CN110569400A - Information extraction method for personnel information modeling based on CNN and LSTM - Google Patents
Information extraction method for personnel information modeling based on CNN and LSTM Download PDFInfo
- Publication number
- CN110569400A CN110569400A CN201910665726.XA CN201910665726A CN110569400A CN 110569400 A CN110569400 A CN 110569400A CN 201910665726 A CN201910665726 A CN 201910665726A CN 110569400 A CN110569400 A CN 110569400A
- Authority
- CN
- China
- Prior art keywords
- information
- personnel information
- neural network
- cnn
- keywords
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
an information extraction method for personnel information modeling based on CNN and LSTM comprises the following steps: s1: acquiring personnel information; s2: constructing an LSTM-CNN neural network system; s3: classifying the personnel information and selecting a plurality of keywords; s4: training a neural network system through the existing stored personnel information and keywords; s5: through training of S4, acquiring correlation between the keywords and the personnel information; s6: querying different keywords for multiple times, so that the system obtains a primary retrieval result; s7: the neural network system reorders the multiple primary retrieval results to obtain a final retrieval result; s8: and the operator extracts and calls the final retrieval result. According to the invention, the personnel information calling speed is improved, and the problem that the traditional personnel information is difficult to call is solved. The neural network system can timely call related information through the correlation between the keywords and the personnel information, and the excellent search performance is shown.
Description
Technical Field
the invention relates to the field of information extraction, in particular to an information extraction method for personnel information modeling based on CNN and LSTM.
Background
At present, the work of each department in each region is basically electronized. The contents of personnel management, personnel organization management, personnel expense management, work and study and the like can be managed through a computer, and personnel informationized construction is realized. Meanwhile, a plurality of organizations establish own websites, and organize government affair work, develop study and help personnel progress through the network.
However, the existing various personnel information management systems are in the stage of using a computer for operation, and personnel information is difficult to call and query due to a large number of people in charge.
Disclosure of Invention
Objects of the invention
In order to solve the technical problems in the background art, the invention provides an information extraction method for personnel information modeling based on CNN and LSTM, which greatly improves the personnel information retrieval speed and solves the problem of difficulty in retrieving the traditional personnel information. The neural network system can timely call related information through the correlation between the keywords and the personnel information, and the excellent search performance is shown.
(II) technical scheme
in order to solve the above problems, the present invention provides an information extraction method for personnel information modeling based on CNN and LSTM, comprising the following steps:
s1: acquiring personnel information;
S2: constructing an LSTM-CNN neural network system;
S3: classifying the personnel information and selecting a plurality of keywords;
s4: training a neural network system through the existing stored personnel information and keywords;
s5: through training of S4, acquiring correlation between the keywords and the personnel information;
S6: querying different keywords for multiple times, so that the system obtains a primary retrieval result;
s7: the neural network system reorders the multiple primary retrieval results to obtain a final retrieval result;
S8: and the operator extracts and calls the final retrieval result.
preferably, the personnel information comprises name, identity card information, household registration, working time, working age, job title and working location.
Preferably, in S4, name, identification card and personnel information are constructed into a triplet, which is input to the neural network system as an output matrix; wherein, the name and the ID card information are used as key words at the same time.
Preferably, the keyword includes an entry contained in the personal information.
preferably, a recording system is included; after the calling information is operated, the system records the called data, the time of data calling and checking and the detailed calling record of the caller.
Preferably, according to the calling record, carrying out quantity statistics on the used keywords and the inquired personnel information; and carrying out priority calling on the keywords with large statistical quantity and the corresponding personnel information.
Preferably, the neural network system is a circular neural network and a convolutional neural network connected in series.
Preferably, the recurrent neural network is used for processing the time sequence characteristics of the personnel information; the convolutional neural network is used for processing the position characteristics of the personnel information.
The technical scheme of the invention has the following beneficial technical effects:
in the invention, the personnel information is processed by constructing the LSTM-CNN neural network system, so that the personnel information calling speed is greatly improved, and the problem of difficulty in calling the traditional personnel information is solved. The neural network system can timely call related information through the correlation between the keywords and the personnel information, and the excellent search performance is shown.
in the invention, the LSTM algorithm and the CNN algorithm are combined for use to construct an LSTM-CNN neural network system. The LSTM algorithm can inquire the characteristics of the keywords in time sequence, the state characteristics of the keywords are calculated through a gate function, and the CNN algorithm can effectively capture the position characteristic information of the personnel information, so that the searching and inquiring speed is increased, and the process of quickly calling personnel information is realized.
Drawings
FIG. 1 is a flow chart of an information extraction method based on CNN and LSTM modeling for human information according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1, the information extraction method for personnel information modeling based on CNN and LSTM proposed by the present invention includes the following steps:
s1: acquiring personnel information;
S2: constructing an LSTM-CNN neural network system;
S3: classifying the personnel information and selecting a plurality of keywords;
S4: training a neural network system through the existing stored personnel information and keywords;
S5: through training of S4, acquiring correlation between the keywords and the personnel information;
s6: querying different keywords for multiple times, so that the system obtains a primary retrieval result;
S7: the neural network system reorders the multiple primary retrieval results to obtain a final retrieval result;
s8: and the operator extracts and calls the final retrieval result.
in the invention, the personnel information is processed by constructing the LSTM-CNN neural network system, so that the personnel information calling speed is greatly improved, and the problem of difficulty in calling the traditional personnel information is solved. The neural network system can timely call related information through the correlation between the keywords and the personnel information, and the excellent search performance is shown;
in the invention, the LSTM algorithm and the CNN algorithm are combined for use to construct an LSTM-CNN neural network system. The LSTM algorithm can inquire the characteristics of the keywords in time sequence, the state characteristics of the keywords are calculated through a gate function, and the CNN algorithm can effectively capture the position characteristic information of the personnel information, so that the searching and inquiring speed is increased, and the process of quickly calling personnel information is realized.
in an optional embodiment, the personnel information includes names, identification card information, household registration, working time, working age, job title, and working location, and the personnel information can be comprehensively extracted, the basic situation of the personnel can be comprehensively known, and the emergency can be conveniently solved.
in an alternative embodiment, in S4, the name, the identification card, and the person information are constructed into a triplet, which is input to the neural network system as an output matrix; wherein, the name and the ID card information are simultaneously used as key words; the triple improves the algorithm speed of the system, optimizes the algorithm process and realizes the high-efficiency operation of the system; the name and the identity card information are simultaneously used as key words, so that the information can be conveniently and quickly searched.
in an alternative embodiment, the keywords include entries contained in the personal information, such as: the name, the identity card information, the household registration, the working time, the working age, the job title, the working location and the like can be used as key words, so that the search range of the system is expanded, and the service performance of the system is improved.
in an alternative embodiment, a recording system is included; after the calling information is operated, recording the calling data, the time for calling and checking the data and the detailed calling record of the caller
in an optional embodiment, according to the call record, carrying out quantity statistics on the used keywords and the queried personnel information; and carrying out priority calling on the keywords with large statistical quantity and the corresponding personnel information.
It should be noted that the recording system is used for recording the calling information process, and when a problem occurs in calling, the record can be called through the record searching place, so that the safety of the system is improved. Meanwhile, the keywords with large statistical quantity and the corresponding personnel information are preferentially called, so that the sequencing of the commonly used calling information is improved, and the more rapid calling of the commonly used information is facilitated.
in an alternative embodiment, the neural network system is a circular neural network and a convolutional neural network connected in series
In an alternative embodiment, the recurrent neural network is used to process time series characteristics of the person information; the convolutional neural network is used for processing the position characteristics of the personnel information.
It should be noted that, in the LSTM-CNN neural network system, the LSTM algorithm and the CNN algorithm are used in combination to construct the LSTM-CNN neural network system. The LSTM algorithm can inquire the characteristics of the keywords in time sequence, the state characteristics of the keywords are calculated through a gate function, and the CNN algorithm can effectively capture the position characteristic information of the personnel information, so that the searching and inquiring speed is increased, and the process of quickly calling personnel information is realized.
it is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (8)
1. An information extraction method for personnel information modeling based on CNN and LSTM is characterized by comprising the following steps:
S1: acquiring personnel information;
S2: constructing an LSTM-CNN neural network system;
S3: classifying the personnel information and selecting a plurality of keywords;
S4: training a neural network system through the existing stored personnel information and keywords;
S5: through training of S4, acquiring correlation between the keywords and the personnel information;
S6: querying different keywords for multiple times, so that the system obtains a primary retrieval result;
S7: the neural network system reorders the multiple primary retrieval results to obtain a final retrieval result;
S8: and the operator extracts and calls the final retrieval result.
2. The information extraction method of personnel information based on CNN and LSTM modeling according to claim 1, wherein personnel information includes name, ID card information, household registration, working hours, working age, job title, and working location.
3. The information extraction method based on CNN and LSTM modeling of personnel information as claimed in claim 1, wherein in S4, name, ID card and personnel information are constructed into triples, and input into neural network system as output matrix; wherein, the name and the ID card information are used as key words at the same time.
4. The information extraction method based on CNN and LSTM modeling of personnel information as claimed in claim 1, wherein the keywords are terms included in the personnel information.
5. The information extraction method based on CNN and LSTM modeling of personnel information according to claim 1, characterized by comprising a recording system; after the calling information is operated, the system records the called data, the time of data calling and checking and the detailed calling record of the caller.
6. The information extraction method based on CNN and LSTM modeling of personnel information as claimed in claim 5, wherein the used keywords and the queried personnel information are counted according to the call records; and carrying out priority calling on the keywords with large statistical quantity and the corresponding personnel information.
7. The information extraction method based on CNN and LSTM modeling of human information as claimed in claim 1, wherein the neural network system is a serial cyclic neural network and convolutional neural network.
8. the information extraction method based on CNN and LSTM modeling of personnel information as claimed in claim 7, wherein the recurrent neural network is used to process the time series characteristics of personnel information; the convolutional neural network is used for processing the position characteristics of the personnel information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665726.XA CN110569400A (en) | 2019-07-23 | 2019-07-23 | Information extraction method for personnel information modeling based on CNN and LSTM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910665726.XA CN110569400A (en) | 2019-07-23 | 2019-07-23 | Information extraction method for personnel information modeling based on CNN and LSTM |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110569400A true CN110569400A (en) | 2019-12-13 |
Family
ID=68773264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910665726.XA Pending CN110569400A (en) | 2019-07-23 | 2019-07-23 | Information extraction method for personnel information modeling based on CNN and LSTM |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110569400A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202044A (en) * | 2016-07-07 | 2016-12-07 | 武汉理工大学 | A kind of entity relation extraction method based on deep neural network |
| CN107832289A (en) * | 2017-10-12 | 2018-03-23 | 北京知道未来信息技术有限公司 | A kind of name entity recognition method based on LSTM CNN |
| CN107977353A (en) * | 2017-10-12 | 2018-05-01 | 北京知道未来信息技术有限公司 | A kind of mixing language material name entity recognition method based on LSTM-CNN |
| CN108304478A (en) * | 2017-12-28 | 2018-07-20 | 深圳市轱辘车联数据技术有限公司 | A kind of data processing method and server |
| CN109840279A (en) * | 2019-01-10 | 2019-06-04 | 山东亿云信息技术有限公司 | File classification method based on convolution loop neural network |
-
2019
- 2019-07-23 CN CN201910665726.XA patent/CN110569400A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202044A (en) * | 2016-07-07 | 2016-12-07 | 武汉理工大学 | A kind of entity relation extraction method based on deep neural network |
| CN107832289A (en) * | 2017-10-12 | 2018-03-23 | 北京知道未来信息技术有限公司 | A kind of name entity recognition method based on LSTM CNN |
| CN107977353A (en) * | 2017-10-12 | 2018-05-01 | 北京知道未来信息技术有限公司 | A kind of mixing language material name entity recognition method based on LSTM-CNN |
| CN108304478A (en) * | 2017-12-28 | 2018-07-20 | 深圳市轱辘车联数据技术有限公司 | A kind of data processing method and server |
| CN109840279A (en) * | 2019-01-10 | 2019-06-04 | 山东亿云信息技术有限公司 | File classification method based on convolution loop neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210042533A1 (en) | Inmate tracking system in a controlled environment | |
| CN109635146B (en) | Target query method and system based on image characteristics | |
| CN108509424B (en) | System information processing method, apparatus, computer device and storage medium | |
| US11258895B2 (en) | Automated speech-to-text processing and analysis of call data apparatuses, methods and systems | |
| CN105244031A (en) | Speaker identification method and device | |
| EP2674884A1 (en) | Method, system and computer-readable recording medium for adding a new image and information on the new image to an image database | |
| CN103235825A (en) | Method used for designing large-quantity face recognition search engine and based on Hadoop cloud computing frame | |
| US20100174712A1 (en) | Expertise ranking using social distance | |
| CN109299040B (en) | A kind of file storage smart allocation method based on big data | |
| CN106326438A (en) | Personnel information correlating method | |
| CN103699679A (en) | Method and equipment for retrieving information of target objects | |
| CN110543477B (en) | Label construction system and method | |
| CN110727756A (en) | Management method and device of space-time trajectory data | |
| CN110543584A (en) | method, device, processing server and storage medium for establishing face index | |
| CN111427972B (en) | Method, device, service searching system and storage medium for searching service data | |
| CN110569400A (en) | Information extraction method for personnel information modeling based on CNN and LSTM | |
| CN107590233A (en) | A kind of file management method and device | |
| CN111666263A (en) | Method for realizing heterogeneous data management in data lake environment | |
| CN107784588A (en) | Insurance user information merging method and device | |
| CN110019237B (en) | System and method for analyzing criminal whereabouts based on map | |
| CN115630057A (en) | Method for realizing automatic integration of multi-source heterogeneous data | |
| CN115295164A (en) | Medical insurance data processing method and device, electronic equipment and storage medium | |
| CN114117174A (en) | Multi-format data screening management system based on big data | |
| CN106777233A (en) | The personalized search system of the support secret protection based on cloud computing | |
| CN104951869A (en) | Workflow-based public opinion monitoring method and workflow-based public opinion monitoring device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191213 |