CN104346446A - Paper associated information recommendation method and device based on mapping knowledge domain - Google Patents
Paper associated information recommendation method and device based on mapping knowledge domain Download PDFInfo
- Publication number
- CN104346446A CN104346446A CN201410585040.7A CN201410585040A CN104346446A CN 104346446 A CN104346446 A CN 104346446A CN 201410585040 A CN201410585040 A CN 201410585040A CN 104346446 A CN104346446 A CN 104346446A
- Authority
- CN
- China
- Prior art keywords
- paper
- papers
- scholar
- attribute information
- information
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/338—Presentation of query results
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 provides a paper associated information recommendation method and device based on a mapping knowledge domain. The method comprises the following steps: analyzing inquired content of a user, so as to obtain the type of the inquired content, retrieving the inquired content, so as to obtain a plurality of papers containing the inquired content, obtaining a side relation corresponding to the type from the mapping knowledge domain according to attribute information of the papers, and recommending paper information associated with the inquired content for the user according to the side relation. The embodiment of the method can ensure that a user obtains more paper information associated with interested inquired content from the mapping knowledge domain, the user can properly carry out scientific research, and the efficiency for obtaining relevant paper information by the user is improved.
Description
Technical field
The present invention relates to internet technique field, particularly relate to a kind of paper related information recommend method and device of knowledge based collection of illustrative plates.
Background technology
At academic scientific research field, scholar/student/researcher etc. finally can be delivered in the mode of paper the achievement in research of certain knowledge, and the paper delivered itself contains a lot of attribute, Fig. 1 is the schematic diagram of one section of paper information of library's record, as shown in Figure 1, in one section of paper of library's record, topmost attribute is: Authors of Science Articles (being more than or equal to 1 author) and author mechanism, paper publishing place (comprising periodical, meeting, school's (i.e. academic dissertation)), paper keyword, citing document and cited literature 2, research field.
Respective community set is constituted again between the same alike result of many sections of papers, association between collection of thesis and property set defines the knowledge mapping of paper, current domestic and international Chinese and English paper has a more than one hundred million section, scientific research scholars still rest on when doing scientific research and obtaining scientific research data and utilize search engine to do the modes such as keyword retrieval, tutor's recommendation, scientific seminar's interchange, huge paper knowledge factor data amount is large, and normalizing difficulty problem is not well used at present.
Summary of the invention
The embodiment of the present invention provides a kind of paper related information recommend method and device of knowledge based collection of illustrative plates, and user is better engaged in scientific research, and improves the efficiency that user obtains correlative theses information.
For achieving the above object, embodiments of the invention adopt following technical scheme:
A paper related information recommend method for knowledge based collection of illustrative plates, the method comprises:
The query contents of user is resolved, obtains the type of described query contents, and, described query contents is retrieved, obtains the many sections of papers comprising described query contents;
From knowledge mapping, obtaining the frontier juncture corresponding with described type according to the attribute information of described many sections of papers is;
Be the paper information that described user recommends to be associated with described query contents according to described frontier juncture.
A paper related information recommendation apparatus for knowledge based collection of illustrative plates, this device comprises:
Pretreatment module, for resolving the query contents of user, obtains the type of described query contents, and, described query contents is retrieved, obtains the many sections of papers comprising described query contents;
First acquisition module, for obtaining the frontier juncture corresponding with described type according to the attribute information of described many sections of papers from knowledge mapping is;
Recommending module, for according to described frontier juncture being the paper information that described user recommends to be associated with described query contents.
The paper related information recommend method of the knowledge based collection of illustrative plates that the embodiment of the present invention provides and device, by query contents from knowledge mapping for user recommends paper information, allow user can get the paper information of knowledge based collection of illustrative plates recommendation while retrieval paper, thus make user just can get from interested query contents the more paper information be associated with this query contents from knowledge mapping, user is better engaged in scientific research, improves the efficiency that user obtains correlative theses information.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of one section of paper information of library's record.
Fig. 2 is the schematic diagram of the knowledge mapping in the embodiment of the present invention.
The schematic flow sheet of the paper related information recommend method of the knowledge based collection of illustrative plates that Fig. 3 provides for the embodiment of the present invention one.
Fig. 4 is the result schematic diagram that the embodiment of the present invention carries out with professional term " action recognition " searching for.
Fig. 5 is the result schematic diagram that the embodiment of the present invention carries out with scholar " Xu Guangyou " searching for.
Fig. 6 is the result schematic diagram that the embodiment of the present invention carries out with periodical " journal of information " searching for.
The schematic flow sheet of the paper related information recommend method of the knowledge based collection of illustrative plates that Fig. 7 provides for the embodiment of the present invention two.
The structural representation of the paper related information recommendation apparatus of the knowledge based collection of illustrative plates that Fig. 8 provides for the embodiment of the present invention three.
The structural representation of the paper related information recommendation apparatus of the knowledge based collection of illustrative plates that Fig. 9 provides for the embodiment of the present invention four.
Embodiment
Below in conjunction with accompanying drawing, the paper related information recommend method of the knowledge based collection of illustrative plates that the embodiment of the present invention provides and device are described in detail.
Fig. 2 is the schematic diagram of the knowledge mapping in the embodiment of the present invention; As shown in Figure 2, the knowledge mapping in the embodiment of the present invention includes paper, scholar, periodical, meeting, mechanism five class entity; Wherein, frontier juncture system (embodiment of the present invention also can be called incidence relation) is set up between entity; Wherein, in the knowledge mapping of the embodiment of the present invention, in one embodiment, knowledge mapping can also comprise: scholar's collection of illustrative plates, scholar-periodical collection of illustrative plates, scholar-meeting collection of illustrative plates, scholar-mechanism's collection of illustrative plates.
Particularly, in scholar's collection of illustrative plates, if two scholars have the paper of co-present, just represent relevant between the entity represented by two scholars, be then set up a limit between two scholars, as the frontier juncture between the scholar A in Fig. 2 and scholar B be, frontier juncture between scholar A and scholar C is, frontier juncture between scholar B and scholar C is; The paper of two scholar's co-presents is more, then the weight of frontier juncture system is larger, represents that the incidence relation between these two scholars is tightr.
In scholar-periodical collection of illustrative plates, if there is scholar to deliver paper at this periodical, then represent relevant between this periodical and this scholar, then determine frontier juncture system therebetween (as the frontier juncture between the scholar A in Fig. 2 and periodical M be, frontier juncture between scholar B and periodical N is), thus, each periodical has a lot of bar limit according to the relation between scholar; Otherwise from the angle of scholar, if this scholar all has paper publishing at a lot of periodicals, then also corresponding between this scholar to multiple periodical multiple frontier juncture that has is.
In scholar-meeting collection of illustrative plates, if scholar delivered paper in this meeting, then represent relevant between this meeting and scholar, then set up a limit, frontier juncture between scholar B as shown in Figure 2 and meeting E is, frontier juncture between scholar B and meeting F is, frontier juncture between scholar C and meeting E is therefore have a lot of bar limit in each meeting; Conversely from the angle of scholar, if scholar all has paper publishing a lot of meetings, then each scholar also has a lot of bar limit.
In scholar-mechanism's collection of illustrative plates, each scholar has a corresponding scholar mechanism, and from mechanism, have a lot of scholars under each mechanism, then each institutional bodies has a lot of limit; As shown in Figure 2, the frontier juncture between scholar C and mechanism D is, the frontier juncture between scholar A and mechanism G is.
From the knowledge mapping shown in Fig. 2, the collection of illustrative plates of knowledge network has been built between multiple entity, from the point of any one entity, can have between a lot of limit and other entity and be associated, every bar limit represents different weight relationships, also just means and can recommend paper information according to different weight relationships to user.
Embodiment one:
The schematic flow sheet of the paper related information recommend method of the knowledge based collection of illustrative plates that Fig. 3 provides for the embodiment of the present invention one, Fig. 4 is the result schematic diagram that the embodiment of the present invention carries out with professional term " action recognition " searching for, Fig. 5 is the result schematic diagram that the embodiment of the present invention carries out with scholar " Xu Guangyou " searching for, and Fig. 6 is the result schematic diagram that the embodiment of the present invention carries out with periodical " journal of information " searching for; Below in conjunction with the knowledge mapping shown in Fig. 2 and Fig. 4-Fig. 6, the technical scheme to the embodiment of the present invention is described, and as shown in Figure 3, the embodiment of the present invention comprises the steps:
Step 101, resolves the query contents of user, obtains the type of query contents, and, query contents is retrieved, obtains the many sections of papers comprising query contents.
Step 102, obtains the frontier juncture system corresponding with type according to the attribute information of many sections of papers from knowledge mapping;
Step 103 is the paper information that user recommends to be associated with query contents according to frontier juncture.
In a step 101, as shown in Figure 4, the query contents of user is " action recognition ", by resolving query contents " action recognition ", determine that the type of this query contents is the professional term in professional term, " action recognition " is retrieved, obtain the many sections of many sections of papers containing " action recognition ", in these many sections of papers, contain " attribute information " of many sections of papers, in one embodiment, " attribute information " can comprise " the keyword set in paper, scholar, meeting or periodical " etc., in addition, also need by retrieving this " action recognition ", thus obtain the many sections of papers comprising this " action recognition ".In another embodiment, type can also be scholar, such as, as shown in Figure 5, inputted " Xu Guangyou " by the interface of search engine, then can be retrieved by " Xu Guangyou ", thus be comprised the many sections of papers of " Xu Guangyou ", in a further embodiment, type can also be periodical, as shown in Figure 6, is inputted " journal of information " by the interface of search engine, then can be retrieved by " journal of information ", thus be comprised many sections of relevant papers of " journal of information ".In another embodiment, can also input " action recognition " or " Xu Guangyou " from the interface of corresponding Periodical Database Based, thus get many sections of papers in corresponding database.
In a step 102, first can obtain the attribute information of many sections of papers, the further position of acquisition attribute information in knowledge mapping, the position in knowledge mapping obtains the frontier juncture system corresponding with type, and the frontier juncture system in the embodiment of the present invention also can become weight relationship, in one embodiment, type due to " action recognition " is professional term, after retrieving many sections of papers by " action recognition ", corresponding attribute information is got from many sections of papers, as shown in Figure 4, after retrieving many sections of papers, the attribute information that can get many sections of papers comprises " intelligent space, space-time characteristic, wireless body area network, ... " etc. keyword set, the attribute information that can also get many sections of papers comprises " " computer engineering and application ", " Journal of Software ", " Shanghai Communications University's journal ", " electronic engineering " " etc. periodical title, " Yang Jie can also be got, Zhang Zonglin, Xu Guangyou, Qin Liang demonstrate,proves, Liu Hong " etc. the name of the scholar relevant to " action recognition " place technical field.It will be appreciated by persons skilled in the art that above-mentioned citing be recommended out carry out exemplary illustration for example, also need can obtain the recommendation information shown in Fig. 4 by step 103.After passing through above-mentioned attribute information, the frontier juncture system corresponding with type can be obtained from knowledge mapping, such as, the type of " action recognition " is professional term, after obtaining many sections of papers according to this professional term, from these many sections of papers, corresponding attribute information can be got again, then from knowledge mapping, obtain the frontier juncture corresponding with this professional term " action recognition " according to attribute information " keyword set " and be.
In step 103, shown in composition graphs 2, be the paper information that user recommends to be associated with " action recognition " according to frontier juncture again, the content of recommendation is as the paper information be associated with " action recognition " in " keyword, related journals, the relevant scholar " shown on the right side of Fig. 4.
The paper related information recommend method of the knowledge based collection of illustrative plates that the embodiment of the present invention provides, by query contents from knowledge mapping for user recommends paper information, allow user can get the paper information of knowledge based collection of illustrative plates recommendation while retrieval paper, thus make user just can get from interested query contents the more paper information be associated with this query contents from knowledge mapping, user is better engaged in scientific research, improves the efficiency that user obtains correlative theses information.
Below by Fig. 4, the Advantageous Effects of the embodiment of the present invention is described in detail, search engine of the prior art just provides the information relevant to paper by descriptor search, the content that paper is associated can not be seen, such as: search for the paper relevant to " action recognition ", existing search engine only carries out converging information to " action recognition ", user can acquire the correlative theses comprising " action recognition " descriptor, and do not know which the research be associated with " action recognition " has, do not know which well-known scholar in " action recognition " this field and outstanding periodical have yet.
As shown in Figure 4, user search " action recognition " this descriptor equally, the embodiment of the present invention is except retrieving query contents, the paper information that is associated with query contents can also be recommended for user, thus make user from the descriptor expressed by a query contents, get abundanter more fully knowledge, user is better engaged in scientific research, improve the efficiency that user obtains correlative theses information.As shown in Figure 4, on searched page, include following paper information:
1) keyword: recommend the keyword relevant to " action recognition ", represent the research relevant to " action recognition ", such as " sparse coding ", " wavelet transformation ", which the research that user can know easily and " action recognition " is associated has, thus expanded the scope of one's knowledge of user;
2) related journals: represent and study and the paper delivered " action recognition ", these papers are mainly published on recommended authoritative journal, thus make user can with reference to other correlative theses on recommended periodical.
3) relevant scholar: the well-known scholar of representative research " action recognition " technical field, user can get its paper be associated with " action recognition " delivered by these scholars.
Embodiment two:
The schematic flow sheet of the paper related information recommend method of the knowledge based collection of illustrative plates that Fig. 5 provides for the embodiment of the present invention two; As shown in Figure 5, the embodiment of the present invention comprises the steps:
Step 201, resolves the query contents of user, obtains the type of query contents, and, query contents is retrieved, obtains the many sections of papers comprising query contents, perform step 201.
The detailed description of the step 201 in the embodiment of the present invention please refer to the description of step 101 in above-described embodiment one, does not repeat them here.
Step 202, determines the attribute information of many sections of papers, and wherein, attribute information comprises the keyword set of many sections of papers, several scholar, periodical or meeting; If attribute information comprises the keyword set of many sections of papers, perform step 203, if attribute information comprises the several scholars relevant to many sections of papers, perform step 206, if attribute information comprises the multiple periodicals be associated with many sections of papers, perform step 209.
In step 202., the attribute information of paper can carry out Classification and Identification by Authors of Science Articles (being more than or equal to 1 author) included in section paper of shown in Fig. 1 and author mechanism, paper publishing place (comprising periodical, meeting, school's (i.e. academic dissertation)), paper keyword, citing document and the attribute such as cited literature 2, research field, when the paper having many sections of fields close or identical, the then set that formed of the attribute information of each section of paper, forms the attribute information of many sections of papers.
Step 203, sorts to the paper record that keyword set occurs jointly, and wherein, paper record represents the weight that frontier juncture is, performs step 204.
Step 204, obtains the keyword coming front first setting number, performs step 205 from keyword combination.
Step 205, the keyword of the first setting number before recommending to user, keyword is paper information, and flow process terminates.
In step 203-step 205, in one embodiment, the type of query contents is professional term, then retrieval comprises all papers of this query contents, according to the attribute information such as author, periodical, meeting of paper, obtain the position of above-mentioned attribute information in knowledge mapping, and obtain the paper information be associated with this query contents according to classification information.In one embodiment, if got the keyword set in the many sections of papers be associated with query contents by query contents, then can get other keywords that the paper that comprises current queries content comprises simultaneously (such as by many sections of papers, machine vision etc.), then by multiple keyword (action recognition, machine vision etc.) number of times in the common many sections of papers occurred sorts from high to low, the keyword of the first setting number can be obtained (such as, first setting number is 15 to the maximum, minimum is 3), thus got and the maximally related research contents in field, current queries content place by the keyword of this first setting number.In another embodiment, the type of query contents is scholar, retrieve the many sections of papers that this scholar delivers, find the position of the attribute information of many sections of papers in knowledge mapping according to the author of many sections of papers, periodical, conferencing information, and obtain the paper information be associated with query contents according to type.In one embodiment, the multiple keywords comprised in the many sections of papers that this scholar delivers, the number of times jointly occurred in many sections of papers by multiple keyword sorts from high to low, the keyword of the first setting number can be got (such as, first setting number is 15 to the maximum, minimum is 3), thus get by keyword of this first setting number the maximally related research contents that to publish thesis with the scholar of current queries.
Step 206, sorts to the first quoted frequency sum of the paper that several scholar is associated, and wherein, the first quoted frequency represents the weight that frontier juncture is, performs step 207.
Step 207, obtains the scholar coming front second setting number, performs step 208 from several scholar.
Step 208, the scholar of the second setting number before recommending to user, wherein, second sets the scholar of number as paper information, and flow process terminates.
In step 206-step 208, in one embodiment, as shown in Figure 5, the type of query contents is scholar " Xu Guangyou ", then first retrieve the many sections of papers that this scholar has delivered, according to the author of many sections of papers, periodical, the attribute informations such as conferencing information obtain the position of this attribute information in knowledge mapping, and the paper information be associated with this scholar is obtained according to classification, the quoted frequency sum sequence of the paper that can relate to according to each author in multiple paper, get the scholar of front second setting number (such as, second setting number is 6 to the maximum, minimum is 3), the scholar of this front second setting number represents the maximally related well-known scholar with current queries content.In another embodiment, retrieve the many sections of papers that this scholar delivers, obtain the position of this attribute information in knowledge mapping according to the author of many sections of papers, periodical, conferencing information, and obtain the knowledge content relevant to this scholar according to classification.As shown in Figure 5, by " Xu Guangyou ", the keyword can recommended to user comprises: support vector machine, common calculating etc., related journals comprises: " Journal of Software ", " Chinese journal of computers ", " Journal of Computer Research and Development " etc., relevant scholar comprises: Zhao Hai, Yang Shiqiang etc.
Step 209, sorts to multiple periodical quoted frequency sum, and wherein, the second quoted frequency represents the weight that frontier juncture is, performs step 210.
Step 210, obtains the periodical coming front 3rd setting number, performs step 211 from multiple periodical.
Step 211, the periodical of the 3rd setting number before recommending to user, flow process terminates.
In step 209-step 211, in one embodiment, as shown in Figure 6, the type of query contents is periodical, then first retrieve the many sections of papers that this scholar has delivered, according to the author of many sections of papers, periodical, the attribute informations such as conferencing information obtain the position of this attribute information in knowledge mapping, and the paper information be associated with this scholar is obtained according to classification, the quoted frequency sum sequence of the paper that can relate to according to each author in multiple paper, get the periodical title of front 3rd setting number (such as, 3rd setting number is 6 to the maximum, minimum is 3), the periodical of this front 3rd setting number represents the best periodical that maximally related many sections of papers can be delivered with current queries content.In another embodiment, retrieve the many sections of papers that this scholar delivers, obtain the position of this attribute information in knowledge mapping according to the author of many sections of papers, periodical, conferencing information, and obtain the knowledge content relevant to this scholar according to classification.As shown in Figure 6, by " journal of information ", the keyword can recommended to user comprises: editorial office, preventive medicine etc., related journals comprises: " journal of information ", " preventive medicine journal of information ", " Modern Information " etc., relevant scholar comprises: Yang Hua, Zhang Jinghai etc.
Further, on the basis of above-described embodiment one and embodiment two, the building process of knowledge mapping can also be comprised, specifically can comprise:
First, the attribute information of each section of paper in paper storehouse is obtained;
Secondly, the attribute information according to each section of paper builds knowledge mapping, and wherein, knowledge mapping forms reticulate texture by frontier juncture system.
In one embodiment, the attribute information of every section of paper in paper storehouse can be parsed, each attribute information is by an expression entity (paper as shown in Figure 2, scholar, periodical, mechanism, meeting etc.), by setting up frontier juncture system each other, make to set up contact between multiple entity, final formation reticulate texture, the knowledge mapping namely in the embodiment of the present invention.
Embodiment three:
The structural representation of the paper related information recommendation apparatus of the knowledge based collection of illustrative plates that Fig. 8 provides for the embodiment of the present invention three; As shown in Figure 8, the embodiment of the present invention comprises:
Pretreatment module 31, for resolving the query contents of user, obtains the type of described query contents, and, described query contents is retrieved, obtains the many sections of papers comprising described query contents;
First acquisition module 32, for obtaining the frontier juncture corresponding with described type according to the attribute information of described many sections of papers from knowledge mapping is;
Recommending module 33, for according to described frontier juncture being the paper information that described user recommends to be associated with described query contents.
The Advantageous Effects of the embodiment of the present invention with reference to the Advantageous Effects in above-described embodiment one, can not repeat them here.
Embodiment four:
The structural representation of the paper related information recommendation apparatus of the knowledge based collection of illustrative plates that Fig. 9 provides for the embodiment of the present invention four; As shown in Figure 9, the embodiment of the present invention is on the basis of above-described embodiment three, and the first acquisition module 32 comprises:
First acquiring unit 321, for obtaining the attribute information of described many sections of papers;
Second acquisition unit 322, for obtaining the position of described attribute information in knowledge mapping;
3rd acquiring unit 323, obtaining the frontier juncture corresponding with described type for the position in described knowledge mapping is.
Further, described attribute information is the keyword set of described many sections of papers, and recommending module 33 can comprise:
First sequencing unit 331, sorts for the paper record jointly occurred described keyword set, and wherein, described paper record represents the weight that described frontier juncture is;
4th acquiring unit 332, for obtaining the keyword coming front first setting number from described keyword combination;
First recommendation unit 333, for recommending the keyword of described front first setting number to described user, described keyword is described paper information.
Further, described attribute information is the several scholars relevant to described many sections of papers, and recommending module 33 can comprise:
Second sequencing unit 334, the first quoted frequency sum for the paper be associated to described several scholar sorts, and wherein, described first quoted frequency represents the weight that described frontier juncture is;
5th acquiring unit 335, for obtaining the scholar coming front second setting number from described several scholar;
Second recommendation unit 336, for recommending the scholar of described front second setting number to described user, described second sets the scholar of number as described paper information.
Further, described attribute information is the multiple periodicals be associated with described many sections of papers, and recommending module 33 can comprise:
3rd sequencing unit 337, for sorting to described multiple periodical quoted frequency sum, wherein, described second quoted frequency represents the weight that described frontier juncture is;
6th acquiring unit 338, for obtaining the periodical coming front 3rd setting number from described multiple periodical;
3rd recommendation unit 339, for recommending the periodical of described front 3rd setting number to described user.
In addition, the embodiment of the present invention also can comprise:
Second acquisition module 34, for obtaining the attribute information of each section of paper in paper storehouse;
Build module 35, for building described knowledge mapping according to the attribute information of described each section of paper, wherein, described knowledge mapping forms reticulate texture by described frontier juncture system.
The Advantageous Effects of the embodiment of the present invention with reference to the Advantageous Effects in above-described embodiment two, can not repeat them here.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (12)
1. a paper related information recommend method for knowledge based collection of illustrative plates, it is characterized in that, described method comprises:
The query contents of user is resolved, obtains the type of described query contents, and, described query contents is retrieved, obtains the many sections of papers comprising described query contents;
From knowledge mapping, obtaining the frontier juncture corresponding with described type according to the attribute information of described many sections of papers is;
Be the paper information that described user recommends to be associated with described query contents according to described frontier juncture.
2. method according to claim 1, is characterized in that, the described attribute information according to described many sections of papers obtains the step that the frontier juncture corresponding with described type be and comprises from knowledge mapping:
Obtain the attribute information of described many sections of papers;
Obtain the position of described attribute information in knowledge mapping;
Position in described knowledge mapping obtains the frontier juncture corresponding with described type.
3. method according to claim 1, is characterized in that, described attribute information is the keyword set of described many sections of papers, and described is that described user recommends the step of the paper information be associated with described query contents to comprise according to described frontier juncture:
Sort to the paper record that described keyword set occurs jointly, wherein, described paper record represents the weight that described frontier juncture is;
The keyword coming front first setting number is obtained from described keyword combination.
4. method according to claim 1, is characterized in that, described attribute information is the several scholars relevant to described many sections of papers, and described is that described user recommends the step of the paper information be associated with described query contents to comprise according to described frontier juncture:
Sort to the first quoted frequency sum of the paper that described several scholar is associated, wherein, described first quoted frequency represents the weight that described frontier juncture is;
The scholar coming front second setting number is obtained from described several scholar;
Recommend the scholar of described front second setting number to described user, described second sets the scholar of number as described paper information.
5. method according to claim 1, is characterized in that, described attribute information is the multiple periodicals be associated with described many sections of papers, and described is that described user recommends the step of the paper information be associated with described query contents to comprise according to described frontier juncture:
Sort to described multiple periodical quoted frequency sum, wherein, described second quoted frequency represents the weight that described frontier juncture is;
The periodical coming front 3rd setting number is obtained from described multiple periodical;
The periodical of described front 3rd setting number is recommended to described user.
6., according to the arbitrary described method of claim 1-5, it is characterized in that, described method also comprises:
Obtain the attribute information of each section of paper in paper storehouse;
Build described knowledge mapping according to the attribute information of described each section of paper, wherein, described knowledge mapping forms reticulate texture by described frontier juncture system.
7. a paper related information recommendation apparatus for knowledge based collection of illustrative plates, it is characterized in that, described device comprises:
Pretreatment module, for resolving the query contents of user, obtains the type of described query contents, and, described query contents is retrieved, obtains the many sections of papers comprising described query contents;
First acquisition module, for obtaining the frontier juncture corresponding with described type according to the attribute information of described many sections of papers from knowledge mapping is;
Recommending module, for according to described frontier juncture being the paper information that described user recommends to be associated with described query contents.
8. device according to claim 7, is characterized in that, the step of described first acquisition module comprises:
First acquiring unit, for obtaining the attribute information of described many sections of papers;
Second acquisition unit, for obtaining the position of described attribute information in knowledge mapping;
3rd acquiring unit, obtaining the frontier juncture corresponding with described type for the position in described knowledge mapping is.
9. device according to claim 7, is characterized in that, described attribute information is the keyword set of described many sections of papers, and described recommending module comprises:
First sequencing unit, sorts for the paper record jointly occurred described keyword set, and wherein, described paper record represents the weight that described frontier juncture is;
4th acquiring unit, for obtaining the keyword coming front first setting number from described keyword combination;
First recommendation unit, for recommending the keyword of described front first setting number to described user, described keyword is described paper information.
10. device according to claim 7, is characterized in that, described attribute information is the several scholars relevant to described many sections of papers, and described recommending module comprises:
Second sequencing unit, the first quoted frequency sum for the paper be associated to described several scholar sorts, and wherein, described first quoted frequency represents the weight that described frontier juncture is;
5th acquiring unit, for obtaining the scholar coming front second setting number from described several scholar;
Second recommendation unit, for recommending the scholar of described front second setting number to described user, described second sets the scholar of number as described paper information.
11. devices according to claim 7, is characterized in that, described attribute information is the multiple periodicals be associated with described many sections of papers, and described recommending module comprises:
3rd sequencing unit, for sorting to described multiple periodical quoted frequency sum, wherein, described second quoted frequency represents the weight that described frontier juncture is;
6th acquiring unit, for obtaining the periodical coming front 3rd setting number from described multiple periodical;
3rd recommendation unit, for recommending the periodical of described front 3rd setting number to described user.
12. according to the arbitrary described device of claim 7-11, and it is characterized in that, described device also comprises:
Second acquisition module, for obtaining the attribute information of each section of paper in paper storehouse;
Build module, for building described knowledge mapping according to the attribute information of described each section of paper, wherein, described knowledge mapping forms reticulate texture by described frontier juncture system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410585040.7A CN104346446A (en) | 2014-10-27 | 2014-10-27 | Paper associated information recommendation method and device based on mapping knowledge domain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410585040.7A CN104346446A (en) | 2014-10-27 | 2014-10-27 | Paper associated information recommendation method and device based on mapping knowledge domain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104346446A true CN104346446A (en) | 2015-02-11 |
Family
ID=52502037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410585040.7A Pending CN104346446A (en) | 2014-10-27 | 2014-10-27 | Paper associated information recommendation method and device based on mapping knowledge domain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104346446A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866593A (en) * | 2015-05-29 | 2015-08-26 | 中国电子科技集团公司第二十八研究所 | Database searching method based on knowledge graph |
| CN105335519A (en) * | 2015-11-18 | 2016-02-17 | 百度在线网络技术（北京）有限公司 | Model generation method and device as well as recommendation method and device |
| CN105550216A (en) * | 2015-12-03 | 2016-05-04 | 百度在线网络技术（北京）有限公司 | Searching method and device of academic research information and excavating method and device of academic research information |
| WO2017005196A1 (en) * | 2015-07-08 | 2017-01-12 | 谭红 | Knowledge point structure-based search apparatus |
| CN106934040A (en) * | 2017-03-15 | 2017-07-07 | 中国科学技术信息研究所 | The determination method and determining device of team information |
| CN107133276A (en) * | 2017-04-12 | 2017-09-05 | 安徽富驰信息技术有限公司 | A kind of judicial class case searching system and its search method |
| CN108920556A (en) * | 2018-06-20 | 2018-11-30 | 华东师范大学 | Recommendation expert method based on subject knowledge map |
| CN109033132A (en) * | 2018-06-05 | 2018-12-18 | 中证征信（深圳）有限公司 | The method and device of text and the main body degree of correlation are calculated using knowledge mapping |
| CN109255033A (en) * | 2018-11-05 | 2019-01-22 | 桂林电子科技大学 | A kind of recommended method of the knowledge mapping based on location-based service field |
| CN109522551A (en) * | 2018-11-09 | 2019-03-26 | 天津新开心生活科技有限公司 | Entity link method, apparatus, storage medium and electronic equipment |
| CN110147437A (en) * | 2019-05-23 | 2019-08-20 | 北京金山数字娱乐科技有限公司 | A kind of searching method and device of knowledge based map |
| CN110209779A (en) * | 2018-02-05 | 2019-09-06 | 索意互动（北京）信息技术有限公司 | A kind of client, server, search method and its system |
| CN110362692A (en) * | 2019-07-23 | 2019-10-22 | 中南大学 | A kind of academic circle construction method of knowledge based map |
| CN110502671A (en) * | 2019-08-29 | 2019-11-26 | 南京智慧光信息科技研究院有限公司 | Academic relationship knowledge mapping generation method and robot system based on artificial intelligence |
| CN110737774A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Book knowledge graph construction method, book recommendation method, device, equipment and medium |
| CN111859125A (en) * | 2020-07-09 | 2020-10-30 | 威海天鑫现代服务技术研究院有限公司 | Semantic network construction and service recommendation method oriented to intellectual property technical resource field |
| CN113434706A (en) * | 2020-03-23 | 2021-09-24 | 北京国双科技有限公司 | Academic collaboration relation analysis method and device |
| CN113806597A (en) * | 2021-09-10 | 2021-12-17 | 浙江创邻科技有限公司 | Financial search system and method based on graph database |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308499A (en) * | 2008-07-04 | 2008-11-19 | 华中科技大学 | Document retrieval method based on correlation analysis |
| CN102156706A (en) * | 2011-01-28 | 2011-08-17 | 清华大学 | Mentor recommendation system and method |
| CN103412921A (en) * | 2013-08-12 | 2013-11-27 | 同方光盘股份有限公司 | Structure for displaying knowledge network nodes of literature resources |
| CN103530316A (en) * | 2013-09-12 | 2014-01-22 | 浙江大学 | Science subject extraction method based on multi-view learning |
| CN103995847A (en) * | 2014-05-06 | 2014-08-20 | 百度在线网络技术（北京）有限公司 | Information search method and device |
| US20140280576A1 (en) * | 2013-03-14 | 2014-09-18 | Google Inc. | Determining activities relevant to groups of individuals |
-
2014
- 2014-10-27 CN CN201410585040.7A patent/CN104346446A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101308499A (en) * | 2008-07-04 | 2008-11-19 | 华中科技大学 | Document retrieval method based on correlation analysis |
| CN102156706A (en) * | 2011-01-28 | 2011-08-17 | 清华大学 | Mentor recommendation system and method |
| US20140280576A1 (en) * | 2013-03-14 | 2014-09-18 | Google Inc. | Determining activities relevant to groups of individuals |
| CN103412921A (en) * | 2013-08-12 | 2013-11-27 | 同方光盘股份有限公司 | Structure for displaying knowledge network nodes of literature resources |
| CN103530316A (en) * | 2013-09-12 | 2014-01-22 | 浙江大学 | Science subject extraction method based on multi-view learning |
| CN103995847A (en) * | 2014-05-06 | 2014-08-20 | 百度在线网络技术（北京）有限公司 | Information search method and device |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104866593A (en) * | 2015-05-29 | 2015-08-26 | 中国电子科技集团公司第二十八研究所 | Database searching method based on knowledge graph |
| CN104866593B (en) * | 2015-05-29 | 2018-05-22 | 中国电子科技集团公司第二十八研究所 | A kind of database search method of knowledge based collection of illustrative plates |
| WO2017005196A1 (en) * | 2015-07-08 | 2017-01-12 | 谭红 | Knowledge point structure-based search apparatus |
| CN105335519A (en) * | 2015-11-18 | 2016-02-17 | 百度在线网络技术（北京）有限公司 | Model generation method and device as well as recommendation method and device |
| CN105335519B (en) * | 2015-11-18 | 2021-08-17 | 百度在线网络技术（北京）有限公司 | Model generation method and device and recommendation method and device |
| CN105550216A (en) * | 2015-12-03 | 2016-05-04 | 百度在线网络技术（北京）有限公司 | Searching method and device of academic research information and excavating method and device of academic research information |
| CN106934040A (en) * | 2017-03-15 | 2017-07-07 | 中国科学技术信息研究所 | The determination method and determining device of team information |
| CN106934040B (en) * | 2017-03-15 | 2020-06-16 | 中国科学技术信息研究所 | Method and device for determining team information |
| CN107133276A (en) * | 2017-04-12 | 2017-09-05 | 安徽富驰信息技术有限公司 | A kind of judicial class case searching system and its search method |
| CN110209779A (en) * | 2018-02-05 | 2019-09-06 | 索意互动（北京）信息技术有限公司 | A kind of client, server, search method and its system |
| CN109033132A (en) * | 2018-06-05 | 2018-12-18 | 中证征信（深圳）有限公司 | The method and device of text and the main body degree of correlation are calculated using knowledge mapping |
| CN109033132B (en) * | 2018-06-05 | 2020-12-11 | 中证征信（深圳）有限公司 | Method and device for calculating text and subject correlation by using knowledge graph |
| CN108920556B (en) * | 2018-06-20 | 2021-11-19 | 华东师范大学 | Expert recommending method based on discipline knowledge graph |
| CN108920556A (en) * | 2018-06-20 | 2018-11-30 | 华东师范大学 | Recommendation expert method based on subject knowledge map |
| CN110737774B (en) * | 2018-07-03 | 2024-05-24 | 百度在线网络技术（北京）有限公司 | Book knowledge graph construction method, book recommendation method, device, equipment and medium |
| CN110737774A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Book knowledge graph construction method, book recommendation method, device, equipment and medium |
| CN109255033A (en) * | 2018-11-05 | 2019-01-22 | 桂林电子科技大学 | A kind of recommended method of the knowledge mapping based on location-based service field |
| CN109255033B (en) * | 2018-11-05 | 2021-10-08 | 桂林电子科技大学 | Knowledge graph recommendation method based on location-based service field |
| CN109522551A (en) * | 2018-11-09 | 2019-03-26 | 天津新开心生活科技有限公司 | Entity link method, apparatus, storage medium and electronic equipment |
| CN109522551B (en) * | 2018-11-09 | 2024-02-20 | 天津新开心生活科技有限公司 | Entity linking method and device, storage medium and electronic equipment |
| CN110147437A (en) * | 2019-05-23 | 2019-08-20 | 北京金山数字娱乐科技有限公司 | A kind of searching method and device of knowledge based map |
| CN110362692A (en) * | 2019-07-23 | 2019-10-22 | 中南大学 | A kind of academic circle construction method of knowledge based map |
| CN110502671A (en) * | 2019-08-29 | 2019-11-26 | 南京智慧光信息科技研究院有限公司 | Academic relationship knowledge mapping generation method and robot system based on artificial intelligence |
| CN113434706A (en) * | 2020-03-23 | 2021-09-24 | 北京国双科技有限公司 | Academic collaboration relation analysis method and device |
| CN111859125A (en) * | 2020-07-09 | 2020-10-30 | 威海天鑫现代服务技术研究院有限公司 | Semantic network construction and service recommendation method oriented to intellectual property technical resource field |
| CN113806597A (en) * | 2021-09-10 | 2021-12-17 | 浙江创邻科技有限公司 | Financial search system and method based on graph database |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104346446A (en) | Paper associated information recommendation method and device based on mapping knowledge domain | |
| Chen et al. | Collabseer: a search engine for collaboration discovery | |
| Jomsri et al. | A framework for tag-based research paper recommender system: an IR approach | |
| CN108647276B (en) | Searching method | |
| Ni et al. | Short text clustering by finding core terms | |
| Rakesh et al. | Personalized recommendation of twitter lists using content and network information | |
| CN103838756A (en) | Method and device for determining pushed information | |
| Patak et al. | Taking Mendeley as multimedia-based application in academic writing | |
| CN103399862B (en) | Determine the method and apparatus of search index information corresponding to target query sequence | |
| CN101799830A (en) | Flow data processing method capable of realizing multi-dimensional free analysis | |
| Alghamdi et al. | Topic detections in Arabic dark websites using improved vector space model | |
| CN106294358A (en) | The search method of a kind of information and system | |
| Adamu et al. | A survey on big data indexing strategies | |
| Quattrone et al. | Effective retrieval of resources in folksonomies using a new tag similarity measure | |
| Pratama et al. | Weighted inverse document frequency and vector space model for hadith search engine | |
| Padilla et al. | Intuitive large image database browsing using perceptual similarity enriched by crowds | |
| CN105159899B (en) | Searching method and device | |
| Landia et al. | Extending FolkRank with content data | |
| Yan et al. | A NOVEL SOCIAL IMAGE DATA MINING ALGORITHM BASED ON MULTI-MODEL DATA FUSION. | |
| Jomsri et al. | Improving research paper searching with social tagging—A preliminary investigation | |
| CN105912584B (en) | Data indexing system based on webpage information data | |
| KC et al. | Similarity based web data extraction and integration system for web content mining | |
| Tho et al. | A Web mining approach for finding expertise in research areas | |
| Rettberg et al. | Mining the Knowledge Base: Exploring Methodologies for Analysing the Field of Electronic Literature | |
| US20230134441A1 (en) | Method and system for recommending bookmark of website |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150211 |
|
| RJ01 | Rejection of invention patent application after publication |