CN117131288A - Recommendation system and method for obstetric and academic research - Google Patents
Recommendation system and method for obstetric and academic research Download PDFInfo
- Publication number
- CN117131288A CN117131288A CN202311147104.0A CN202311147104A CN117131288A CN 117131288 A CN117131288 A CN 117131288A CN 202311147104 A CN202311147104 A CN 202311147104A CN 117131288 A CN117131288 A CN 117131288A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- recommendation
- learner
- research
- 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
- 238000011160 research Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000001914 filtration Methods 0.000 claims abstract description 26
- 230000000007 visual effect Effects 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000013500 data storage Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims description 33
- 238000010276 construction Methods 0.000 claims description 6
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002452 interceptive effect Effects 0.000 claims description 3
- 238000012827 research and development Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application discloses a recommendation system and a recommendation method for obstetric and academic research, and relates to the technical field of obstetric and academic research, wherein the system comprises the following modules; the data acquisition module is used for carrying out data retrieval on the input related keywords, establishing a research resource database, and constructing a knowledge graph based on the database to form a visual graph module; a data processing module; a recommendation engine module; a display module; a data storage module; the technical key points are as follows: by adopting the mutual coordination of each module in the recommendation system, in the process of collecting and processing data, the timely processing of error reporting data can be completed through the switching operation of the primary and secondary data systems, meanwhile, the normal operation of the working process can be ensured, and then the corresponding learner and the corresponding interest model can be effectively matched by utilizing the configured filtering training model and combining a big data algorithm, so that the recommendation work of the content can be effectively and accurately completed according to different matching degrees.
Description
Technical Field
The application relates to the technical field of obstetric and academic research, in particular to a recommendation system and a recommendation method for obstetric and academic research.
Background
The obstetric and research is a cooperative system engineering, and literally means the system cooperation of production, study, scientific research and practical application; in the aspect of school, the cooperative education for obstetrics and students fully utilizes various different teaching environments and teaching resources such as schools, enterprises, scientific research institutions and the like and respective advantages in talent culture, and organically combines school education mainly based on classroom teaching knowledge with production and scientific research practice mainly based on practical experience and practical capability; the 'use' mainly refers to 'application' and 'user', wherein the 'use' is the starting point and the foothold of the technical innovation, and the user directly participates in the obstetric research and development work, so that the blindness of the technical innovation can be reduced, the period from research and development to market entering of a new product is shortened, and the risk and cost of the technical innovation can be effectively reduced.
In the chinese application of the application publication No. CN110377815a, a recommendation system for obstetric and academic research is disclosed, comprising: the data network construction module for obstetric and academic research is used for constructing a data network for obstetric and academic research through basic data, dynamic data, social data, relation data and search/browse data of a user; the interest data generation module is used for generating category attributes of interest of a user through searching/browsing data, and searching data possibly of interest of the user in the data network for obstetrics and research according to the basic data, the dynamic data, the social data and the relationship data to form a recommendation result; and the recommendation result pushing module is used for pushing the recommendation result to the user.
In the above application, the interest data generating module of the user is generated by browsing or searching data for the user (i.e. learner), the searched and browsed content is not completely related to the interest of the user, and the content for irrelevant obstetrics and research is recorded, so that the control of the recommended content is unreasonable and not comprehensive, and when the system is used, if some data recommendation results are wrong, the recommending efficiency of the system is easily reduced, thereby affecting the overall working efficiency.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the application provides a recommendation system and a recommendation method for obstetrics and research, wherein the recommendation system is adopted to mutually coordinate each module, in the process of collecting and processing data, the timely processing of error reporting data can be completed through the switching operation of a primary data system and a secondary data system, meanwhile, the normal operation of the working process can be ensured, and then the corresponding learner and the corresponding interest model can be effectively matched by utilizing a configured filtering training model and combining a big data algorithm, so that the recommendation work of the content can be effectively and accurately completed according to different matching degrees, and the problems in the background technology are solved.
(II) technical scheme
In order to achieve the above purpose, the application is realized by the following technical scheme:
a recommendation system for obstetric and academic research comprises the following modules; the data acquisition module is used for carrying out data retrieval on the input related keywords, establishing a research resource database, and constructing a knowledge graph based on the database to form a visual graph module;
the data processing module is used for dividing the acquired data as objects according to a pre-built data type outline, completing classification processing of the data types, establishing interest models aiming at different keywords input in the data acquisition module, and synchronously carrying out the whole data processing process in a primary data system and a secondary data system;
when the data error reporting condition occurs, the switching of the primary and secondary data systems can be completed, and an early warning is sent out;
the recommendation engine module is used for carrying out similarity proportioning calculation on data resources and learners in the interest model by utilizing a big data recommendation algorithm in the configured filtering training model, judging the recommended content according to the percentage of similarity, wherein the big data recommendation algorithm adopts a collaborative filtering recommendation algorithm and comprises an online collaborative filtering part and an offline filtering part; the online collaboration is to find out the articles possibly liked by the user through online data, and the offline filtering is to filter out some data which is not worth recommending;
the display module is used for displaying the data in the form of a map module after the data recommendation is completed, analyzing the habit of a learner by utilizing big data, completing the data display in the form of a table or a bar graph, and finally realizing the recommendation operation of the data resource;
and the data storage module is used for carrying out step-type storage on the node data of each module in the whole system.
Further, in the data acquisition module, related keywords are obtained by analyzing the field of the learner by the AI module and are input, if the learners with different production directions are involved, the corresponding data retrieval directions are different, and the summary of related words and adjacent words in the keywords are all in the direction of data retrieval;
the data in the study resource database comprises data summarization corresponding to learners with different study directions, and the specific steps of knowledge graph construction are carried out according to the database formed after the data summarization:
firstly, carrying out preliminary analysis on each basic data in a database to obtain corresponding entities, attributes and categories;
then extracting the attribute of each basic data and corresponding the attribute with the knowledge graph;
finally, an interactive map associated with a learner is obtained, secondary coding is carried out on the basis of an original study resource database, the extracted basic data are marked, and a further visual map module is established and obtained.
Further, in the data processing module, if the visual map module has made a marking process for the learner, the classifying process may be divided according to the marking content; if the marking processing is not performed, dividing according to the outline of the data type;
the establishment of the interest model is to use an analysis unit, combine the running state of the system and the functional requirement, complete the secondary analysis of the classified data, enter an execution unit after the analysis is completed, the execution unit is carried out in a primary and secondary data system, and complete the buffer storage processing before entering a recommendation engine module to carry out data recommendation;
and (3) obtaining that the data has the error reporting problem due to the analysis of the analysis unit during the data caching period, stopping working of the parent system, sending the data with the error reporting problem to the analysis unit of the subsystem again for analysis, and if the error reporting problem still exists, switching n times, wherein n is more than or equal to 2, until the error reporting is stopped.
Further, in the recommendation engine module, the configured filtering training model needs to collect information of a corresponding learner when in use, and the archive information of the learner is called, wherein the archive information at least comprises age, academic, profession, currently engaged position of the learner and specific working content under the position of the learner, and the actual keywords corresponding to the learner are extracted;
the filtering training model compares the similarity between the actual keywords and different interest models to obtain specific data of the actual keywords and the proportion of the actual keywords in the interest models;
and under the analysis of the built-in judging unit of the filtering training model, obtaining a group of interest models with highest similarity, and if the matching similarity is higher than 80%, completing the recommendation of all contents under the interest models.
If the learner is in the state that the number of positions is more than or equal to 2, namely the learner has more positions, so that the work content is wide, the proportion of the learner to a group of interest models with highest similarity in the filtering training models is lower than 60%, the training models with the similarity not lower than 20% are summarized, and a visual map module is built again for the learner to select according to the current requirements so as to complete passive recommendation;
if the proportion of a group of interest models with highest similarity is between 60% and 80% in the filtering training models, the rest training models with similarity not lower than 20% are summarized according to the equal proportion, and a visual map module is built again for a learner to select according to the current requirement.
The recommended method for obstetric and academic research comprises the following specific steps:
inputting related keywords for data retrieval, establishing a research resource database, and constructing a knowledge graph based on the database to form a visual graph module;
dividing the acquired data as objects according to a pre-built data type outline, completing classification processing of the data types, establishing interest models aiming at different keywords input in a data acquisition module to obtain a plurality of groups of line interest models, and synchronously carrying out the whole data processing process in a primary data system and a secondary data system; when the data error reporting occurs, the switching of the primary and secondary data systems can be completed, and an early warning is sent out.
Performing similarity proportioning calculation on data resources and learners in the interest model by using a big data recommendation algorithm in the configured filtering training model, and judging recommended content according to the percentage of similarity;
after data recommendation is completed, the data is displayed in a map module mode, habits of learners are analyzed by utilizing big data, data display is completed in a form of a table or a bar chart, and finally recommendation operation of data resources is achieved.
(III) beneficial effects
The application provides a recommendation system and a recommendation method for obstetric and academic research. The beneficial effects are as follows:
1. by adopting the mutual coordination of each module in the recommendation system, in the process of collecting and processing data, the timely processing of error reporting data can be completed through the switching operation of the primary and secondary data systems, and meanwhile, the normal operation of the working process can be ensured, even if the error reporting problem cannot be solved in the first time, the switching analysis can be completed through the analysis unit established in the interest model until the problem is solved, and the problem of reduced working efficiency caused by processing the error reporting data is avoided;
2. the matched filter training model is utilized, and the big data algorithm is combined, so that the matching of the corresponding learner and the corresponding interest model can be effectively completed, and the recommendation of the content can be effectively and accurately completed according to different matching degrees;
3. if the work content of the learner is single, the recommendation of all the contents under the interest model with the highest similarity can be completed according to the requirement, and the content recommendation in equal proportion can be performed according to the value of the similarity; if the learner is in a state of more positions and wide working content, the visual map module can be built again for the learner to select according to the current requirements, so that passive recommendation is completed, on one hand, the required recommendation mode can be provided for different learners, and on the other hand, the problem that the traditional recommendation content is not comprehensive is solved.
Drawings
FIG. 1 is a schematic diagram of an overall modular structure of a recommendation system for obstetric and research in accordance with the present application;
FIG. 2 is a flow chart of the proposed system for obstetric and research in a state of use.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Examples:
referring to fig. 1-2, the present application provides a recommendation method for obstetric and academic research,
step one, performing data retrieval by using a data acquisition module and the input related keywords, establishing an research resource database, and constructing a knowledge graph based on the database to form a visual graph module.
The first step includes the following:
the specific key words of the input are as follows: the related keywords are obtained by analyzing the field of the learner by the AI module and are input, if the learners with different production directions are involved, the corresponding data retrieval directions are different, and the collection of the related keywords and the adjacent words thereof are all in the direction of data retrieval;
the data in the study resource database comprises data summarization corresponding to learners with different study directions, and the specific steps of knowledge graph construction are carried out according to the database formed after the data summarization:
s101, performing preliminary analysis on each basic data in a database to obtain corresponding entities, attributes and categories;
s102, extracting the attribute of each basic data, and corresponding the attribute to the knowledge graph;
s103, obtaining an interactive map associated with a learner, performing secondary coding on the basis of an original study resource database, marking the extracted basic data, and establishing and obtaining a further visual map module.
In use, the contents of steps 101 and 102 are combined:
in the process of data acquisition, the formation of a database and the construction of a knowledge graph are carried out, so that the analysis and preliminary classification processing of the data attribute related information can be ensured, and the relation between the data contents is clearer through the construction of a visual graph module, thereby being convenient for system research and development personnel to effectively call and check the data.
Dividing acquired data serving as objects according to a pre-built data type outline by using a data processing module, completing classification processing of data types, establishing interest models aiming at different keywords input in the data acquisition module, and synchronously carrying out the whole data processing process in a primary-secondary data system;
when the data error reporting condition occurs, the switching of the primary and secondary data systems can be completed, and an early warning is sent out;
the second step comprises the following steps:
s201, if the visual map module has made marking processing for learners, the classifying processing process can be divided according to marking content; if the marking processing is not performed, dividing according to the outline of the data type;
s202, establishing an interest model, namely, needing to use an analysis unit, combining the running state of the system and the function requirement, finishing secondary analysis of the classified data, entering an execution unit after the analysis is finished, wherein the execution unit is carried out in a primary-secondary data system, and finishing caching before entering a recommendation engine module for data recommendation;
the primary and secondary data systems are two identical and mutually parallel systems, can synchronously process data, and send the data to another normal system in time when any system fails; the following description is needed: the setting of the buffer processing is to avoid that the data with error reporting is directly transmitted to the next link, and the data is buffered and analyzed by the analysis unit, so that the missing rate of the error reporting data is greatly reduced.
S203, obtaining that the data has the problem of error reporting due to analysis by the analysis unit during the data caching period, stopping working of the parent system, sending the data with the problem of error reporting to the analysis unit of the subsystem again for analysis, and if the problem of error reporting still exists, switching for n times, wherein n is more than or equal to 2, until error reporting is stopped.
In use, the contents of steps 201 and 203 are combined:
in the process of collecting and processing the data, the modules in the recommendation system are mutually matched, the timely processing of the error reporting data can be completed through the switching operation of the primary and secondary data systems, meanwhile, the normal operation of the working process can be ensured, even if the error reporting problem cannot be solved in the first time, the switching type analysis can be completed through the analysis unit established in the interest model until the problem is solved, and the problem of reduced working efficiency caused by processing the error reporting data is avoided.
Step three, using a recommendation engine module, performing in a configured filtering training model, performing similarity proportioning calculation on data resources and learners in the interest model by using a big data recommendation algorithm, and judging recommended content according to the percentage of similarity;
the third step comprises the following steps:
s301, in the recommendation engine module, the configured filtering training model needs to collect information of a corresponding learner when in use, and the archive information of the learner is called, wherein the archive information at least comprises age, academic, profession, currently engaged position of the learner and specific working content under the position of the learner, and actual keywords corresponding to the learner are extracted;
s302, performing similarity comparison on the actual keywords and different interest models by using a filtering training model to obtain concrete data of the actual keywords and the proportion of the actual keywords in the interest models;
s303, under the analysis of a built-in judging unit of the filtering training model, obtaining a group of interest models with highest similarity, if the matching similarity is higher than 80%, completing the recommendation of all contents under the interest models;
if a group of interest models with highest similarity exist in the filtering training models, the proportion of the interest models is between 60% and 80%, and the rest training models with similarity not lower than 20% are summarized according to the equal proportion, and a visualized map module is built again for a learner to select according to the current requirement
If the learner is in a state of more positions and wide working content, the proportion of the learner to a group of interest models with highest similarity in the filtering training models is lower than 60%, the training models with the similarity not lower than 20% are summarized, and the learner selects according to the current requirements by establishing a visual map module again, so that passive recommendation is completed.
In use, the contents of steps 301 and 303 are combined:
the matched filter training model is utilized, and the big data algorithm is combined, so that the matching of the corresponding learner and the corresponding interest model can be effectively completed, and the recommendation of the content can be effectively and accurately completed according to different matching degrees;
if the work content of the learner is single, the recommendation of all the contents under the interest model with the highest similarity can be completed according to the requirement, and the content recommendation in equal proportion can be performed according to the value of the similarity; if the learner is in a state of more positions and wide working content, the visual map module can be built again for the learner to select according to the current requirements, so that passive recommendation is completed, on one hand, the required recommendation mode can be provided for different learners, and on the other hand, the problem that the traditional recommendation content is not comprehensive is solved.
Step four, using a display module to display in a pattern module mode after data recommendation is completed, analyzing habits of learners by using big data, completing data display in a form of a table or a bar chart, and finally realizing recommendation operation of data resources;
the fourth step includes the following:
s401, performing public display in a map module mode of the step after data recommendation is completed;
s402, analyzing habit of learner using big data, for example: the information retrieval, searching and browsing data of the learner in the working period are detected, the regular browsing is carried out, the working content of the corresponding learner is obtained after the comprehensive big data analysis, and the working content is combined with the operation of the interest model in the steps, so that the mutual information verification effect can be achieved;
s403, selecting to display the recommended data in a form of a table according to the habit of the learner.
The data storage module is used in the period from the first step to the fourth step, and is used for carrying out step-by-step storage on node data of each module in the whole system, wherein the node is a demarcation point between each module, so that the data in each module can be respectively stored, and the condition that the data are emptied due to mutual influence of each module caused by the integral system fault caused by the damage of a certain module is avoided;
specifically, the storage mode used by the data storage module comprises cloud storage and fixed storage, wherein a tool used for the fixed storage comprises any one or a combination of a USB flash disk and a mobile hard disk, and particularly a hard disk with larger capacity can be selected according to the requirement, and the hard disk and the cloud storage can be combined for use.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application.
Claims (10)
1. A recommendation system for obstetric and research, which is characterized in that: the system comprises the following modules;
the data acquisition module is used for carrying out data retrieval on the input related keywords, establishing a research resource database, and constructing a knowledge graph based on the database to form a visual graph module;
the data processing module is used for dividing the acquired data as objects according to a pre-built data type outline, completing classification processing of the data types, establishing interest models aiming at different keywords input in the data acquisition module, and synchronously carrying out the whole data processing process in a primary data system and a secondary data system;
when the data error reporting condition occurs, the switching of the primary and secondary data systems can be completed, and an early warning is sent out;
the recommendation engine module is used for carrying out similarity proportioning calculation on data resources and learners in the interest model by utilizing a big data recommendation algorithm in the configured filtering training model, and judging the recommended content according to the percentage of the similarity;
and the display module is used for displaying the data in the form of a map module after the data recommendation is completed, analyzing the habit of a learner by utilizing big data, completing the data display in the form of a table or a bar graph, and finally realizing the recommendation operation of the data resource.
2. A recommended system for obstetric and research as claimed in claim 1, wherein: in the data acquisition module, related keywords are obtained by analyzing the field of the learner by the AI module and are input, if the learners with different production directions are involved, the corresponding data retrieval directions are different, and the summary of the related keywords and adjacent words in the keywords is in the direction of data retrieval.
3. A recommended system for obstetric and research as claimed in claim 2, wherein: the data in the study resource database comprises data summarization corresponding to learners with different directions of production, and the specific steps of knowledge graph construction are as follows according to the database formed after the data summarization:
firstly, carrying out preliminary analysis on each basic data in a database to obtain corresponding entities, attributes and categories;
then extracting the attribute of each basic data and corresponding the attribute with the knowledge graph;
finally, an interactive map associated with a learner is obtained, secondary coding is carried out on the basis of an original study resource database, the extracted basic data are marked, and a further visual map module is established and obtained.
4. A recommended system for obstetric and research as claimed in claim 3, wherein: in the data processing module, if the visual map module has made marking processing for the learner, the classifying processing process can be divided according to marking content; if the marking process is not performed, the data type outline is divided.
5. The recommended system for obstetric and research as defined in claim 4, wherein: the establishment of the interest model is to use an analysis unit, combine the running state of the system and the functional requirement, complete the secondary analysis of the classified data, enter an execution unit after the analysis is completed, the execution unit is carried out in a primary and secondary data system, and complete the buffer storage processing before entering a recommendation engine module to carry out data recommendation;
and (3) obtaining that the data has the error reporting problem due to the analysis of the analysis unit during the data caching period, stopping working of the parent system, sending the data with the error reporting problem to the analysis unit of the subsystem again for analysis, and if the error reporting problem still exists, switching n times, wherein n is more than or equal to 2, until the error reporting is stopped.
6. A recommended system for obstetric and research as claimed in claim 1, wherein: in the recommendation engine module, the configured filtering training model needs to collect information of a corresponding learner when in use, and the actual keywords corresponding to the corresponding learner are extracted by calling the file information of the learner;
the filtering training model compares the similarity between the actual keywords and different interest models to obtain specific data of the actual keywords and the proportion of the actual keywords in the interest models;
and under the analysis of the built-in judging unit of the filtering training model, obtaining a group of interest models with highest similarity, and if the matching similarity is higher than 80%, completing the recommendation of all contents under the interest models.
7. The recommended system for obstetric and research as defined in claim 6, wherein: the archive information at least comprises the age, the academic, the specialty of the learner, the position currently engaged in and the specific work content under the position.
8. The recommended system for obstetric and research as defined in claim 6, wherein:
when the learner is in a state that the number of positions is more than or equal to 2, matching the learner with a group of interest models with highest similarity in the filtering type training models is lower than 60%, summarizing the training models with similarity not lower than 20%, and selecting the learner according to current requirements by establishing a visual map module again to complete passive recommendation;
if the proportion of a group of interest models with highest similarity is between 60% and 80% in the filtering training models, the rest training models with similarity not lower than 20% are summarized according to the equal proportion, and a visual map module is built again for a learner to select according to the current requirement.
9. A recommended system for obstetric and research as claimed in claim 1, wherein: the system also comprises a data storage module which is used for carrying out step-type storage on the node data of each module in the whole system.
10. A recommendation method for obstetric and academic research is characterized in that: the method comprises the following steps:
inputting related keywords for data retrieval, establishing a research resource database, and constructing a knowledge graph based on the database to form a visual graph module;
dividing the acquired data as objects according to a pre-built data type outline, completing classification processing of the data types, establishing interest models aiming at different keywords input in a data acquisition module to obtain a plurality of groups of line interest models, and synchronously carrying out the whole data processing process in a primary data system and a secondary data system; when the data error reporting condition occurs, the switching of the primary and secondary data systems can be completed, and an early warning is sent out;
performing similarity proportioning calculation on data resources and learners in the interest model by using a big data recommendation algorithm in the configured filtering training model, and judging recommended content according to the percentage of similarity;
after data recommendation is completed, the data is displayed in a map module mode, habits of learners are analyzed by utilizing big data, data display is completed in a form of a table or a bar chart, and finally recommendation operation of data resources is achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147104.0A CN117131288A (en) | 2023-09-07 | 2023-09-07 | Recommendation system and method for obstetric and academic research |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311147104.0A CN117131288A (en) | 2023-09-07 | 2023-09-07 | Recommendation system and method for obstetric and academic research |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117131288A true CN117131288A (en) | 2023-11-28 |
Family
ID=88859808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311147104.0A Pending CN117131288A (en) | 2023-09-07 | 2023-09-07 | Recommendation system and method for obstetric and academic research |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117131288A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085803A (en) * | 2017-03-31 | 2017-08-22 | 弘成科技发展有限公司 | The individualized teaching resource recommendation system of knowledge based collection of illustrative plates and capability comparison |
| CN110188208A (en) * | 2019-06-04 | 2019-08-30 | 河海大学 | A kind of the information resources inquiry recommended method and system of knowledge based map |
| CN110377815A (en) * | 2019-06-06 | 2019-10-25 | 创易汇(北京)科技有限公司 | A kind of production, teaching & research recommender system and method |
| CN111813918A (en) * | 2020-06-18 | 2020-10-23 | 国网上海市电力公司 | Scientific and technological resource recommendation processing method and device |
| WO2021033208A1 (en) * | 2019-08-21 | 2021-02-25 | Heuristix Digital Technologies Private Limited | Recommendation system for learning and method thereof |
| CN114065040A (en) * | 2021-11-18 | 2022-02-18 | 扬州大学 | Individual learning path and learning resource recommendation method based on discipline knowledge graph |
-
2023
- 2023-09-07 CN CN202311147104.0A patent/CN117131288A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085803A (en) * | 2017-03-31 | 2017-08-22 | 弘成科技发展有限公司 | The individualized teaching resource recommendation system of knowledge based collection of illustrative plates and capability comparison |
| CN110188208A (en) * | 2019-06-04 | 2019-08-30 | 河海大学 | A kind of the information resources inquiry recommended method and system of knowledge based map |
| CN110377815A (en) * | 2019-06-06 | 2019-10-25 | 创易汇(北京)科技有限公司 | A kind of production, teaching & research recommender system and method |
| WO2021033208A1 (en) * | 2019-08-21 | 2021-02-25 | Heuristix Digital Technologies Private Limited | Recommendation system for learning and method thereof |
| CN111813918A (en) * | 2020-06-18 | 2020-10-23 | 国网上海市电力公司 | Scientific and technological resource recommendation processing method and device |
| CN114065040A (en) * | 2021-11-18 | 2022-02-18 | 扬州大学 | Individual learning path and learning resource recommendation method based on discipline knowledge graph |
Non-Patent Citations (1)
| Title |
|---|
| 孙雨生等: "国内基于知识图谱的信息推荐研究进展", 情报理论与实践, vol. 42, no. 12, pages 163 - 169 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784721B (en) | Employment data analysis and data mining analysis platform system | |
| CN105518658A (en) | Apparatus, systems, and methods for grouping data records | |
| Daskalaki et al. | Instance matching benchmarks in the era of linked data | |
| CN116383198A (en) | Decision analysis method and system based on big data | |
| Dang et al. | MOOC-KG: A MOOC knowledge graph for cross-platform online learning resources | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| CN112596731B (en) | Programming teaching system and method integrating intelligent education | |
| CN111737364A (en) | Safe multi-party data fusion and federal sharing method, device, equipment and medium | |
| CN109584127B (en) | Teaching resource management method and system for experiment teaching | |
| CN110889069A (en) | Resource access platform based on web online learning | |
| CN109934631A (en) | Question and answer information processing method, device and computer equipment | |
| Moalla et al. | Data warehouse design from social media for opinion analysis: the case of Facebook and Twitter | |
| CN110389944B (en) | Metadata management system and method based on model | |
| US20200160359A1 (en) | User-experience development system | |
| CN117131288A (en) | Recommendation system and method for obstetric and academic research | |
| Veglis | Interactive Data Visualization | |
| Xu et al. | An application of big data learning analysis based on MOOC platform | |
| Ababneh et al. | Social media usage in education: big data perspective | |
| TWM625409U (en) | Platform for automatically collecting destination tourism planning and online evaluation information | |
| Hai-ling et al. | Big data technology applied to learning behavior evaluation system | |
| Lin | Application of Big Data Platform in Course of Java Language Programming. | |
| Sun et al. | Dynamic early warning system of College Students’ target course performance based on improved Apriori algorithm | |
| CN113868322B (en) | Semantic structure analysis method, device and equipment, virtualization system and medium | |
| Naito et al. | Supporting consecutive data exploration by visualizing Spatio-temporal Trend information | |
| Cai et al. | Reform of Smart Exhibition English Guiding from the Perspective of New Media based on Data Association Analysis Model |
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 |