;
mapping the instance-layer named entities into the talent map constructed as claimed in claim 1, resulting in a closure centered on each instance-layer named entity; and
counting the named entities of the example layer and the concept layer named entities covered in the intersection of the at least two closures to obtain a named entity set, and extracting the named entity set and the relationship among the named entities in the named entity set to be used as a talent portrait.
Further, for example layer named entities which cannot be mapped into the talent map, verb-object pairs can be extracted from the materials to obtain verbs corresponding to the example layer named entities, and the verbs are mapped into relations among the example layer named entities by using a pre-trained model; and updating the talent map by using the obtained example layer named entities and the relationship among the example layer named entities.
A third aspect of the present invention provides a talent map construction apparatus comprising,
the system comprises an information segmentation unit, a search unit and a search unit, wherein the information segmentation unit is configured to segment information in a talent information base to obtain a plurality of phrases, and the talent information base comprises a plurality of resumes, interview evaluation and/or performance examination tables;
the named entity recognition and classification unit is configured to recognize and classify the named entities at the concept layer from the phrases according to predefined categories;
the verb-object phrase extraction unit is configured to extract verb-object pairs from the information in the talent information base to obtain verbs corresponding to the named entities of each concept layer;
and the relationship mapping unit is configured to map the verbs into relationships among the concept layer named entities by using a pre-trained model to obtain the talent map which takes the concept layer named entities as nodes and the relationships among the concept layer named entities as edges.
A fourth aspect of the present invention provides a talent representation construction apparatus comprising,
a material receiving unit configured to receive materials, wherein the materials include any one or more of resumes, interview evaluations, and performance review forms;
the information segmentation unit is configured to extract information in the material and segment the information in the material to obtain a plurality of phrases;
the named entity recognition and classification unit is configured to recognize and classify the named entities of the example layer from the phrases according to predefined categories;
a closure identification unit configured to map the instance-layer named entities into the talent map constructed as claimed in claim 6, resulting in closures centered around each instance-layer named entity; and
the talent portrait construction unit is configured to count named entities of the instance layer and named entities of the concept layer covered in the intersection of the at least two closures to obtain a named entity set, and extract the named entity set and relations among the named entities in the named entity set to serve as a talent portrait.
A fifth aspect of the present invention provides an apparatus, which includes a processor, a memory, and a communication connection established between the processor and the memory;
a processor configured to read a program in a memory to execute the method provided by the foregoing first aspect or second aspect and any implementation manner thereof.
A sixth aspect of the present invention provides a non-volatile storage medium, in which a program is stored, and when the program is executed by a computing device, the computing device executes the method provided by the first aspect or the second aspect and any implementation manner thereof.
The invention extracts effective information from the talent resume, interview evaluation and the like based on knowledge of the knowledge map, can form reliable inference on the skill range of the talents beyond the knowledge skills mentioned in the resume and the like, can establish deep and comprehensive talent portrait and form a good system for depicting the talents.
Drawings
FIG. 1 is a flow diagram of a method of constructing a talent map according to an embodiment of the present invention.
FIG. 2 is a flow diagram of a method of constructing a talent representation according to an embodiment of the present invention.
FIG. 3 is a schematic diagram of an architecture of a human resources management system according to an embodiment of the invention.
Fig. 4 is a schematic structural diagram of a talent map according to an embodiment of the present invention.
FIG. 5 is a schematic diagram of a closure according to an embodiment of the invention.
Detailed Description
The invention is further illustrated with reference to the following specific embodiments and the accompanying drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. In addition, for convenience of description, only a part of structures or processes related to the present invention, not all of them, is illustrated in the drawings.
According to one embodiment of the present invention, a human resources management system is provided, as shown in FIG. 3. The system includes a talent map construction system 10 and a talent representation construction system 20.
The talent map construction system 10 comprises an information segmentation unit 101, a named entity identification and classification unit 102, a dynamic guest phrase extraction unit 103 and a relation mapping unit 104. The information segmentation unit 101 is configured to segment information in a talent information base to obtain a plurality of phrases, wherein the talent information base comprises a plurality of resumes, interview evaluation and/or performance examination tables; the Named Entity identifying and classifying unit 102 is configured to identify and classify concept Level Named entities (concept Level name Entity recognitions) from the phrases according to predefined categories; the verb-object phrase extraction unit 103 is configured to extract verb-object pairs from the information in the talent information base to obtain verbs corresponding to the named entities of each concept layer; the relationship mapping unit 104 is configured to map the verbs into relationships between the concept-level named entities by using a pre-trained model, so as to obtain a talent map with the concept-level named entities as nodes and the relationships between the concept-level named entities as edges.
The talent representation construction system 20 comprises a material receiving unit 205, an information segmentation unit 101, a named entity recognition and classification unit 102, a closure recognition unit 206, and a talent representation construction unit 207. Wherein the material receiving unit 205 is configured to receive various types of human management materials such as resumes, evaluations, performance review forms, and the like. The information segmentation unit 101 and the Named Entity identification and classification unit 102 have the same functions as those in the talent map construction system 10, and only process a certain newly received material such as a specific resume or evaluation, which is not described herein again, and for the sake of distinction, the Named Entity identified from the material received by the material receiving unit 205 is used as an Instance level Named Entity (instant level name Entity) in the embodiment. The closure identification unit 206 is configured to map the named entities of the instance layer identified in the named entity identification and classification unit to the talent map constructed by the talent map construction system 10, so as to obtain a closure centered on the named entities of each instance layer. The talent portrait construction unit 207 is configured to count named entities of an instance layer and named entities of a concept layer included in an intersection of at least two closures to obtain a named entity set, and extract the named entity set and relationships among the named entities in the named entity set to serve as a talent portrait.
Optionally, in some embodiments, there may be some example-layer named entities that cannot be mapped into the talent map, and the talent representation construction system 20 may further include a verb phrase extraction unit 103 and a relationship mapping unit 104, each configured to extract verb-object pairs from the material, obtain verbs corresponding to the example-layer named entities, and map the verbs to relationships between the example-layer named entities using a pre-trained model, so as to update the talent map with the obtained example-layer named entities and the relationships between the example-layer named entities.
Note that the human resources management system described above with reference to fig. 3 may be designed and used as a whole, or may be designed and used separately. For example, those skilled in the art may design and use talent atlas system 10 alone, or design and use talent representation construction system 20 alone, based on an existing talent atlas system 10. It should be noted that it is within the scope of the present invention whether both are designed and used separately or as a whole. The method for talent map construction and talent portrait construction using the above system will be described in detail below with reference to fig. 1 and 2.
As shown in fig. 1, according to an embodiment of the present invention, a talent map construction method is provided, which specifically includes the following steps:
and step S101, segmenting information in a talent information base to obtain a plurality of phrases, wherein the talent information base comprises a plurality of resumes, interview evaluation and/or performance review tables. The invention realizes a model with a Chunking function, noun phrases which are not required to be cut are marked out from a sentence, and the Chunking model can be realized by various general ways, which are not limited by the invention.
Subsequently, step S102 identifies and classifies the concept-layer named entity from the above phrases according to predefined categories. For example, the categories may be predefined according to the conventional classification in the human resource field, for example, 9 categories of schools, specialties, industries, companies, functions, skills, projects, work contents, and certificates may be defined, and the phrases obtained in step S101 are subjected to Named Entity Recognition (NER) by using a pre-trained model, and are classified into the 9 categories. In the machine learning based approach, NER can be used as a sequence labeling problem, and a large-scale corpus is used to learn a labeling model, so as to label each position of a sentence. Here, the NER model may employ a generative model HMM, a discriminant model CRF, or the like, and may be trained by a Bi-LSTM neural network, for example.
Based on the two models described in step S101 and step S102 above, each named entity, i.e., the concept level named entity, can be excerpted from the segmented text in the talent information base.
Subsequently, in step S103, verb-object pairs are extracted from the information in the talent information base to obtain verbs corresponding to the named entities in each concept layer. Subsequently, in step S104, the verb is mapped to the relationship between the named entities of each concept layer by using the pre-trained model, and the roles reflected by the verb are distinguished, so that the relationship between the named entities of each concept layer can be perfected. For example, named entities such as names of people and items may be extracted from the resume, and after verbs corresponding to the items are mapped, roles played by the candidates in the items, such as participating in the items or pushing the item to be realized, can be definitely obtained.
Subsequently, in step S105, a talent map is obtained, in which the concept-layer named entities are nodes and the relationship between the concept-layer named entities is an edge. For example, as shown in fig. 4-5, in which fig. 4 exemplarily shows a structure of the talent map, and a named entity of a certain position a is taken as a center, and 2 layers of nodes are shown, but in different embodiments, there may be one or more layers of nodes, and the number, types and relationships between the nodes in fig. 4 are exemplary illustrations and do not constitute a limitation to the present invention, and in practical applications, each node may continue to extend out of other related nodes. For example, as shown in fig. 5, for a named entity, which is a machine learning algorithm engineer, a network composed of a plurality of named entities directly or indirectly related to the named entity can be obtained through massive information in the talent information base.
The method for constructing the talent map is described above with reference to fig. 1, and after the talent map is constructed, the talent map can be used as a map library of an enterprise or a human resource platform, and a talent portrait can be rapidly inferred after a new brief is received. The specific method is shown in figure 2.
As shown in fig. 2, first, in step S201, materials are received, wherein the materials include any one or more of resumes, interview evaluation, and performance review forms.
Subsequently, in the steps S202-S203, information in the material is extracted, and the information in the material is segmented to obtain a plurality of phrases; and identifying instance layer named entities from the phrases and classifying according to the predefined categories. These two steps are similar to steps S101-S102, except that the material is different, steps S202-S203 are for the newly received material, and steps S101-S102 are for the content in the talent information base, and the description is omitted here for the sake of brevity.
Subsequently, step S204, the example layer named entities obtained in the above steps are mapped to the talent map constructed in the foregoing, and after mapping is completed, extended reasoning is performed on each node or part of key nodes according to the extension and reasoning relationship between each node in the talent map, so that a closure centered on each example layer named entity can be obtained, that is, a more complete range is obtained through closed-box sub-map reasoning based on each named entity.
In the invention, the closure refers to a set of all nodes and their relationships belonging to the same circle from a named entity as a central node in a graph, more than half of adjacent nodes of nodes obtained by extension after inference belong to the same circle, for example, as shown in fig. 5, a knowledge range that a machine learning algorithm engineer may have is shown, and as can be seen from the graph, the node of the machine learning algorithm engineer is taken as the center, it can be inferred that the node may have various kinds of knowledge such as artificial intelligence, mata, machine learning, Python, neural network, and data mining … …, that is, a first layer of extension nodes are inferred; taking Python nodes in the first layer of extended nodes as an example, from the Python nodes, a statistical analysis tool, a data mining tool, a scripting language, a programming language, computer programming and other nodes can be inferred, which are all adjacent nodes of the Python nodes, and most of the adjacent nodes can also be obtained by extended inference of MATLAB nodes, Java platform nodes and the like in the first layer of nodes, or by extended inference of a central node, namely, the nodes belong to the same circle. Thus, the node Python is included in the closure, and the same reasoning can be applied to other nodes belonging to the closure, as shown by the various open nodes in the figure. Thus, a set of central nodes (machine learning algorithm engineers) and the hollow nodes in fig. 5 and their relationships can be obtained, which is a closure of the knowledge range required by the machine learning algorithm engineers. Also, fig. 5 is a schematic diagram for illustrating the concept of closure, wherein the number and types of nodes and the relationship between the nodes are exemplary illustrations only, and do not limit the present invention. In different embodiments, there may be various different types, numbers, and extending relationships of nodes.
Then, in step S205, the named entities in the instance layer and the named entities in the concept layer included in the intersection of at least two closures centered on the named entities in the instance layer are counted to obtain a named entity set, and the named entity set and the relationship between the named entities in the named entity set are extracted to serve as a talent portrait.
In some embodiments, there may be some example-layer named entities that cannot be mapped to the talent map, that is, named entities that exceed the scope of the concept-layer named entities in the original talent map, for example-layer named entities that cannot be mapped to the talent map, steps S103-S104 may be repeated, verb-object pairs are extracted from the material, verbs corresponding to the example-layer named entities are obtained, and the verbs are mapped to relationships between the example-layer named entities using a pre-trained model. And updating the talent map by using the obtained example layer named entities and the relation among the example layer named entities.
In some embodiments, a dialogue robot system can be combined into the invention, and the dialogue robot is used to ask the candidate to obtain more information and send the information to the talent portrayal construction system of the invention as a material, so that the overall ability of the candidate can be more comprehensively inferred.
For example, the dialogue robot can receive the interview corpus, perform syntactic analysis, extract core vocabularies as features, and obtain some qualitative features of the human through a classifier and a rule engine, and the processing logic and results thereof can be highly similar to those of the counseling consultant. In addition, information such as working experience of the candidate can be input through a deep neural network, various mental states including motivation, mental state, expectation and the like behind each behavior of the candidate are obtained, various characteristics of the human personality layer and the element layer are extracted, and the extracted characteristics are collected into materials to be input into the talent portrait construction system.
The invention applies knowledge atlas technology to ensure that the talent portrait can form reliable inference on the skill range beyond the skill range mentioned in the resume or other materials of the talents, can overcome the defect that the resume or the traditional evaluation text is single in depicting the talents, and form a comprehensive model covering the talents from the aspects of skill, psychology, quality and the like. Meanwhile, the portrait can be subjected to digitalized assignment of all dimensions of people, so that the portrait can be used for a subsequent machine learning model and can be better served in the field of human resources.
Some example embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
There is also provided, in accordance with another embodiment of the present invention, a computing device including a processor and a memory, the processor and the memory establishing a communication connection, the processor reading a program in the memory to perform the methods illustrated in fig. 1 and 2.
According to another embodiment of the present invention, there is also provided a non-volatile storage medium having a program stored therein, the program being executed by a computing device which performs the methods shown in fig. 1 and 2.
The system/method provided by the present invention may be implemented in any computing device, including a personal computer, workstation, server, Portable Computing Device (PCD), such as a cellular telephone, Portable Digital Assistant (PDA), portable game player, palmtop or tablet computer, and the like.
While the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the use of the technical solution of the present invention is not limited to the applications mentioned in the embodiments of the patent, and various structures and modifications can be easily implemented with reference to the technical solution of the present invention to achieve various advantageous effects mentioned herein. Variations that do not depart from the gist of the invention are intended to be within the scope of the invention as defined by the appended claims.
Claims (10)
1. A method for constructing a talent portrait by using a talent map is characterized by comprising,
receiving material, wherein the material comprises any one or more of a resume, an interview evaluation, a performance review form;
extracting information in the material, and segmenting the information in the material to obtain a plurality of phrases;
according to predefined categories, identifying instance layer named entities from the phrases and classifying;
mapping the example layer named entities to a talent map to obtain a closure with each example layer named entity as a center; and
counting the named entities of the example layer and the concept layer named entities covered in the intersection of at least two closures to obtain a named entity set, extracting the named entity set and the relationship among the named entities in the named entity set to be used as a talent portrait,
in the talent map, a named entity of a certain instance layer is used as a central node, and after reasoning, extension is carried out to obtain an extension node; if more than half of the neighboring nodes in the neighboring nodes of a certain extension node can also be obtained by extension reasoning of other extension nodes except the certain extension node obtained by extension after reasoning of the central node or by extension reasoning of the central node, determining that the certain extension node is in the closure of the central node; all the extension nodes meeting the above conditions, the central node and the relationship thereof form a set, the set is the closure of the central node,
wherein the construction method of the talent map comprises the following steps,
segmenting information in a talent information base to obtain a plurality of phrases, wherein the talent information base comprises a plurality of resumes, interview evaluation and/or performance examination tables;
according to predefined categories, identifying concept layer named entities from the phrases and classifying;
extracting verb-object pairs from the information in the talent information base to obtain verbs corresponding to the named entities of each concept layer; and
and mapping the verbs into the relationship among the concept layer named entities by using a pre-trained model to obtain a talent map which takes the concept layer named entities as nodes and the relationship among the concept layer named entities as edges.
2. The method of claim 1, further comprising the step of constructing a talent representation using a talent atlas,
for the named entities of the example layers which cannot be mapped into the talent map, extracting verb-object pairs from the materials to obtain verbs corresponding to the named entities of the example layers, and mapping the verbs into relations among the named entities of the example layers by utilizing a pre-trained model;
and updating the talent map by using the obtained example layer named entities and the relationship among the example layer named entities.
3. The method of claim 1, wherein the predefined categories include any one or more of schools, specialties, industries, companies, functions, skills, projects, work content and/or certificates.
4. The method of claim 1, wherein the model for identifying concept-level named entities from the phrases is trained using a Bi-LSTM neural network.
5. An image construction device for talents, comprising,
a material receiving unit configured to receive materials, wherein the materials include any one or more of resumes, interview evaluations, and performance review forms;
the information segmentation unit is configured to extract information in the material and segment the information in the material to obtain a plurality of phrases;
the named entity recognition and classification unit is configured to recognize and classify example layer named entities from the phrases according to predefined categories;
the closure identification unit is configured to map the instance layer named entities into a talent map to obtain a closure with each instance layer named entity as a center; and
a talent portrait construction unit configured to count named entities of the instance layer and named entities of the concept layer included in the intersection of at least two of the closures to obtain a named entity set, extract the named entity set and relations among the named entities in the named entity set as a talent portrait,
in the talent map, a named entity of a certain instance layer is used as a central node, and after reasoning, extension is carried out to obtain an extension node; if more than half of the neighboring nodes in the neighboring nodes of a certain extension node can also be obtained by extension reasoning of other extension nodes except the certain extension node obtained by extension after reasoning of the central node or by extension reasoning of the central node, determining that the certain extension node is in the closure of the central node; all the extension nodes meeting the above conditions, the central node and the relationship thereof form a set, the set is the closure of the central node,
wherein the talent map constructing device comprises,
the system comprises an information segmentation unit, a search unit and a search unit, wherein the information segmentation unit is configured to segment information in a talent information base to obtain a plurality of phrases, and the talent information base comprises a plurality of resumes, interview evaluation and/or performance examination tables;
the named entity recognition and classification unit is configured to recognize and classify the named entities at the concept layer from the phrases according to predefined categories;
the verb-object phrase extraction unit is configured to extract verb-object pairs from the information in the talent information base to obtain verbs corresponding to the named entities of each concept layer;
and the relationship mapping unit is configured to map the verbs into relationships among the concept layer named entities by using a pre-trained model to obtain the talent map which takes the concept layer named entities as nodes and the relationships among the concept layer named entities as edges.
6. The human figure constructing apparatus as claimed in claim 5, further comprising,
a verb-object phrase extraction unit configured to extract verb-object pairs from the material for the instance-layer named entities that cannot be mapped to the talent map, to obtain verbs corresponding to the respective instance-layer named entities, and
a relationship mapping unit configured to map the verbs into relationships between instance-level named entities using a pre-trained model; and updating the talent map by using the obtained example layer named entities and the relationship among the example layer named entities.
7. The talent representation construction device according to claim 5, wherein the predefined categories include any one or more of schools, specialties, industries, companies, functions, skills, projects, work content and/or certificates.
8. The human representation construction apparatus of claim 5, wherein the model for identifying the concept-level named entities from the phrases is trained by a Bi-LSTM neural network.
9. The equipment for constructing the talent portrait by using the talent map is characterized by comprising a processor and a memory, wherein the processor is in communication connection with the memory;
the processor for reading a program in the memory to perform the method of any one of claims 1-4.
10. A non-volatile storage medium, in which a program is stored, which program, when executed by a computing device, performs the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811570090.2A CN109726253B (en) | 2018-12-21 | 2018-12-21 | Talent map and talent portrait construction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811570090.2A CN109726253B (en) | 2018-12-21 | 2018-12-21 | Talent map and talent portrait construction method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109726253A CN109726253A (en) | 2019-05-07 |
| CN109726253B true CN109726253B (en) | 2021-03-09 |
Family
ID=66296295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811570090.2A Expired - Fee Related CN109726253B (en) | 2018-12-21 | 2018-12-21 | Talent map and talent portrait construction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726253B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110443571A (en) * | 2019-07-16 | 2019-11-12 | 阿里巴巴集团控股有限公司 | The method, device and equipment of knowledge based map progress resume assessment |
| CN111177283A (en) * | 2019-12-31 | 2020-05-19 | 广东轩辕网络科技股份有限公司 | Intelligent personnel model construction method and device based on reinforcement learning |
| CN111242565A (en) * | 2019-12-31 | 2020-06-05 | 广州轩辕研究院有限公司 | Resume optimization method and device based on intelligent personnel model |
| CN111666377A (en) * | 2020-06-03 | 2020-09-15 | 贵州航天云网科技有限公司 | Talent portrait construction method and system based on big data modeling |
| CN115330363B (en) * | 2022-10-17 | 2023-02-14 | 北京智鼎管理咨询有限公司 | Talent identification method and device, electronic equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468605B (en) * | 2014-08-25 | 2019-04-12 | 济南中林信息科技有限公司 | Entity information map generation method and device |
| CN107967267A (en) * | 2016-10-18 | 2018-04-27 | 中兴通讯股份有限公司 | A kind of knowledge mapping construction method, apparatus and system |
| CN108595708A (en) * | 2018-05-10 | 2018-09-28 | 北京航空航天大学 | A kind of exception information file classification method of knowledge based collection of illustrative plates |
-
2018
- 2018-12-21 CN CN201811570090.2A patent/CN109726253B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN109726253A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726253B (en) | Talent map and talent portrait construction method, device, equipment and medium | |
| Larsen et al. | Validity in design science research | |
| Hill et al. | Identifying shared understanding in design using document analysis | |
| Berio et al. | Towards an integrating architecture for competence management | |
| US10083403B2 (en) | Data driven classification and data quality checking method | |
| CN107886231A (en) | The QoS evaluating method and system of customer service | |
| Jia et al. | Representation of job-skill in artificial intelligence with knowledge graph analysis | |
| CN110489565A (en) | Based on the object root type design method and system in domain knowledge map ontology | |
| Moreno-Jiménez et al. | A new e-learning tool for cognitive democracies in the Knowledge Society | |
| CN116611071A (en) | Function-level vulnerability detection method based on multiple modes | |
| Harris | Making Better Job Hiring Decisions using" Human in the Loop" Techniques. | |
| Edlund et al. | A multimodal digital humanities study of terrorism in Swedish politics: An interdisciplinary mixed methods project on the configuration of terrorism in parliamentary debates, legislation, and policy networks 1968–2018 | |
| Strohmeier | Handbook of research on artificial intelligence in human resource management | |
| CN111651271B (en) | Multi-task learning semantic annotation method and device based on legal data | |
| Chang et al. | Knowledge element extraction for knowledge-based learning resources organization | |
| Dhamecha et al. | Balancing human efforts and performance of student response analyzer in dialog-based tutors | |
| Balta et al. | How to streamline AI application in government? A case study on citizen participation in Germany | |
| Zhang et al. | Construction of higher education teaching quality evaluation model based on scientific computing | |
| CN116401338A (en) | Design feature extraction and attention mechanism based on data asset intelligent retrieval input and output requirements and method thereof | |
| Olaitan et al. | Critical success factors in introducing performance measurement metrics for small and medium-sized enterprises (SMEs) | |
| Maltseva et al. | Social media sentiment analysis with context space model | |
| Doğan et al. | Discovering the same job ads expressed with the different sentences by using hybrid clustering algorithms | |
| Dhanya et al. | Comparative performance of machine learning algorithms in detecting offensive speech in malayalam-english code-mixed data | |
| Bharadi | Sentiment Analysis of Twitter Data Using Named Entity Recognition | |
| Zhou | Multi-task learning in crisis event classification |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210309 Termination date: 20211221 |