CN104572829A - Research recommendation method for brain informatics - Google Patents
Research recommendation method for brain informatics Download PDFInfo
- Publication number
- CN104572829A CN104572829A CN201410746209.2A CN201410746209A CN104572829A CN 104572829 A CN104572829 A CN 104572829A CN 201410746209 A CN201410746209 A CN 201410746209A CN 104572829 A CN104572829 A CN 104572829A
- Authority
- CN
- China
- Prior art keywords
- interest
- researcher
- value
- brain
- cognitive function
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of brain informatics, and relates to a research recommendation method for the brain informatics. The method comprises the following steps of obtaining all literature published by a researcher in the past; performing statistics on interest in interest sides of cognitive functions in all the literature published by the researcher; computing a retention interest value of each interest in the interest sides of the cognitive functions; computing the interest corresponding to the maximum interest retention value of the interest sides of the cognitive functions; computing the maximum retention interest in other interest sides, i.e. a device type, a subject type and a sensory perception channel; compiling query statements according to the maximum retention interest in four interest sides, and adding the interest of the researcher to the query statements to obtain a recommendation result. According to the research recommendation method provided by the invention, by taking a brain information source as metadata of the literature, the content of an article, and the research interest of the researcher can be expressed more accurately; query is improved according to the interest, on a brain information source model, of the researcher; compared with the existing method, the research recommendation method has the advantages that the problem of query surplus is solved, and the accuracy of a query result is greatly increased.
Description
Technical field
The invention belongs to brain informatics, relate to a kind of brain information science research recommend method, the brain information source utilizing the document delivered in the past by researcher to generate obtains interest, carries out Individuation research recommendation.
Background technology
Brain information science belongs to a cross discipline of computer science, cognitive science, Neuscience, it from the visual angle of both macro and micro to the research of human performane mechanism development system.Systematized brain Informatics Method comprises four aspects: observe complicated brain science problem, Design cognition experiment systematically systematically, manage brain data systematically, analyze brain data systematically.It contains various experimental design method and data analysing method, and researcher needs to consult a large amount of documents to find the research relevant to oneself.In order to the research brain information science of back-up system, brain and intelligent large data center are developed.Based on this system, researcher can inquire about correlative study, but often has a lot of unwanted document in Query Result, and researcher needs the time of at substantial to find the document of oneself needs.To this, often need structure one to study commending system to improve inquiry, reduce the time that researcher filters document, improve Efficiency.Existing research recommend method is generally the recommend method based on keyword in title, because keyword in title is fairly simple, the content of brain information science document and the interest of researcher can not be expressed exactly, as the research commending system (I-ReaSearch) etc. based on interest, cause Query Result superfluous, namely comprise a lot of unwanted document in Query Result, the slow efficiency of inquiry velocity is low.
Summary of the invention
For prior art Problems existing, the invention provides a kind of brain information science research recommend method based on source, effectively can solve the problem of Query Result surplus.
Brain information science research recommend method based on source comprises the following steps:
Step one: obtain the document that researcher delivers in the past according to researcher's name from brain and the large data system of intelligence.
In brain and the large data system of intelligence, brain information science scientific and technical literature stores with the form of brain information source, according to researcher's name, can directly find it to deliver brain information source data corresponding to document in the past, for calculating.
Step 2: the interest to cognitive function interest side in every section of document that statistical research person delivers.
Cognitive function in every section of document that acquisition researcher delivers, it can be used as the value of the cognitive function interest side of this section of article.
Cognitive function is a part for function dimension in data brain.It comprises multiple subclass, such as Attention, computation, Reasoning etc.Cognitive function is one of main contents of brain information science researchist research.Study different cognitive functions with having different experimental designs, analytical approach etc.
Step 3: the reservation interest value calculating each interest in cognitive function interest side.
According to reservation interest formula, calculate the reservation interest value of each interest of cognitive function interest side, formula is as follows:
In formula, t
e (k)i () represents i-th interest in a kth interest side, RI (t
e (k)i (), n) is interest t
e (k)(i) maintenance interest value within this time period; Q is the quantity that author publishes an article in time interval j; W
pbe the weight of p section article, m is author's rank;
value be 0 or 1, when in time interval j, the interest of p section article is t
e (k)i, time (), its value is 1, otherwise be 0.
interest t
e (k)the duration of (i), namely occur to the current time interval from interest; A, b are constant, and the present invention gets A=0.855, b=1.295.
Step 4: the interest calculating the subject of great interest retention of cognitive function interest side.
Retain interest value to the interest of cognitive function interest side to sort, and obtain the interest corresponding to subject of great interest retention.
Step 5: circulation step two ~ tetra-, calculates the maximum reservation interest of other interest side and device type, tested type and sensory perception passage.
Step 6: the maximum reservation interest according to four interest sides writes query statement, joins in query statement by the interest of researcher, obtains recommendation results.
Compared with prior art, tool of the present invention has the following advantages:
The present invention is using the metadata of brain information source as document, and the document delivered in the past according to researcher calculates its interest to brain Study on Information Source Model, expresses the content of article more accurately, and the research interest of researcher.According to researcher, inquiry is improved to the interest of brain Study on Information Source Model, compared with the conventional method, solve inquiry overstock problem, substantially increase the accuracy of Query Result.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the method for the invention;
Fig. 2 is the contrast adopting the method for the invention and existing method Query Result.
Embodiment
Below in conjunction with drawings and Examples, the present invention is conducted further description:
The correlative study that the present embodiment is induction for concrete researcher's beam pendant roc inquiry cognitive function, verifies recommend method by checking its Query Result.
Researcher's beam pendant roc inquires about the research about Induction in brain and intelligent large data center system, has 98 sections, the article of non-beam pendant roc in current system.Commending system can calculate the interest of Liang Peipeng about other three interest sides (having given the interest of cognitive function interest side: Induction) by automatic analysis, improves and inquires about and obtain result.
The recommend method process flow diagram of the present embodiment as shown in Figure 1, specifically comprises the following steps:
Step one: find out the document that Liang Peipeng delivers in the past.
The document of query and search beam pendant roc in brain and intelligent large data center system, as Recruitment of the pre-motorarea in human inductive reasoning:An fMRI study, Time Dissociative Characteristics ofNumerical Inductive Reasoning:Behavioral and ERP Evidence etc.
Step 2: the interest to device type interest side in every section of document that calculating Liang Peipeng delivers.
As in two sections of documents of the Liang Peipeng in step one, the interest of device type interest side is respectively fMRI and ERP.
Step 3: the reservation interest value of each interest in computing equipment type interest side.
According to retaining interest value computing formula (1), to obtain Liang Peipeng about the interest retention that the interest retention of device type fMRI is 0.914, device type ERP be 0.668.
Step 4: the interest of the subject of great interest retention of computing equipment type interest side.
Can be calculated, Liang Peipeng is fMRI about device type subject of great interest.
Step 5: circulation step two ~ tetra-, obtains the maximum reservation interest of other interest side.
Can be calculated, Liang Peipeng is Normal-Subjects about the maximum reservation interest of tested type, and it retains interest value is 1.372; Maximum reservation interest about sensory perception passage is Visual, and it retains interest value is 1.475.
Step 6: utilize fMRI, Normal-Subject and Visual to write query statement, obtains result.
In order to verify the validity of the method for the invention, Fig. 2 gives the Comparative result adopting the method for the invention to carry out inquire about and adopt existing method namely not add to study interest and carry out inquiring about.As shown in Figure 2, the Query Result not adding research interest is 36, and the Query Result after rewritten query statement is 11.The 25 sections of documents not meeting Liang Peipeng research interest remove by the research recommend method that the present invention is based on source.
It can thus be appreciated that the research recommend method based on source greatly can reduce the time that researcher filters document, improve the work efficiency of brain information science researchist.
Claims (2)
1. a brain information science research recommend method, is characterized in that comprising the following steps:
Step one: obtain the document that researcher delivers in the past according to researcher's name from brain and the large data system of intelligence;
Step 2: the interest to cognitive function interest side in every section of document that statistical research person delivers;
Cognitive function in every section of document that acquisition researcher delivers, it can be used as the value of the cognitive function interest side of this section of article;
Step 3: the reservation interest value calculating each interest in cognitive function interest side;
Step 4: the interest calculating the subject of great interest retention of cognitive function interest side;
Retain interest value to the interest of cognitive function interest side to sort, and obtain the interest corresponding to subject of great interest retention;
Step 5: circulation step two ~ tetra-, calculates the maximum reservation interest of other interest side and device type, tested type and sensory perception passage;
Step 6: the maximum reservation interest according to four interest sides writes query statement, joins in query statement by the interest of researcher, obtains recommendation results.
2. a kind of brain information science research recommend method according to claim 1, it is characterized in that, the formula calculating the reservation interest value of each interest in cognitive function interest side described in step 3 is as follows:
In formula, t
e (k)i () represents i-th interest in a kth interest side, RI (t
e (k)i (), n) is interest t
e (k)(i) maintenance interest value within this time period; Q is the quantity that author publishes an article in time interval j; W
pbe the weight of p section article, m is author's rank;
value be 0 or 1, when in time interval j, the interest of p section article is t
e (k)i, time (), its value is 1, otherwise be 0;
interest t
e (k)the duration of (i), namely occur to the current time interval from interest; A, b are constant.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410746209.2A CN104572829B (en) | 2014-12-08 | 2014-12-08 | A kind of brain informatics research recommendation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410746209.2A CN104572829B (en) | 2014-12-08 | 2014-12-08 | A kind of brain informatics research recommendation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104572829A true CN104572829A (en) | 2015-04-29 |
CN104572829B CN104572829B (en) | 2018-02-23 |
Family
ID=53088891
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410746209.2A Active CN104572829B (en) | 2014-12-08 | 2014-12-08 | A kind of brain informatics research recommendation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104572829B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020029162A1 (en) * | 2000-06-30 | 2002-03-07 | Desmond Mascarenhas | System and method for using psychological significance pattern information for matching with target information |
CN103336793A (en) * | 2013-06-09 | 2013-10-02 | 中国科学院计算技术研究所 | Personalized paper recommendation method and system thereof |
CN103440329A (en) * | 2013-09-04 | 2013-12-11 | 北京邮电大学 | Authoritative author and high-quality paper recommending system and recommending method |
-
2014
- 2014-12-08 CN CN201410746209.2A patent/CN104572829B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020029162A1 (en) * | 2000-06-30 | 2002-03-07 | Desmond Mascarenhas | System and method for using psychological significance pattern information for matching with target information |
CN103336793A (en) * | 2013-06-09 | 2013-10-02 | 中国科学院计算技术研究所 | Personalized paper recommendation method and system thereof |
CN103440329A (en) * | 2013-09-04 | 2013-12-11 | 北京邮电大学 | Authoritative author and high-quality paper recommending system and recommending method |
Non-Patent Citations (2)
Title |
---|
门瑞: "高质量个性化论文推荐系统研究", 《中国优秀硕士学位论文全文数据库》 * |
陈建辉: "基于脑信息学的数据脑建模及其应用", 《中国博士学位论文全文数据库》 * |
Also Published As
Publication number | Publication date |
---|---|
CN104572829B (en) | 2018-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pastor et al. | Mean and covariance structure mixture models. | |
Kachroo et al. | Inverse problem for non-viscous mean field control: Example from traffic | |
CN103150383B (en) | A kind of event evolution analysis method of short text data | |
Jafari et al. | Comment on “Parameter identification and synchronization of fractional-order chaotic systems”[Commun Nonlinear Sci Numer Simulat 2012; 17: 305–16] | |
CN105069574A (en) | New method for analyzing business flow behavior similarity | |
CN105787265A (en) | Atomic spinning top random error modeling method based on comprehensive integration weighting method | |
Yuan et al. | How long will the traffic flow time series keep efficacious to forecast the future? | |
Metzke et al. | Enabling semantic complex event processing in the domain of logistics | |
CN104572829A (en) | Research recommendation method for brain informatics | |
Aslam et al. | Design of X-bar control chart using multiple dependent state sampling under indeterminacy environment | |
CN102063812A (en) | Self-adaption optimization computer-assisted learning system and method | |
Sahraei et al. | Determination of gap acceptance at priority intersections | |
Lamba et al. | CitizenPulse: A text analytics framework for proactive e-governance-a case study of mygov. in | |
Wang et al. | Criteria for the Selection and Application of Advanced Traffic Signal Systems | |
Gero et al. | Comparing the design cognition of concept design reviews of industrial and mechanical engineering designers | |
Zare | Application and analysis of physical and data-driven stochastic hydrological simulation-optimization methods for the optimal Management of surface-groundwater resources systems: Iranian cases studies | |
Almas et al. | Representing Humanities Research Data Using Complementary Provenance Models | |
Hadia et al. | Implementation and comparative analysis of the optimisations produced by evolutionary algorithms for the parameter extraction of PSP MOSFET model | |
Grigoraș | Teorii și modele în psihologia sănătății ocupaționale | |
Xia et al. | Modeling of adaptive human–machine systems based on fuzzy inference Petri nets | |
Breard | A continuous learning strategy for self-organizing maps based on convergence windows | |
Liu et al. | CA-RPT: Context-Aware Road Passage Time Estimation for Urban Traffic | |
Jiang et al. | Traffic Parameters Prediction Method Based on Rolling Time Series | |
李梦妍 et al. | Prediction method of equipment performance parameter based on improved wavelet neural network and grey model | |
Chebel | Raymond Aron and the ethics of current global affairs |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Chen Jianhui Inventor after: Han Jian Inventor after: Zhong Han Inventor after: Wang Ningning Inventor after: Zhong Ning Inventor before: Han Jian Inventor before: Zhong Han Inventor before: Wang Ningning Inventor before: Chen Jianhui Inventor before: Zhong Ning |
|
GR01 | Patent grant | ||
GR01 | Patent grant |