CN110377815A - A kind of production, teaching & research recommender system and method - Google Patents
A kind of production, teaching & research recommender system and method Download PDFInfo
- Publication number
- CN110377815A CN110377815A CN201910490657.3A CN201910490657A CN110377815A CN 110377815 A CN110377815 A CN 110377815A CN 201910490657 A CN201910490657 A CN 201910490657A CN 110377815 A CN110377815 A CN 110377815A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- teaching
- research
- production
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (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 discloses a kind of production, teaching & research recommender systems, comprising: production, teaching & research constructs module with data network, for constructing production, teaching & research data network by the master data of user, dynamic data, social data, relation data and search/browse data；Interesting data generation module, for generating the interested category attribute of user by search/browse data, then recommendation results, with the possible interested data of the user are searched in data network, are formed in the production, teaching & research according to the master data, dynamic data, social data, relation data；Recommendation results pushing module, for the recommendation results to be pushed to the user.The present invention has the advantages that can reduce the retrieval cost of user, recommend relatively reliable data to user, improves the joint efficiency of production, teaching & research；Form more true production, teaching & research data network；User is recommended with true and reliable production, teaching & research with data network based on production, teaching & research, meets the needs of user's quick obtaining valid data.
Description
Technical field
The invention belongs to data processing, data recommendation, production, teaching & research technical fields, and in particular to a kind of production, teaching & research recommendation
Method and system.
Background technique
" production, teaching & research with " is a kind of partner systems engineering, literal meaning be exactly produce, learn, scientific research, practice principle
System cooperating.It is said in terms of school, production, teaching & research is exactly to make full use of school and enterprise, R&D institution etc. a variety of with cooperative education
Various teaching environment and teaching resource and the respective advantage in terms of personnel training, teaching school based on knowledge with classroom
Educate and directly acquire practical experience, the forms of education that the production based on the ability of practice, research practice organically combine.
Traditional " production, teaching & research use " cooperation approach has following two:
It 1, is leading " production, teaching & research use " cooperation with enterprise
With the advantage that enterprise is leading " production, teaching & research with " cooperation approach be enterprise can according to the variation in market, in addition
The development need of itself proposes technical requirements, makes " to learn " and " grinding " has specific aim, ensured the market of " production, teaching & research use " cooperation
Change guiding, the new product that makes to study and design and develop out is suitble to market needs.
But this approach is there are some problems, technical application, project selection, in terms of have it is certain
Limitation.Such as most enterprises can only be in enterprise location Finding Cooperative partner, thus not on selection affiliate
The optimal talent can be selected, has significant limitation in the selection of the talent.
It 2, is leading " production, teaching & research use " cooperation with scientific research institutions or institution of higher learning
It is that there is a large amount of outstanding personnel with the advantage that scientific research institutions or institution of higher learning are leading " production, teaching & research with " cooperation
With good scientific research condition, research contents, selection cooperation object are independently determined, the achievement of " " and " grinding " is with technology transfer, special
Benefit is sold to the enterprise of needs.
But this approach, there is also certain limitation, the achievement of " " and " grinding " is although with technology transfer, patent
It is sold to the enterprise of needs, but this achievement may be detached from market, cause technological achievement marketability weaker.Equally, this
The resource consolidation mode of kind approach can not cover the whole nation, there is significant limitation in position.
As can be seen that every kind of approach has respective superiority and inferiority, although these approach from traditional " production, teaching & research use " approach
The one side that all played an important role during cooperation, but also have its unfavorable.
In recent years, the approach to cooperation of " production, teaching & research with " had gradually been transferred on line under line, more and more " production, teaching & research
With " co-operation platform emerges, can integrate the various resources of " production, teaching & research use " on line by way of platform, break ground
The limitation in domain effectively reduces the cost of communication, cooperation.But these platforms are currently limited to the displaying of static data, such as
Achievement, the research contents etc. for introducing a Scientific Research in University Laboratory can not have a mechanism only by these static datas
One comprehensive understanding increases the selection cost of cooperation.
" production, teaching & research with " platform does not carry out the calculating of dynamic data simultaneously as current, leads to not be truly reflected
Relationship of the production, teaching & research between each member；And when " production, teaching & research use " data volume increases, production, teaching & research required for finding manually
It also will increase with the difficulty of data, the reliability for searching for data is also unknowable.
The development of recommender system (Recommender System) has gone through nearly 20 years time, but so far
Attempt to provide recommender system one precise definition still without people.Sensu lato recommender system can be understood as actively to
The system that article (Item) is recommended at family, the article recommended can be music, books, dining room, activity, stock, digital product, new
Entry etc. is heard, this depends on specific application field, the article or be helpful for users that recommender system is recommended, Huo Zheyong
It family may be interested.
With the continuous expansion of e-commerce scale, commodity amount and type constantly increase, and user is for retrieving and recommending
More stringent requirements are proposed.Due to different user hobby, Focus Area, in terms of difference, with meet
For the purpose of the different recommended requirements of different user, different people can obtain the different personalized recommendation systems for being recommended as important feature
(Personalized Recommender System) comes into being.Said recommender system refers generally to personalized recommendation
System.
There is presently no occur comprehensive production, teaching & research master data, dynamic data, social data, relation data and search/
Browse the production, teaching & research recommender system of data.
Summary of the invention
The purpose of the present invention is what is be achieved through the following technical solutions.
The present invention constructs a kind of production, teaching & research recommender system and method, based on " production, teaching & research use " master data, dynamic data,
Social data, relation data and search/browse data form true production, teaching & research data network, according to production, teaching & research data
Network recommends relatively reliable data to user, to improve the joint efficiency and success rate of production, teaching & research, pushes China to produce and learns
It grinds with quickly advancing.
According to the first aspect of the invention, a kind of production, teaching & research recommender system is provided, comprising: production, teaching & research data network
Network constructs module, for passing through the master data of user, dynamic data, social data, relation data and search/browse data structure
Build production, teaching & research data network；Interesting data generation module, for generating the interested classification of user by search/browse data
Attribute, then according to the master data, dynamic data, social data, relation data in the production, teaching & research data network
The possible interested data of the user are searched, recommendation results are formed；Recommendation results pushing module, for pushing away the recommendation results
Give the user.
Further, the master data includes: essential information, ability etc.；The dynamic data include publication achievement,
Project demands, personnel demand, credit requirement, the match of participation and meeting etc.；The social data includes in social operating process
Plusing good friend, give a mark, thumb up, paying close attention to, collecting data etc., and data that partner is evaluated after user cooperates；
The relation data is the relation data between the user excavated based on above-mentioned master data, dynamic data and social data.
Further, the push mode of the recommendation results are as follows: when user actively searches for, by search key and produce
It grinds and is combined with data network, the possible interested data of user are placed on front, recommendation results are pushed to user.
Further, the push mode of the recommendation results are as follows: when user passively receives, according to the search of user/clear
Look at data, searched in production, teaching & research network user may interested data, recommendation results are pushed to user.
According to the second aspect of the invention, a kind of production, teaching & research recommended method is additionally provided, comprising: pass through the base of user
Notebook data, dynamic data, social data, relation data and search/browse data construct production, teaching & research data network；By searching
Rope/browsing data generate the interested category attribute of user, then according to the master data, dynamic data, social data, pass
Coefficient, with the possible interested data of the user are searched in data network, forms recommendation results according in the production, teaching & research；It will be described
Recommendation results are pushed to the user.
According to the third aspect of the present invention, a kind of non-transitorycomputer readable storage medium is additionally provided, is deposited thereon
Computer program is contained, the production, teaching & research recommendation side as described in second aspect is realized when the computer program is executed by processor
Method.
The present invention has the advantages that
1, the exclusive recommender system of " production, teaching & research use " can reduce the retrieval cost of user, recommend to user relatively reliable
Data, improve production, teaching & research joint efficiency.
2, comprehensive " production, teaching & research use " master data, dynamic data, social data, relation data and search/browse data, shape
At more true production, teaching & research data network.
3, user is recommended with true and reliable production, teaching & research with data network based on production, teaching & research, meets user and quickly obtains
Take the needs of valid data.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Attached drawing 1 shows a kind of production, teaching & research recommender system structure chart of embodiment according to the present invention；
The production, teaching & research that attached drawing 2 shows embodiment according to the present invention constructs schematic diagram with data network；
Attached drawing 3 shows a kind of production, teaching & research recommended method flow chart of embodiment according to the present invention.
Specific embodiment
The illustrative embodiments of the disclosure are more fully described below with reference to accompanying drawings.Although showing this public affairs in attached drawing
The illustrative embodiments opened, it being understood, however, that may be realized in various forms the disclosure without the reality that should be illustrated here
The mode of applying is limited.It is to be able to thoroughly understand the disclosure on the contrary, providing these embodiments, and can be by this public affairs
The range opened is fully disclosed to those skilled in the art.
The invention proposes a kind of production, teaching & research recommender systems, firstly, passing through the master data of user, dynamic data, society
Intersection number evidence, relation data and search/browse data construct production, teaching & research data network, raw with data network based on production, teaching & research later
At user's data of interest, recommendation results are finally pushed to user in some way.
Embodiment 1
Specifically, the present invention describes a kind of production, teaching & research recommender system, as shown in Figure 1, comprising:
1. production, teaching & research constructs module 101 with data network, for constructing production, teaching & research data network.
According to the master data of " production, teaching & research use " member, dynamic data, social data, relation data and search/browse number
According to building production, teaching & research data network together.
It is as shown in Figure 2 that production, teaching & research data network constitutes figure, comprising:
(1) master data
Master data includes: essential information, ability etc., such as the master data of expert may include: name, work shoe
It goes through, research topic etc., master data is stored in the data network of " production, teaching & research use " as independent node.
(2) dynamic data
Dynamic data refers to achievement, project demands, personnel demand, credit requirement, the match of participation and meeting of publication etc.,
These dynamic datas can embody the information such as demand and the ability of the users such as expert, team.
(3) social data
The socially relevant data such as plusing good friend is had in social operating process, gives a mark, thumb up, paying close attention to, collecting, in addition to this,
System evaluation can be carried out to partner after user cooperates, evaluation content may include that efficiency is high/low, it is difficult/easy etc. to link up, and comment
Valence content had both been used as a part of social data, also can provide reference for other users that will cooperate.Social data is carried out
Parametrization, as the social parameter of each user, social parameter can embody the intimate degree between user.Joined based on social activity
Number can more comprehensively parameterize " production, teaching & research with " member, reinforce the precision recommended.
(4) relation data
Master data, dynamic data and social data based on user, excavate the relationship between user, signified herein
Relationship had both included the relationship of same type user, such as the relationship between expert and expert, also contained the pass of different type user
System, such as the relationship of expert and enterprise.
Such as the achievement in " Zhang San " master data contains A paper, the first authors of " Zhang San " as A paper；Meanwhile
Achievement in " Li Si " master data also contains A paper, second author of " Li Si " as A paper, at this moment by A paper this
A medium is by " Zhang San " and " Li Si " opening relationships.
Achievement contains B project for example in " Li Ming " master data again, meanwhile, achievement also includes in " Wang Hong " master data
B project, but B project is identified as failure, failure cause is " Li Si " promise breaking, at this moment by B project this medium by " Lee
It is bright " and " Wang Hong " opening relationships.
The member relation excavated provides reference when both can carry out project cooperation for user, also can be for the present invention below
Recommending module more accurate data supporting is provided, to realize more accurate recommendation.
(5) search/browse data
The data that user searches for or browsed, can embody the recent point of interest of user.
2. interesting data generation module 102, for generating the interested data of user according to production, teaching & research data network.
Production, teaching & research data network is by the master data of all users, dynamic data, social data, relation data and searches
Rope/browsing data collectively constitute, and the interested category attribute of user are generated by " search/browse data ", later according to these
Categorical data, with the possible interested data of the user are found in data network, forms recommendation results in production, teaching & research.
For example, A expert issued personnel demand relevant to medical artificial intelligence in the recent period, meanwhile, also browsed it is many with
Relevant team, medical artificial intelligence and enterprise, at this moment can generate the category attribute of " medical artificial intelligence ", in " production, teaching & research use "
Attribute and relation data network find with " medical artificial intelligence " relevant enterprise, team, the talent, expert etc. " production, teaching & research use " at
Member, usually will be associated with strong data arrangement in front with A expert, and forming A expert may interested data.
For another example the B team in certain enterprise, the content of recent research is related with " quantum calculation ", and master data
In brief introduction, achievement most of be all that " quantum calculation " is relevant, the content of B team regular job has also browsed a large amount of " amount
Son calculates " expert, it at this moment can be inferred that B team is possible to want recruitment expert or cooperate with " quantum calculation " domain expert,
" quantum calculation " and " expert " category attribute are generated, it is special with the correlation for finding quantum calculation field in data network in production, teaching & research
Family is handled (sequence or screening etc.) to recommendation results, and forming B team may interested data.
3. recommendation results pushing module 103, for recommendation results to be pushed to user.
The push mode of recommendation results is divided into two kinds, the first is that user actively searches for, by search key and production, teaching & research
Be combined with data network, by user may more interested data be placed on front, finally will search (recommendations) result push
To user；Second is that user passively receives, and according to the search/browse data of user, finds use in " production, teaching & research with " network
Family may interested data by these data-pushings to user be in the client of corresponding user in some way
It is existing.
Embodiment 2
Specifically, the present invention describes a kind of production, teaching & research recommended method, as shown in Figure 3, comprising:
S1, production is constructed by the master data of user, dynamic data, social data, relation data and search/browse data
Grind uses data network.
It is as shown in Figure 2 that production, teaching & research data network constitutes figure, comprising:
(1) master data
Master data includes: essential information, ability etc., such as the master data of expert may include: name, work shoe
It goes through, research topic etc., master data is stored in the data network of " production, teaching & research use " as independent node.
(2) dynamic data
Dynamic data refers to achievement, project demands, personnel demand, credit requirement, the match of participation and meeting of publication etc.,
These dynamic datas can embody the information such as demand and the ability of the users such as expert, team.
(3) social data
The socially relevant data such as plusing good friend is had in social operating process, gives a mark, thumb up, paying close attention to, collecting, in addition to this,
System evaluation can be carried out to partner after user cooperates, evaluation content may include that efficiency is high/low, it is difficult/easy etc. to link up, and comment
Valence content had both been used as a part of social data, also can provide reference for other users that will cooperate.Social data is carried out
Parametrization, as the social parameter of each user, social parameter can embody the intimate degree between user.Joined based on social activity
Number can more comprehensively parameterize " production, teaching & research with " member, reinforce the precision recommended.
(4) relation data
Master data, dynamic data and social data based on user, excavate the relationship between user, signified herein
Relationship had both included the relationship of same type user, such as the relationship between expert and expert, also contained the pass of different type user
System, such as the relationship of expert and enterprise.
Such as the achievement in " Zhang San " master data contains A paper, the first authors of " Zhang San " as A paper；Meanwhile
Achievement in " Li Si " master data also contains A paper, second author of " Li Si " as A paper, at this moment by A paper this
A medium is by " Zhang San " and " Li Si " opening relationships.
Achievement contains B project for example in " Li Ming " master data again, meanwhile, achievement also includes in " Wang Hong " master data
B project, but B project is identified as failure, failure cause is " Li Si " promise breaking, at this moment by B project this medium by " Lee
It is bright " and " Wang Hong " opening relationships.
The member relation excavated provides reference when both can carry out project cooperation for user, also can be for the present invention below
Recommending module more accurate data supporting is provided, to realize more accurate recommendation.
(5) search/browse data
The data that user searches for or browsed, can embody the recent point of interest of user.
S2, the interested category attribute of user is generated by search/browse data, then according to the master data, dynamic
State data, social data, relation data the production, teaching & research with searched in data network the user may interested data, shape
At recommendation results.
For example, A expert issued personnel demand relevant to medical artificial intelligence in the recent period, meanwhile, also browsed it is many with
Relevant team, medical artificial intelligence and enterprise, at this moment can generate the category attribute of " medical artificial intelligence ", in " production, teaching & research use "
Attribute and relation data network find with " medical artificial intelligence " relevant enterprise, team, the talent, expert etc. " production, teaching & research use " at
Member, usually will be associated with strong data arrangement in front with A expert, and forming A expert may interested data.
For another example the B team in certain enterprise, the content of recent research is related with " quantum calculation ", and master data
In brief introduction, achievement most of be all that " quantum calculation " is relevant, the content of B team regular job has also browsed a large amount of " amount
Son calculates " expert, it at this moment can be inferred that B team is possible to want recruitment expert or cooperate with " quantum calculation " domain expert,
" quantum calculation " and " expert " category attribute are generated, it is special with the correlation for finding quantum calculation field in data network in production, teaching & research
Family is handled (sequence or screening etc.) to recommendation results, and forming B team may interested data.
S3, recommendation results are pushed to user.
The push mode of recommendation results is divided into two kinds, the first is that user actively searches for, by search key and production, teaching & research
Be combined with data network, by user may more interested data be placed on front, finally will search (recommendations) result push
To user；Second is that user passively receives, and according to the search/browse data of user, finds use in " production, teaching & research with " network
Family may interested data by these data-pushings to user be in the client of corresponding user in some way
It is existing.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of the claim
Subject to enclosing.
Claims (9)
1. a kind of production, teaching & research recommender system characterized by comprising
Production, teaching & research constructs module with data network, for passing through the master data of user, dynamic data, social data, relationship number
Production, teaching & research data network is constructed according to search/browse data；
Interesting data generation module, for generating the interested category attribute of user by search/browse data, then according to institute
Stating master data, dynamic data, social data, relation data may be felt in the production, teaching & research with the user is searched in data network
The data of interest form recommendation results；
Recommendation results pushing module, for the recommendation results to be pushed to the user.
2. a kind of production, teaching & research recommender system according to claim 1, which is characterized in that
The master data includes: essential information, ability etc.；The dynamic data includes the achievement of publication, project demands, personnel
Demand, credit requirement, the match of participation and meeting etc.；The social data include plusing good friend in social operating process, marking,
Thumb up, pay close attention to, collecting data etc., and the data that partner is evaluated after user cooperates；The relation data is
The relation data between user excavated based on above-mentioned master data, dynamic data and social data.
3. a kind of production, teaching & research recommender system according to claim 2, which is characterized in that
The push mode of the recommendation results are as follows: when user actively searches for, by search key and production, teaching & research data network
It is combined, the possible interested data of user is placed on front, recommendation results are pushed to user.
4. a kind of production, teaching & research recommender system according to claim 3, which is characterized in that
The push mode of the recommendation results are as follows: when user passively receives, according to the search/browse data of user, learned producing
It grinds with the possible interested data of user are searched in network, recommendation results is pushed to user.
5. a kind of production, teaching & research recommended method characterized by comprising
Production, teaching & research is constructed by the master data of user, dynamic data, social data, relation data and search/browse data to use
Data network；
By search/browse data generate the interested category attribute of user, then according to the master data, dynamic data,
Social data, relation data, with the possible interested data of the user are searched in data network, form and recommend in the production, teaching & research
As a result；
The recommendation results are pushed to the user.
6. a kind of production, teaching & research recommended method according to claim 5, which is characterized in that
The master data includes: essential information, ability etc.；The dynamic data includes the achievement of publication, project demands, personnel
Demand, credit requirement, the match of participation and meeting etc.；The social data include plusing good friend in social operating process, marking,
Thumb up, pay close attention to, collecting data etc., and the data that partner is evaluated after user cooperates；The relation data is
The relation data between user excavated based on above-mentioned master data, dynamic data and social data.
7. a kind of production, teaching & research recommended method according to claim 6, which is characterized in that
The push mode of the recommendation results are as follows: when user actively searches for, by search key and production, teaching & research data network
It is combined, the possible interested data of user is placed on front, recommendation results are pushed to user.
8. a kind of production, teaching & research recommended method according to claim 7, which is characterized in that
The push mode of the recommendation results are as follows: when user passively receives, according to the search/browse data of user, learned producing
It grinds with the possible interested data of user are searched in network, recommendation results is pushed to user.
9. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the calculating
The production, teaching & research recommended method as described in any one of claim 5-8 is realized when machine program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910490657.3A CN110377815A (en) | 2019-06-06 | 2019-06-06 | A kind of production, teaching & research recommender system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910490657.3A CN110377815A (en) | 2019-06-06 | 2019-06-06 | A kind of production, teaching & research recommender system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110377815A true CN110377815A (en) | 2019-10-25 |
Family
ID=68249913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910490657.3A Pending CN110377815A (en) | 2019-06-06 | 2019-06-06 | A kind of production, teaching & research recommender system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110377815A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062732A (en) * | 2022-08-18 | 2022-09-16 | 睿驰(深圳)智能有限公司 | Resource sharing cooperation recommendation method and system based on big data user tag information |
| CN117131288A (en) * | 2023-09-07 | 2023-11-28 | 苏州椿之硕信息科技有限公司 | Recommendation system and method for obstetric and academic research |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075942A (en) * | 2007-06-22 | 2007-11-21 | 清华大学 | Method and system for processing social network expert information based on expert value progation algorithm |
| US20130031173A1 (en) * | 2011-07-30 | 2013-01-31 | Huawei Technologies Co., Ltd. | Information recommendation method, recommendation engine, network system |
| CN107608986A (en) * | 2016-07-12 | 2018-01-19 | 上海视畅信息科技有限公司 | A kind of personalized recommendation method based on social networks |
| CN107730430A (en) * | 2017-11-15 | 2018-02-23 | 重庆衡大科技有限公司 | Production, teaching ＆ research public service system based on big data |
| CN109308315A (en) * | 2018-10-19 | 2019-02-05 | 南京理工大学 | A kind of collaborative recommendation method based on specialist field similarity and incidence relation |
-
2019
- 2019-06-06 CN CN201910490657.3A patent/CN110377815A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075942A (en) * | 2007-06-22 | 2007-11-21 | 清华大学 | Method and system for processing social network expert information based on expert value progation algorithm |
| US20130031173A1 (en) * | 2011-07-30 | 2013-01-31 | Huawei Technologies Co., Ltd. | Information recommendation method, recommendation engine, network system |
| CN107608986A (en) * | 2016-07-12 | 2018-01-19 | 上海视畅信息科技有限公司 | A kind of personalized recommendation method based on social networks |
| CN107730430A (en) * | 2017-11-15 | 2018-02-23 | 重庆衡大科技有限公司 | Production, teaching ＆ research public service system based on big data |
| CN109308315A (en) * | 2018-10-19 | 2019-02-05 | 南京理工大学 | A kind of collaborative recommendation method based on specialist field similarity and incidence relation |
Non-Patent Citations (1)
| Title |
|---|
| 赵娟等: "社会网络分析技术在科研信息化中的应用", 《科研信息化技术与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062732A (en) * | 2022-08-18 | 2022-09-16 | 睿驰(深圳)智能有限公司 | Resource sharing cooperation recommendation method and system based on big data user tag information |
| CN117131288A (en) * | 2023-09-07 | 2023-11-28 | 苏州椿之硕信息科技有限公司 | Recommendation system and method for obstetric and academic research |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huyen | Designing machine learning systems | |
| Mishra et al. | Vision, applications and future challenges of Internet of Things: A bibliometric study of the recent literature | |
| CN107679661B (en) | Personalized tour route planning method based on knowledge graph | |
| White et al. | Exploratory search: Beyond the query-response paradigm | |
| CN101751448B (en) | Commendation method of personalized resource information based on scene information | |
| He et al. | A spatial-temporal topic model for the semantic annotation of POIs in LBSNs | |
| US9141966B2 (en) | Opinion aggregation system | |
| TW201514735A (en) | System and method for providing targeted applications within a search results page | |
| CN103620605A (en) | Organizing search history into collections | |
| TW200951734A (en) | Social aspects of content aggregation, syndication, sharing, and updating | |
| CN106203761A (en) | Extract and manifest the user job attribute from data source | |
| Xue et al. | Social media user behavior analysis applied to the fashion and apparel industry in the big data era | |
| CN104750771A (en) | Method and system for contextual data analysis using domain information | |
| CN105786897B (en) | For providing the context aware body constructing method for paying close attention to information of the user based on context aware | |
| Chen et al. | A big data and time series analysis technology-based multi-agent system for smart tourism | |
| CN110059230A (en) | For improving the Generalized Linear Mixed Models of search | |
| Cutler | ChatGPT and search engine optimisation: the future is here | |
| CN110377815A (en) | A kind of production, teaching & research recommender system and method | |
| Maree et al. | Multi-modality search and recommendation on Palestinian cultural heritage based on the holy-land ontology and extrinsic semantic resources | |
| Wright | Seeing triple: Archaeology, field drawing and the semantic web | |
| Atta | The effect of usability and information quality on decision support information system (DSS) | |
| Ohsawa et al. | Data mining for design and marketing | |
| Tossavainen et al. | Implementing a system enabling open innovation by sharing public goals based on linked open data | |
| Abrahams | Tourism information systems integration and utilization within the semantic web | |
| Braun et al. | Ontology maturing with lightweight collaborative ontology editing tools |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191025 |