CN110209993A - A kind of information extraction method and system detecting target - Google Patents
A kind of information extraction method and system detecting target Download PDFInfo
- Publication number
- CN110209993A CN110209993A CN201910520375.3A CN201910520375A CN110209993A CN 110209993 A CN110209993 A CN 110209993A CN 201910520375 A CN201910520375 A CN 201910520375A CN 110209993 A CN110209993 A CN 110209993A
- Authority
- CN
- China
- Prior art keywords
- information
- target
- aiming field
- indicate
- descriptive model
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/15—Correlation function computation including computation of convolution operations
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of information extraction method and system for detecting target, which comprises determining that detection target target information and aiming field to be extracted；The descriptive model of the target information is established, the descriptive model is that the relational expression of the detection target is described using the target information in the aiming field；According to the descriptive model, the objective function and constraint condition of information extraction are established；According to the objective function and the constraint condition, the target information is extracted in the aiming field.A kind of information extraction method detecting target provided by the present application, the information of complete, irredundant detection target can be extracted from multiple dimensions, so as to realize under conditions of the information of extraction has non-correlation constraint, the information of the optimization detection target reconstructed, and then guidance can be provided for the design of subsequent detection mission and detection system.
Description
Technical field
The present invention relates to target acquisition technical field more particularly to a kind of information extraction methods and system for detecting target.
Background technique
In target acquisition technology, detection target usually has various dimensions information, for example, the various dimensions information of target can be with
It include: position, speed, size and shape etc..Detection system can detect the discrete message of the information of target by extracting, according to
The discrete message of the information of extraction, the information of reconstruct detection target, is realized to detection target detection, positioning, tracking and identification etc..
When extracting to the information of detection target, detection target single dimension information is only extracted, is not enough to be formed preferable
Detectivity, so the various dimensions information to detection target is needed to extract, still, in practical extraction process, the dimension of extraction
Spend will cause information redundancy more, the excessively few information for being then not enough to accurately reconstruct detection target of the dimension of extraction.Also, mesh
Before, the information extraction method only for the information of time domain, and for the information extraction in other domains such as airspace, lack rationally effectively
Information extraction method.So how accurately to detection target various dimensions information carry out extract be those skilled in the art urgently
Problem to be solved.
Summary of the invention
The present invention provides a kind of information extraction methods and system for detecting target, how to solve accurately to detection target
Various dimensions information the problem of being extracted.
In a first aspect, the information extraction method includes: true the present invention provides a kind of information extraction method for detecting target
Surely detection target target information and aiming field to be extracted；The descriptive model of the target information is established, the descriptive model is
In the aiming field, the relational expression of the detection target is described using the target information；According to the descriptive model, establish
The objective function and constraint condition of information extraction；It is right in the aiming field according to the objective function and the constraint condition
The target information is extracted.
Further, the process for establishing the descriptive model of the target information, specifically includes: using following relational expressions, establishes
The descriptive model of the target information；
Wherein, χ indicates the target information,Indicate the aiming field.
Further, according to the descriptive model, the objective function of information extraction and the process of constraint condition are established, it is specific to wrap
It includes: using following relational expressions, establish the objective function；
Wherein, Z={ Z1,Z2,Z3L } indicate the letter obtained after extracting in the aiming field to the target information
Breath, Z1,Z2,Z3L is the discrete message for the target information for including in set Z；Indicate reconfiguration information, i.e., according to Z
The information of the detection target of reconstruct；Indicate the descriptive model；Indicate described heavy
Structure informationWith the descriptive modelBetween mutual information；
Using following relational expressions, the constraint condition is established；
I(Zi,Zj) < D0, i, j=1,2,3, K i ≠ j；
Wherein, ZiAnd ZjIndicate the discrete message for the target information for including in the set Z；I(Zi,Zj) indicate
Discrete message ZiWith discrete message ZjBetween mutual information；D0Indicate discrete message ZiWith discrete message ZjBetween mutual information threshold
Value.
Further, according to the objective function and the constraint condition, in the aiming field to the target information into
The process that row extracts, specifically includes: solving the optimization problem being made of the objective function and the constraint condition, obtains in institute
State the information after extracting in aiming field to the target information.
Further, information extraction method further include: the target information is extracted according in the aiming field
The information of target is detected described in the signal reconstruct obtained afterwards.
Second aspect, the present invention provides a kind of information extraction systems for detecting target, which includes: true
Cover half block, for determining detection target target information and aiming field to be extracted；First establishes module, for establishing the target
The descriptive model of information, the descriptive model are to describe the detection target using the target information in the aiming field
Relational expression；Second establishes module, for establishing the objective function and constraint condition of information extraction according to the descriptive model；
Information extraction module is used for according to the objective function and the constraint condition, to the target information in the aiming field
It is extracted.
Further, it described first establishes module and is specifically used for: using following relational expressions, establish the description of the target information
Model；
Wherein, χ indicates the target information,Indicate the aiming field.
Further, it described second establishes module and is specifically used for: using following relational expressions, establish the objective function；
Wherein, Z={ Z1,Z2,Z3L } indicate the letter obtained after extracting in the aiming field to the target information
Breath, Z1,Z2,Z3L is the discrete message for the target information for including in set Z；Indicate reconfiguration information, i.e., according to Z
The information of the detection target of reconstruct；Indicate the descriptive model；Indicate described heavy
Structure informationWith the descriptive modelBetween mutual information；
Using following relational expressions, the constraint condition is established；
I(Zi,Zj) < D0, i, j=1,2,3, K i ≠ j；
Wherein, ZiAnd ZjIndicate the discrete message for the target information for including in the set Z；I(Zi,Zj) indicate
Discrete message ZiWith discrete message ZjBetween mutual information；D0Indicate discrete message ZiWith discrete message ZjBetween mutual information threshold
Value.
Further, the information extraction module is specifically used for: solution is made of the objective function and the constraint condition
Optimization problem, obtain the information after extracting in the aiming field to the target information.
Further, the information extraction system further include: signal reconstruct module, for basis to described in the aiming field
The information of target is detected described in the signal reconstruct that target information obtains after being extracted.
The technical solution that the embodiment of the present invention provides can include the following benefits: the present invention provides a kind of detections
The information extraction method and system of target.In the information extraction method, it is according to the detection mission of detection target and detection first
The composition of system determines the target information and aiming field of the detection pending extraction of target, then establishes in the aiming field, uses
The descriptive model of target information description detection target, later, according to descriptive model, establish information extraction objective function and
Constraint condition；Finally, the optimization problem being made of the objective function of information extraction and constraint condition is solved, in the aiming field
The target information is extracted, the discrete message of target information is obtained, to realize to detection target in the target
The information extraction of multiple dimensions in domain.It follows that a kind of information extraction method for detecting target provided by the present application, it can be with
The information of complete, irredundant detection target is extracted, from multiple dimensions so as to realize that the information in extraction has non-phase
Under conditions of the constraint of closing property, the information of the optimization detection target reconstructed, and then can be subsequent detection mission and spy
The design of examining system provides guidance.
Detailed description of the invention
In order to illustrate more clearly of technical solution of the present invention, letter will be made to attached drawing needed in the embodiment below
Singly introduce, it should be apparent that, for those of ordinary skills, without any creative labor,
It is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of information extraction method for detecting target provided in an embodiment of the present invention；
Fig. 2 is a kind of structural block diagram of information extraction system for detecting target provided in an embodiment of the present invention.
Specific embodiment
In conjunction with background technique it is found that in the prior art, be only directed to the abstracting method of time-domain information, for airspace etc. other
The information extraction in domain lacks reasonable effective information extraction method, so, at present for the not same area of being suitable for of detection target
Multidimensional information extracts, without more unified suitable solution.In order to solve this problem, the embodiment of the invention provides
A kind of information extraction method and system detecting target.A kind of information extraction method detecting target provided by the present application, can be with
The information of complete, irredundant detection target is extracted from multiple dimensions, and may be implemented that there is non-phase in the information of extraction
Under conditions of the constraint of closing property, the information of the optimization detection target reconstructed, and then can be subsequent detection mission and spy
The design of examining system provides guidance.
With reference to the accompanying drawing, a kind of information extraction method for detecting target provided in an embodiment of the present invention is discussed in detail and is
System.
Referring to Fig. 1, Fig. 1 is a kind of process signal of information extraction method for detecting target provided in an embodiment of the present invention
Figure.In conjunction with Fig. 1 it is found that the information extraction method includes:
Step 101 determines detection target target information and aiming field to be extracted.
When it is implemented, can determine detection target target information to be extracted according to the detection mission of detection target.Example
Such as, if detection mission is detection detection target, corresponding target information is the energy for detecting target, utilizes different moments
Energy judgement detection target whether there is；If detection mission is tracking detection target, corresponding target information is detection mesh
Target position vector tracks detection target using the position vector of different moments；If detection mission is to detection mesh
Target positioning or identification etc., then corresponding target information is the information of detection target needed for the detection missions such as positioning or identification,
It will not enumerate herein.
Furthermore, it is possible to according to detection target the corresponding detection system of detection mission composition, determine detection target wait for into
The aiming field that row information extracts.For example, if detection system is single dress system, it usually needs extract and detect from time domain (time-domain)
The information of target, then corresponding aiming field is time domain；If detection system is made of multiple nodes that wide area is distributed, it usually needs
The information of detection target is extracted from airspace (spatial domain), then corresponding aiming field is airspace；If electromagnetism needed for detection system
Signal is made of multiple frequencies, it usually needs the information of detection target is extracted from frequency domain (frequency domain), then corresponding aiming field is
Frequency domain；In addition, if detection system needs to extract the information of detection target from time domain and airspace joint, then corresponding aiming field is
Time domain-airspace composition joint domain；And so on, if detection system is other types of system, can be according to detection
The demand of system determines aiming field, and details are not described herein again.
Step 102 establishes the descriptive model for detecting the target information of target.
Wherein, the descriptive model is to describe the detection target using the target information in the aiming field
Relational expression.
When it is implemented, following relational expressions (1) can be used, the descriptive model of the target information is established:
In relational expression (1), χ indicates the target information,Indicate the aiming field.Relational expression (1) is descriptive model
General expression can be according to corresponding target information for the current detection mission of any one specific detection target
And aiming field, it establishes in the aiming field, the relational expression of detection target is described using the target information, using the relational expression as this
Detect the descriptive model of the corresponding target information of current detection mission of target.
Step 103, according to the descriptive model, establish the objective function and constraint condition of information extraction.
When it is implemented, following relational expressions (2) can be used, the objective function of information extraction is established:
In relational expression (2), Z={ Z1,Z2,Z3L } it indicates to obtain after extracting the target information in the aiming field
The information arrived, Z1,Z2,Z3L is the discrete message for the target information for including in set Z, that is to say, that uses the application
The information extraction method of offer, finally extracting information of the obtained detection target in the aiming field is by multiple discrete messages
Z1,Z2,Z3The set Z that L is constituted, if aiming field is time domain, Z is the information that different moments sampling obtains, if aiming field is
Airspace, then Z indicates the information that the different perspectives down-sampling in airspace obtains, if aiming field is frequency domain, Z is indicated using different
The information that frequency sampling obtains, and so on, if aiming field is other domains, Z indicates to extract target information in other domains
The information obtained afterwards, will not enumerate herein；It indicates to be attached most importance to according to the information of the Z detection target reconstructed, definition
Structure information；Indicate the descriptive model；Indicate the reconfiguration informationWith it is described
Descriptive modelBetween mutual information, the numerical value of the mutual information is bigger, indicateIn containLetter
Breath is more, available to arrive by the maximization of the mutual information numerical valueCorresponding best reconfiguration information
It should be noted that relational expression (2) is similarly the general expression of the objective function of information extraction, it can be according to tool
Relational expression (2) is set corresponding concrete form by the detection target and detection mission of body and the composition of detection system.
According to the theory of information theory it is found that the mutual information between two variables is smaller, show the phase between the two variables
Guan Xingyue is few, is based on this, following relational expressions (3) can be used, establish the constraint condition of information extraction:
I(Zi,Zj) < D0, i, j=1,2,3, K i ≠ j (3)
In relational expression (3), ZiAnd ZjIndicate the discrete message for the target information for including in the set Z；I(Zi,
Zj) indicate discrete message ZiWith discrete message ZjBetween mutual information；D0Indicate discrete message ZiWith discrete message ZjBetween it is mutual
The threshold value of information.
Explanation is also needed, relational expression (3) is the general expression of the constraint condition of information extraction, can be according to tool
Relational expression (3) are carried out corresponding specific setting by the detection target and detection mission of body and the composition of detection system.
Step 104, according to the objective function and the constraint condition, in the aiming field to the target information into
Row extracts.
It establishes after objective function and the constraint condition of information extraction, solves by the objective function and the constraint condition
The optimization problem of composition can obtain the information after extracting in the aiming field to the target information.
Specifically, optimization algorithm can be used, such as particle filter algorithm or genetic algorithm etc., solve by the target letter
The optimization problem that the several and constraint condition is constituted, the result of optimization algorithm output are in the aiming field to the target
The information that information obtains after being extracted.
Further, in some alternative embodiments, which can also include: according in the aiming field
In the target information is extracted after the information of target is detected described in obtained signal reconstruct.According in the aiming field
After the information for detecting target described in the signal reconstruct obtained after extracting to the target information, the information in extraction is realized
Between there is non-correlation constraint in the case where, information of the optimal reconfiguration detection target in the aiming field, thus
The information of irredundant optimization detection target is obtained.
It is provided by the present application it is a kind of detect target information extraction method in, first according to detection target detection mission and
The composition of detection system determines the target information and aiming field of the detection pending extraction of target, then establishes in the aiming field
In, according to descriptive model, the mesh of information extraction is established later using the descriptive model that the target information describes detection target
Scalar functions and constraint condition；Finally, the optimization problem being made of the objective function of information extraction and constraint condition is solved, described
The target information is extracted in aiming field, to realize multiple dimensions to detection target in the aiming field
Information extraction.It follows that a kind of information extraction method for detecting target provided by the present application, can extract from multiple dimensions
The information of complete, irredundant detection target, so as to realize under conditions of the information of extraction has non-correlation constraint,
The information of the optimization detection target reconstructed, and then finger can be provided for the design of subsequent detection mission and detection system
It leads.
Corresponding with a kind of above-mentioned detection information extraction method of target, the embodiment of the invention also discloses a kind of detection mesh
Target information extraction system.
Referring to fig. 2, Fig. 2 is a kind of structural block diagram of information extraction system for detecting target provided in an embodiment of the present invention.
In conjunction with Fig. 2 it is found that the information extraction system 200 includes:
Determining module 201, for determining detection target target information and aiming field to be extracted；First establishes module 202,
For establishing the descriptive model of the target information, the descriptive model is to use the target information in the aiming field
The relational expression of the detection target is described；Second establishes module 203, for establishing information extraction according to the descriptive model
Objective function and constraint condition；Information extraction module 204 is used for according to the objective function and the constraint condition, described
The target information is extracted in aiming field.
Further, it described first establishes module 202 and is specifically used for: using following relational expressions, establish the target information
Descriptive model；
Wherein, χ indicates the target information,Indicate the aiming field.
Further, it described second establishes module 203 and is specifically used for: using following relational expressions, establish the objective function；
Wherein, Z={ Z1,Z2,Z3L } indicate the letter obtained after extracting in the aiming field to the target information
Breath, Z1,Z2,Z3L is the discrete message for the target information for including in set Z；Indicate reconfiguration information, i.e., according to Z
The information of the detection target of reconstruct；Indicate the descriptive model；Indicate described heavy
Structure informationWith the descriptive modelBetween mutual information；
Using following relational expressions, the constraint condition is established；
I(Zi,Zj) < D0, i, j=1,2,3, K i ≠ j；
Wherein, ZiAnd ZjIndicate the discrete message for the target information for including in the set Z；I(Zi,Zj) indicate
Discrete message ZiWith discrete message ZjBetween mutual information；D0Indicate discrete message ZiWith discrete message ZjBetween mutual information threshold
Value.
Further, the information extraction module 204 is specifically used for: solving by the objective function and the constraint condition structure
At optimization problem, obtain the information after extracting in the aiming field to the target information.
Further, which can also include: signal reconstruct module, for according in the aiming field
In the target information is extracted after the information of target is detected described in obtained signal reconstruct.
Using a kind of information extraction system for detecting target provided in an embodiment of the present invention, it is possible to implement a kind of above-mentioned detection
Each step in the information extraction method of target, and obtain identical beneficial effect.A kind of detection provided in an embodiment of the present invention
The information extraction system of target determines that detection target waits for first according to the composition of the detection mission of detection target and detection system
The target information and aiming field extracted, is then established in the aiming field, describes detection mesh using the target information
Target descriptive model according to descriptive model, establishes the objective function and constraint condition of information extraction later；Finally, solving by believing
The optimization problem for ceasing the objective function extracted and constraint condition composition, takes out the target information in the aiming field
It takes, to realize the information extraction of multiple dimensions to detection target.It follows that a kind of detection target provided by the present application
Information extraction system, the information of complete, irredundant detection target can be extracted, from multiple dimensions so as to realize
Under conditions of the information of extraction has non-correlation constraint, the information of the optimization detection target reconstructed, and then can be
The design of subsequent detection mission and detection system provides guidance, and applicability is more preferable.
In the specific implementation, the application also provides a kind of computer storage medium, wherein the computer storage medium can store
There is program, described program includes instruction, which may include a kind of information extraction for detecting target provided by the present application when executing
Step some or all of in each embodiment of method.The storage medium can be magnetic disk, CD, read-only memory
(read-only memory, ROM) or random access memory (random access memory, RAM) etc..
It is required that those skilled in the art can be understood that the technology in the embodiment of the present application can add by software
The mode of general hardware platform realize.Based on this understanding, the technical solution in the embodiment of the present application substantially or
Say that the part that contributes to existing technology can be embodied in the form of software products, which can deposit
Storage is in storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used so that computer equipment (can be with
It is personal computer, server or wireless telecom equipment etc.) execute certain portions of each embodiment of the application or embodiment
Method described in point.
Same and similar part may refer to each other between each embodiment in this specification.Especially for a kind of detection
For the embodiment of the information extraction system of target, since it is substantially similar to the method embodiment, so be described relatively simple,
Related place is referring to the explanation in embodiment of the method.
In addition, unless otherwise indicated, " multiple " refer to two or more in the description of the present application.In addition, in order to
Convenient for clearly describing the technical solution of the embodiment of the present application, in embodiments herein, the words such as " first ", " second " are used
Sample distinguishes function and the essentially identical identical entry of effect or similar item.It will be appreciated by those skilled in the art that " first ",
Printed words such as " second " are not defined quantity and execution order, and the printed words such as " first ", " second " also do not limit one
Fixed difference.
Above-described the application embodiment does not constitute the restriction to the application protection scope.
Claims (10)
1. a kind of information extraction method for detecting target characterized by comprising
Determine detection target target information and aiming field to be extracted；
The descriptive model of the target information is established, the descriptive model is to use the target information in the aiming field
The relational expression of the detection target is described；
According to the descriptive model, the objective function and constraint condition of information extraction are established；
According to the objective function and the constraint condition, the target information is extracted in the aiming field.
2. information extraction method according to claim 1, which is characterized in that establish the descriptive model of the target information
Process specifically includes:
Using following relational expressions, the descriptive model of the target information is established；
Wherein, χ indicates the target information,Indicate the aiming field.
3. information extraction method according to claim 2, which is characterized in that according to the descriptive model, establish information pumping
The process of the objective function and constraint condition that take, specifically includes:
Using following relational expressions, the objective function is established；
Wherein, Z={ Z1,Z2,Z3L } indicate the information obtained after extracting in the aiming field to the target information, Z1,
Z2,Z3L is the discrete message for the target information for including in set Z；Indicate reconfiguration information, i.e., according to Z reconstruct
The information of the detection target；Indicate the descriptive model；Indicate the reconfiguration informationWith the descriptive modelBetween mutual information；
Using following relational expressions, the constraint condition is established；
I(Zi,Zj) < D0, i, j=1,2,3, K i ≠ j；
Wherein, ZiAnd ZjIndicate the discrete message for the target information for including in the set Z；I(Zi,Zj) indicate discrete letter
Cease ZiWith discrete message ZjBetween mutual information；D0Indicate discrete message ZiWith discrete message ZjBetween mutual information threshold value.
4. information extraction method according to claim 1, which is characterized in that according to the objective function and the constraint item
Part, the process extracted in the aiming field to the target information, specifically includes:
The optimization problem being made of the objective function and the constraint condition is solved, is obtained in the aiming field to the mesh
Mark the information after information is extracted.
5. information extraction method according to claim 1, which is characterized in that the information extraction method further include: according to
The information of target is detected described in the signal reconstruct obtained after extracting in the aiming field to the target information.
6. a kind of information extraction system for detecting target characterized by comprising
Determining module, for determining detection target target information and aiming field to be extracted；
First establishes module, for establishing the descriptive model of the target information, the descriptive model be in the aiming field,
The relational expression of the detection target is described using the target information；
Second establishes module, for establishing the objective function and constraint condition of information extraction according to the descriptive model；
Information extraction module is used for according to the objective function and the constraint condition, to the target in the aiming field
Information is extracted.
7. information extraction system according to claim 6, which is characterized in that described first, which establishes module, is specifically used for:
Using following relational expressions, the descriptive model of the target information is established；
Wherein, χ indicates the target information,Indicate the aiming field.
8. information extraction system according to claim 7, which is characterized in that described second, which establishes module, is specifically used for:
Using following relational expressions, the objective function is established；
Wherein, Z={ Z1,Z2,Z3L } indicate the information obtained after extracting in the aiming field to the target information, Z1,
Z2,Z3L is the discrete message for the target information for including in set Z；Indicate reconfiguration information, i.e., according to Z reconstruct
The information of the detection target；Indicate the descriptive model；Indicate the reconfiguration informationWith the descriptive modelBetween mutual information；
Using following relational expressions, the constraint condition is established；
I(Zi,Zj) < D0, i, j=1,2,3, K i ≠ j；
Wherein, ZiAnd ZjIndicate the discrete message for the target information for including in the set Z；I(Zi,Zj) indicate discrete letter
Cease ZiWith discrete message ZjBetween mutual information；D0Indicate discrete message ZiWith discrete message ZjBetween mutual information threshold value.
9. information extraction system according to claim 6, which is characterized in that the information extraction module is specifically used for:
The optimization problem being made of the objective function and the constraint condition is solved, is obtained in the aiming field to the mesh
Mark the information after information is extracted.
10. information extraction system according to claim 6, which is characterized in that the information extraction system further include: information weight
Structure module, for detecting mesh according to the signal reconstruct obtained after extracting in the aiming field to the target information
Target information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520375.3A CN110209993B (en) | 2019-06-17 | 2019-06-17 | Information extraction method and system for detection target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910520375.3A CN110209993B (en) | 2019-06-17 | 2019-06-17 | Information extraction method and system for detection target |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110209993A true CN110209993A (en) | 2019-09-06 |
| CN110209993B CN110209993B (en) | 2023-05-05 |
Family
ID=67792885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910520375.3A Active CN110209993B (en) | 2019-06-17 | 2019-06-17 | Information extraction method and system for detection target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110209993B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819622A (en) * | 2021-01-26 | 2021-05-18 | 深圳价值在线信息科技股份有限公司 | Information entity relationship joint extraction method and device and terminal equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751385A (en) * | 2008-12-19 | 2010-06-23 | 华建机器翻译有限公司 | Multilingual information extraction method adopting hierarchical pipeline filter system structure |
| CN105137498A (en) * | 2015-09-17 | 2015-12-09 | 鲁东大学 | Underground target detection and recognition system and method based on feature fusion |
| CN105550636A (en) * | 2015-12-04 | 2016-05-04 | 中国电子科技集团公司第三研究所 | Method and device for identifying target types |
| CN107728124A (en) * | 2017-09-08 | 2018-02-23 | 中国电子科技集团公司信息科学研究院 | A kind of more radar dynamic regulating methods and device based on comentropy |
| US20180248592A1 (en) * | 2016-07-21 | 2018-08-30 | Nxgen Partners Ip, Llc | System and method for reducing pilot signal contamination using orthogonal pilot signals |
| CN108764141A (en) * | 2018-05-25 | 2018-11-06 | 广州虎牙信息科技有限公司 | A kind of scene of game describes method, apparatus, equipment and its storage medium |
| CN109118064A (en) * | 2018-07-25 | 2019-01-01 | 中国电子科技集团公司第二十八研究所 | A kind of optimal resource allocation method for detection mission planning |
| CN109307862A (en) * | 2018-07-05 | 2019-02-05 | 西安电子科技大学 | A kind of target radiation source individual discrimination method |
-
2019
- 2019-06-17 CN CN201910520375.3A patent/CN110209993B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751385A (en) * | 2008-12-19 | 2010-06-23 | 华建机器翻译有限公司 | Multilingual information extraction method adopting hierarchical pipeline filter system structure |
| CN105137498A (en) * | 2015-09-17 | 2015-12-09 | 鲁东大学 | Underground target detection and recognition system and method based on feature fusion |
| CN105550636A (en) * | 2015-12-04 | 2016-05-04 | 中国电子科技集团公司第三研究所 | Method and device for identifying target types |
| US20180248592A1 (en) * | 2016-07-21 | 2018-08-30 | Nxgen Partners Ip, Llc | System and method for reducing pilot signal contamination using orthogonal pilot signals |
| CN107728124A (en) * | 2017-09-08 | 2018-02-23 | 中国电子科技集团公司信息科学研究院 | A kind of more radar dynamic regulating methods and device based on comentropy |
| CN108764141A (en) * | 2018-05-25 | 2018-11-06 | 广州虎牙信息科技有限公司 | A kind of scene of game describes method, apparatus, equipment and its storage medium |
| CN109307862A (en) * | 2018-07-05 | 2019-02-05 | 西安电子科技大学 | A kind of target radiation source individual discrimination method |
| CN109118064A (en) * | 2018-07-25 | 2019-01-01 | 中国电子科技集团公司第二十八研究所 | A kind of optimal resource allocation method for detection mission planning |
Non-Patent Citations (3)
| Title |
|---|
| 张春菊: "中文文本中事件时空与属性信息解析方法研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
| 杨文芳: "基于信息论的雷达波形设计研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 葛建军 等: "探测体系能力生成理论及方法", 《雷达科学与技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819622A (en) * | 2021-01-26 | 2021-05-18 | 深圳价值在线信息科技股份有限公司 | Information entity relationship joint extraction method and device and terminal equipment |
| CN112819622B (en) * | 2021-01-26 | 2023-10-17 | 深圳价值在线信息科技股份有限公司 | Information entity relationship joint extraction method and device and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110209993B (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huda et al. | A malicious threat detection model for cloud assisted internet of things (CoT) based industrial control system (ICS) networks using deep belief network | |
| Estrada | Introduction to complex networks: structure and dynamics | |
| Arnborg et al. | Characterization and recognition of partial 3-trees | |
| CN103430179B (en) | Add method, system and the computer-readable recording medium of new images and its relevant information in image data base | |
| CN109815788A (en) | A kind of picture clustering method, device, storage medium and terminal device | |
| CN108491228A (en) | A kind of binary vulnerability Code Clones detection method and system | |
| CN108388923A (en) | A kind of unified diagram analysis network based on object detector and recurrent neural network | |
| Ghassemi et al. | An extended bayesian optimization approach to decentralized swarm robotic search | |
| CN110209993A (en) | A kind of information extraction method and system detecting target | |
| Sun et al. | A parallel self-organizing overlapping community detection algorithm based on swarm intelligence for large scale complex networks | |
| CN109543424A (en) | Data-privacy guard method, device, system and storage medium | |
| CN109088788A (en) | Data processing method, device, equipment and computer readable storage medium | |
| Chen et al. | Automatic and exact symmetry recognition of structures exhibiting high-order symmetries | |
| CN110210564A (en) | Similar house type detection method and device | |
| Maray et al. | Intelligent metaheuristics with optimal machine learning approach for malware detection on IoT‐enabled maritime transportation systems | |
| Cui et al. | A distributed agent implementation of multiple species flocking model for document partitioning clustering | |
| CN109726404A (en) | Training data Enhancement Method, device and the medium of end to end model | |
| CN114974398A (en) | Information processing method and device and computer readable storage medium | |
| CN110399485A (en) | The data source tracing method and system of word-based vector sum machine learning | |
| Chiang et al. | Identification of Patterns of Repeated Parts in Solid Objects | |
| Ho et al. | Multi-task learning improves ancestral state reconstruction | |
| Feiler et al. | Simultaneous identification and control of time-varying systems | |
| Balasubramanyam et al. | P-field: a computational model for binocular motion processing | |
| CN113450612A (en) | Development method of complete teaching device applied to relay protection training | |
| Sipiran et al. | A fully hierarchical approach for finding correspondences in non-rigid shapes |
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 |