CN110909248A - Teacher recommendation method and device - Google Patents
Teacher recommendation method and device Download PDFInfo
- Publication number
- CN110909248A CN110909248A CN201911225648.8A CN201911225648A CN110909248A CN 110909248 A CN110909248 A CN 110909248A CN 201911225648 A CN201911225648 A CN 201911225648A CN 110909248 A CN110909248 A CN 110909248A
- Authority
- CN
- China
- Prior art keywords
- teacher
- teachers
- student
- information
- students
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000010801 machine learning Methods 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims description 30
- 238000012545 processing Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000002372 labelling Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 abstract description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 239000013598 vector Substances 0.000 description 6
- 238000013499 data model Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a teacher recommendation method and device, relates to the technical field of machine learning, and particularly relates to the teacher recommendation method and device. The teacher recommendation method comprises the following steps: the method comprises the steps of obtaining feature information of students to construct corresponding student figures, wherein the feature information of the students comprises feature information of learning, social contact and difference of the students, training the student figures through a teaching feature rule model to obtain teacher features required by the students, and recommending teachers according to preset rules according to the teacher features. The invention can recommend proper teachers for students, and realize the teaching according to the material, thereby achieving the purpose of maximally utilizing the teacher resources.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a teacher recommendation method and device.
Background
In recent years, a large number of large training and education institutions have emerged in China, which establish subjects with different characteristics and are equipped with a large number of teachers to provide students with course training of various interests and hobbies and various subjects, such as koto teaching, mathematics teaching and the like.
In the prior art, when a family friend registers a certain subject training class for a child, the key factor for selecting the training class is to complete the matching of students and teachers based on teacher-student archive information and character test results.
However, in the prior art, teachers and students are matched only according to the file information and the character characteristics of the teachers and students, so that the purposes of teaching the students according to the characteristics and maximizing the utilization of teacher resources cannot be achieved.
Disclosure of Invention
In view of this, an object of the embodiments of the present invention is to provide a teacher recommendation method and device, which can recommend a suitable teacher to students, and implement the purpose of teaching according to the situation, so as to achieve the purpose of maximizing the utilization of teacher resources.
To achieve the above object, in a first aspect, a preferred embodiment of the present invention provides a teacher recommendation method, including:
acquiring feature information of students to construct corresponding student figures, wherein the feature information of the students comprises feature information of learning, social contact and difference of the students;
training the student portrait through a teaching characteristic rule model to obtain teacher characteristics required by the student;
and recommending the teacher according to the matching degree of the characteristics of the teacher and the preset teacher.
Further, before the step of obtaining feature information of the student to construct a corresponding student portrait, the method further comprises:
collecting sample data of a student portrait and a teacher portrait, and labeling the sample data;
and constructing a teaching characteristic rule model through machine learning according to the labeled sample data.
Further, a teacher is recommended according to the matching degree of the characteristics of the teacher and a preset teacher, and the method further comprises the following steps:
calculating the similarity between the characteristics of the teachers and each teacher through cosine similarity;
and recommending the teachers from high to low according to the ranking of the similarity.
Further, after calculating the similarity of the teacher feature to each teacher through the cosine similarity, the method further comprises the following steps:
if a plurality of teachers with the same similarity are determined, acquiring integral information of the plurality of teachers;
and recommending the teacher according to the high-low sequence of the point information.
Further, before obtaining the point information of a plurality of teachers, the method further comprises:
acquiring classification evaluation data and corresponding weight values of teachers;
and obtaining the integral information of each teacher according to the classification evaluation data and the weighted value and a preset integral calculation rule.
In a second aspect, an embodiment of the present invention further provides a teacher recommendation apparatus, including:
the acquisition module is used for acquiring feature information of students to construct corresponding student figures, wherein the feature information of the students comprises feature information of student learning, social contact and difference;
the processing module is used for carrying out semantic analysis and labeling processing on the student characteristic information acquired by the acquisition module;
the training module is used for training the student portrait constructed by the acquisition module through the teaching characteristic rule model to obtain teacher characteristics required by students;
and the matching module is used for recommending the teacher according to the matching degree of the teacher characteristics obtained by the training module and the preset teacher.
The acquisition module is further used for acquiring sample data of the student portrait and the teacher portrait before acquiring the feature information of the student to construct a corresponding student portrait;
the processing module is also used for marking the sample data;
the training module is also used for constructing a teaching characteristic rule model through machine learning according to the sample data marked by the processing module.
Further, the matching module is used for obtaining the teacher characteristic and recommending the teacher according to the matching degree of presetting the teacher according to the training module, and is specifically used for:
calculating the similarity between the characteristics of the teachers and each teacher through cosine similarity;
and recommending the teachers from high to low according to the ranking of the similarity.
Further, the matching module is used for calculating the similarity between the characteristics of the teachers and each teacher through cosine similarity, and acquiring integral information of a plurality of teachers if a plurality of teachers with the same similarity are determined;
and recommending the teacher according to the high-low sequence of the point information.
Further, the matching module is used for acquiring the classification evaluation data and the corresponding weight values of the teachers before acquiring the integral information of the teachers;
and obtaining the integral information of each teacher according to the classification evaluation data and the weighted value and a preset integral calculation rule.
The invention has the beneficial effects that: the teacher recommending method and device acquire feature information of students to construct corresponding student figures, wherein the feature information of the students comprises feature information of learning, social contact and difference of the students, the student figures are trained through a teaching feature rule model to obtain teacher features required by the students, the teachers are recommended according to the matching degree of the teacher features and preset teachers, the students are recommended with appropriate teachers, the purpose of teaching with factors is achieved, and therefore the purpose of maximally utilizing teacher resources is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a first flowchart illustrating a teacher recommendation method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a second teacher recommendation method according to an embodiment of the present invention;
fig. 3 is a third schematic flowchart of a teacher recommendation method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a teacher recommendation device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
Fig. 1 is a schematic flow chart of a teacher recommendation method according to an embodiment of the present invention, and as shown in fig. 1, the method will be described in detail below.
And step S10, acquiring the characteristic information of the students to construct corresponding student figures, wherein the characteristic information of the students comprises the characteristic information of learning, social contact and difference of the students.
And step S20, training the student portrait through the teaching characteristic rule model to obtain the teacher characteristics required by the student.
And step S30, recommending teachers according to the matching degree of the characteristics of the teachers and the preset teachers.
In this embodiment, first, student characteristic information is collected, where the student characteristic information includes: the student's basic information, character characteristics, interest information, ability characteristic, learning ability, social ability, defect are not enough, information such as concrete difference on original basis to and gather teacher's characteristic information, teacher's characteristic information includes: resume information, professional ability, teaching performance, character features, defect deficiency, comprehensive evaluation materials of teachers in the past year, teaching performance, student evaluation materials, parent evaluation materials and the like.
In this embodiment, a student portrait is trained through a teaching feature rule model to obtain teacher features required by students, where a natural language processing technology is used to perform semantic parsing on unstructured information data in the collected student feature information and teacher feature information, and an artificial tagging is performed on collected sample data in an artificial tagging manner, and repeated model training is performed by machine learning according to results of the artificial tagging to form a data model and model training and construct a student portrait and a teacher portrait, where a specific data model may be set according to actual conditions, but not limited thereto.
Specifically, various information of the student is filled in through logging in a website, and the information comprises: the basic information of students, the character information, the entry information of interest shifts, the original basic difference information and other feature description information. After submission, the student portrait information is input into the teaching feature rule model as an input source through the teaching feature rule model constructed in advance.
And finally, recommending the most suitable teacher to the students according to the characteristics of the teachers trained by the teaching characteristic rule model and a preset rule, wherein the preset rule can be used for recommending the teachers with the highest ranking to the students according to the ranking of the teachers corresponding to the characteristics of the trained teachers, but not limited to the above.
In the embodiment, the collected student characteristic information and teacher characteristic information are used for teaching characteristic rule model training, student figures are input into a teaching characteristic rule model which is built in advance as an input source, the student figures are built according to the characteristic information of student learning, social contact and difference, and the teacher characteristics required by students are obtained according to the teaching characteristic rule model, so that the most suitable teacher can be recommended for the students, the teaching according to the factors is realized, and the purpose of maximally utilizing the teacher resources is achieved.
In this embodiment, fig. 2 is a flowchart illustrating a second teacher recommendation method according to an embodiment of the present invention, which may be implemented through the following steps S11 and S12 before the step of acquiring feature information of a student and constructing a corresponding student image, as follows.
And step S11, collecting sample data of the student portrait and the teacher portrait, and labeling the sample data.
And step S12, constructing a teaching characteristic rule model through machine learning according to the labeled sample data.
In this embodiment, first, sample data of a student portrait and a teacher portrait are collected, specifically, the sample data of the student portrait is collected by writing information of each aspect of the student himself/herself in a student login website, and the written information of each aspect of the student includes: the method comprises the following steps of finishing sample data acquisition of learning student images by information such as student basic information, character information, interest shift information, specific differences on the original basis and the like; the sample data for collecting the teacher portrait is that the teacher logs in the website to fill in the teacher information, and the teacher information comprises: collecting sample data of teacher portrait by using natural language processing technique to make semantic analysis on unstructured information data in the above-mentioned sample data of collected student portrait and teacher portrait, marking collected sample data by means of manual marking, finally utilizing machine learning repeated training model according to marking result, for example, using LSTM + CRF (Long Short-Term Memory + Condition field) algorithm to make repeated model training on the result of manual marking, i.e. using sample data to train parameters in LSTM + CRF (Long Short-Term Memory + Condition field) algorithm, obtaining algorithm model parameters, forming a data model, importing sample data of collected student images and teacher images in batches, completing labeling of the sample data of students and teachers by using the data model through executing scripts, creating a label library and defining the corresponding relation between labels and labels, labeling students and teachers through executing the scripts, completing the construction of student images and teacher images, finally performing model training by adopting a support vector machine algorithm, namely training parameters in the support vector machine algorithm through the collected sample data of the student images and the teacher images to obtain the algorithm model parameters, realizing the construction of a teaching characteristic rule model, and particularly setting a machine learning algorithm according to actual conditions without being limited by the method.
During the sample data period that collection student drawed down and teacher drawdown, can artifical periodic verification, check for leaks and mend the vacancy, wherein, the administrator of training institution school will school information, set up interesting class information, teacher's information, and teacher's information includes: the teacher basic information, resume information, comprehensive evaluation materials, class scores, character features and other information are filled in the system, the scores of students in each interest class are recorded in the system regularly, if the scores are on-line exams, the system carries out on-line appraisal, and the scores of each student, the total scores of the classes and the average scores of the classes are automatically calculated; teachers in schools of training institutions can log in the system regularly, information such as personal character features and soft capability description can be basically modified on the initialized information, teaching records are filled in, collection of sample data of student portraits and teacher portraits is perfected, and teaching feature rule models are gradually formed.
In this embodiment, fig. 3 is a flow diagram of a third method for recommending a teacher according to an embodiment of the present invention, specifically, after a student fills in feature information of the student through a website and submits the feature information, a student portrait may be automatically generated according to the feature information of the student, the student portrait is input to a teaching feature rule model as an input source for training, characteristics of the teacher required by the student are obtained, and the teacher is recommended according to a matching degree of the characteristics of the teacher and a preset teacher, which is specifically as follows.
And step S31, calculating the similarity between the characteristics of the teachers and each teacher through cosine similarity.
Specifically, the process of calculating the similarity between the teacher feature and each teacher by using the cosine similarity includes:
1) and vectorizing the teacher feature vector and the teacher portrait.
2) And measuring the difference between the two individuals by calculating the cosine value of the included angle between the two characteristic vectors, wherein the closer the cosine value is to 1, the closer the included angle is to 0 degree, and the more similar the two vectors are.
The similarity given ranges from-1 to 1; where-1 means that the two vectors point in exactly the opposite direction, 1 means that their points are exactly the same, 0 usually means that they are independent, and the value between them means an intermediate similarity or dissimilarity.
3) And calculating the similarity of each teacher and the feature vector of the teacher, and recommending the teacher with high similarity.
Calculating the formula:
where Ai and Bi each represent vector A.
Specifically, a model matching algorithm can be set according to actual conditions, not limited to this, and if the similarity is different, the teacher is recommended from high to low according to the similarity ranking.
Further, if a plurality of teachers with the same similarity are determined, point information of the plurality of teachers is obtained, and the teachers are recommended according to the high-low order of the point information.
Specifically, the point information may be obtained by evaluating data of a teacher, for example: evaluation data such as resume information of teachers, comprehensive evaluation materials of teachers in the past years, teaching achievements, student evaluation materials, parent evaluation materials and the like can be endowed with corresponding weights, and then calculation rules of points are generated according to indexes defined by classification evaluation data and corresponding weights, so that point information of each teacher can be obtained, and teachers are recommended from high to low according to the point information.
In step S32, classification evaluation data of the teacher and corresponding weight values are obtained.
And step S33, obtaining integral information of each teacher according to the classification evaluation data and the weight value and a preset integral calculation rule.
Specifically, firstly, teacher evaluation entity extraction is carried out on sample data such as resume information collected by a teacher, comprehensive evaluation materials of the teacher in the past year, teaching performance, student evaluation materials, parent evaluation materials and the like, and structured storage is carried out; secondly, evaluating and classifying the structured storage, performing weight setting according to the evaluation classification, and performing quantity threshold setting according to the evaluation classification, wherein specifically, for example, if 1 data of the classification is less than 10, the classification is discarded, if the data is more than 1000, the calculation is performed according to 1000 capping strips, and the threshold can be specifically set according to the actual situation, but not limited to the above; and then, generating an integral calculation rule according to the classified evaluation data and indexes defined by the corresponding weight values, performing structured storage on the generated integral calculation rule, and finally, automatically according to a preset teacher integral rule.
And step S34, recommending teachers according to the high-to-low points of the integral information.
In this embodiment, after the similarity between the teacher characteristics and each teacher is calculated through cosine similarity, the classification evaluation data and the corresponding weight value of the teacher are obtained, according to the classification evaluation data and the weight value, the point information of each teacher is obtained according to a preset point calculation rule, the point information of a plurality of teachers is obtained, the teachers are recommended according to the height sequence of the point information, the most suitable teacher is recommended for students by combining multi-dimensional teacher point information, the teaching and education of the factors are realized, and therefore the purpose of maximally utilizing teacher resources is achieved.
In this embodiment, fig. 4 is a schematic structural diagram of a teacher recommendation device according to an embodiment of the present invention, where the teacher recommendation device 100 includes an acquisition module 1, a processing module 2, a training module 3, and a matching module 4. The acquisition module 1, the processing module 2, the training module 3 and the matching module 4 are sequentially in communication connection to realize data transmission or interaction. For example, the modules are electrically connected to each other through one or more communication buses or signal lines.
The acquisition module 1 is used for acquiring feature information of students to construct corresponding student figures, wherein the feature information of the students comprises feature information of learning, social contact and difference of the students.
And the processing module 2 is used for performing semantic analysis and labeling processing on the student characteristic information acquired by the acquisition module 1.
And the training module 3 is used for training the student portrait constructed by the acquisition module through the teaching characteristic rule model to obtain the teacher characteristics required by the student.
And the matching module 4 is used for recommending teachers according to the matching degree of the teacher characteristics obtained by the training module 3 and preset teachers.
Further, the collection module 1 is further configured to collect sample data of the student representation and the teacher representation before acquiring feature information of the student to construct a corresponding student representation.
The processing module 2 is further configured to label the sample data.
The training module 3 is also used for constructing a teaching characteristic rule model through machine learning according to the sample data marked by the processing module.
Further, the matching module 4 is used for recommending teachers according to the matching degree of the characteristics of the teachers obtained by the training module 3 and preset teachers, and is specifically used for:
calculating the similarity between the characteristics of the teachers and each teacher through cosine similarity;
and recommending the teachers from high to low according to the ranking of the similarity.
Further, the matching module 4 is further configured to, after calculating the similarity between the teacher features and each teacher through cosine similarity, if a plurality of teachers with the same similarity are determined, obtain integral information of the plurality of teachers;
and recommending the teacher according to the high-low sequence of the point information.
Further, the matching module 4 is further configured to obtain classification evaluation data and corresponding weight values of the teachers before obtaining the point information of the plurality of teachers;
and obtaining the integral information of each teacher according to the classification evaluation data and the weighted value and a preset integral calculation rule. The above description has been given of how to obtain the point information of a plurality of teachers, and will not be described again.
In summary, embodiments of the present invention provide a teacher recommendation method and device, wherein feature information of students is obtained to construct corresponding student figures, where the feature information of students includes feature information of learning, social contact and difference of students, the student figures are trained through a teaching feature rule model to obtain teacher features required by the students, a teacher is recommended according to matching degrees of the teacher features and a preset teacher, the matching degrees of the teacher and the preset teacher are calculated through the pre-trained teaching feature rule model, and multi-dimensional teacher point information is combined to realize recommendation of a most suitable teacher for the students, so as to achieve the purposes of student-based education and maximum utilization of teacher resources.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus and method embodiments described above are illustrative only, as the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, an electronic device, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only an alternative embodiment of the present invention and is not intended to limit the present invention, and various modifications and variations of the present invention may occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A teacher recommendation method, the method comprising:
acquiring feature information of students to construct corresponding student pictures, wherein the feature information of the students comprises feature information of learning, social contact and difference of the students;
training the student portrait through a teaching characteristic rule model to obtain teacher characteristics required by the student;
and recommending the teacher according to the matching degree of the teacher characteristics and the preset teacher.
2. The method of claim 1, wherein prior to the step of obtaining the student's characteristic information to construct a corresponding student image, the method further comprises:
collecting sample data of a student portrait and a teacher portrait, and labeling the sample data;
and constructing a teaching characteristic rule model through machine learning according to the labeled sample data.
3. The method of claim 1, wherein recommending teachers based on the matching of the teacher's features with preset teachers comprises:
calculating the similarity of the teacher characteristics and each teacher through cosine similarity;
and recommending the teachers from high to low according to the ranking of the similarity.
4. The method of claim 3, wherein after calculating the similarity of the teacher feature to each teacher by cosine similarity, the method further comprises:
if a plurality of teachers with the same similarity are determined, acquiring integral information of the plurality of teachers;
and recommending teachers according to the high-low sequence of the integral information.
5. The method of claim 4, wherein prior to obtaining the point information for the plurality of teachers, the method further comprises:
acquiring classification evaluation data and corresponding weight values of teachers;
and obtaining the point information of each teacher according to the classification evaluation data and the weight value and a preset point calculation rule.
6. An instructor recommending apparatus, characterized in that said apparatus comprises:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring characteristic information of students and constructing corresponding student pictures, and the characteristic information of the students comprises characteristic information of learning, social contact and difference of the students;
the processing module is used for carrying out semantic analysis and labeling processing on the student characteristic information acquired by the acquisition module;
the training module is used for training the student portrait constructed by the acquisition module through a teaching characteristic rule model to obtain teacher characteristics required by the student;
and the matching module is used for recommending teachers according to the matching degree of the characteristics of the teachers obtained by the training module and preset teachers.
7. The apparatus of claim 6, wherein the capture module is further configured to capture sample data of the student representation and the teacher representation prior to obtaining the feature information of the student to construct the corresponding student representation;
the processing module is also used for marking the sample data;
the training module is also used for constructing a teaching characteristic rule model through machine learning according to the sample data marked by the processing module.
8. The apparatus of claim 6, wherein the matching module is configured to recommend a teacher based on a matching degree of the teacher feature with a preset teacher, and is specifically configured to:
calculating the similarity of the teacher characteristics and each teacher through cosine similarity;
and recommending the teachers from high to low according to the ranking of the similarity.
9. The apparatus of claim 8, wherein the matching module is further configured to, after calculating the similarity between the teacher feature and each teacher through cosine similarity, if a plurality of teachers with the same similarity are determined, obtain the point information of the plurality of teachers;
and recommending teachers according to the high-low sequence of the integral information.
10. The apparatus of claim 9, wherein the matching module is further configured to obtain teacher's classification evaluation data and corresponding weight values before obtaining the plurality of teacher's point information;
and obtaining the point information of each teacher according to the classification evaluation data and the weight value and a preset point calculation rule.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911225648.8A CN110909248A (en) | 2019-12-03 | 2019-12-03 | Teacher recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911225648.8A CN110909248A (en) | 2019-12-03 | 2019-12-03 | Teacher recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110909248A true CN110909248A (en) | 2020-03-24 |
Family
ID=69822166
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911225648.8A Pending CN110909248A (en) | 2019-12-03 | 2019-12-03 | Teacher recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110909248A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311997A (en) * | 2020-04-01 | 2020-06-19 | 孙梦菲 | Interaction method based on network education resources |
| CN111476482A (en) * | 2020-04-03 | 2020-07-31 | 北京弘远博学科技有限公司 | Personalized recommendation method based on portrait |
| CN111667178A (en) * | 2020-06-07 | 2020-09-15 | 中信银行股份有限公司 | Evaluation and recommendation method and device for teachers in training institutions, electronic equipment and medium |
| CN112380263A (en) * | 2020-11-11 | 2021-02-19 | 北京爱论答科技有限公司 | Teaching data recommendation method and device |
| CN112559749A (en) * | 2020-12-18 | 2021-03-26 | 深圳赛安特技术服务有限公司 | Intelligent matching method and device for teachers and students in online education and storage medium |
| CN113256460A (en) * | 2021-04-30 | 2021-08-13 | 深圳市鹰硕教育服务有限公司 | Intelligent lesson preparation method, device, equipment and readable storage medium |
| WO2022237400A1 (en) * | 2021-05-11 | 2022-11-17 | 浙江吉利控股集团有限公司 | Online and offline hybrid education method and system, electronic device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108829752A (en) * | 2018-05-25 | 2018-11-16 | 南京邮电大学 | Based on personalized tutor's proposed algorithm |
| CN109427218A (en) * | 2017-08-25 | 2019-03-05 | 北京三好互动教育科技有限公司 | A kind of on-line education system and method |
| US20190138614A1 (en) * | 2017-11-07 | 2019-05-09 | Beijing Dami Technology Co., Ltd. | Method for recommending a teacher in a network teaching system |
| CN109754349A (en) * | 2019-01-07 | 2019-05-14 | 上海复岸网络信息科技有限公司 | A kind of online education intelligence teachers and students' matching system |
-
2019
- 2019-12-03 CN CN201911225648.8A patent/CN110909248A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109427218A (en) * | 2017-08-25 | 2019-03-05 | 北京三好互动教育科技有限公司 | A kind of on-line education system and method |
| US20190138614A1 (en) * | 2017-11-07 | 2019-05-09 | Beijing Dami Technology Co., Ltd. | Method for recommending a teacher in a network teaching system |
| CN108829752A (en) * | 2018-05-25 | 2018-11-16 | 南京邮电大学 | Based on personalized tutor's proposed algorithm |
| CN109754349A (en) * | 2019-01-07 | 2019-05-14 | 上海复岸网络信息科技有限公司 | A kind of online education intelligence teachers and students' matching system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311997A (en) * | 2020-04-01 | 2020-06-19 | 孙梦菲 | Interaction method based on network education resources |
| CN111476482A (en) * | 2020-04-03 | 2020-07-31 | 北京弘远博学科技有限公司 | Personalized recommendation method based on portrait |
| CN111667178A (en) * | 2020-06-07 | 2020-09-15 | 中信银行股份有限公司 | Evaluation and recommendation method and device for teachers in training institutions, electronic equipment and medium |
| CN111667178B (en) * | 2020-06-07 | 2023-10-20 | 中信银行股份有限公司 | Evaluation and recommendation method and device for training mechanism teacher, electronic equipment and medium |
| CN112380263A (en) * | 2020-11-11 | 2021-02-19 | 北京爱论答科技有限公司 | Teaching data recommendation method and device |
| CN112559749A (en) * | 2020-12-18 | 2021-03-26 | 深圳赛安特技术服务有限公司 | Intelligent matching method and device for teachers and students in online education and storage medium |
| CN112559749B (en) * | 2020-12-18 | 2024-04-09 | 深圳赛安特技术服务有限公司 | Intelligent matching method, device and storage medium for online education teachers and students |
| CN113256460A (en) * | 2021-04-30 | 2021-08-13 | 深圳市鹰硕教育服务有限公司 | Intelligent lesson preparation method, device, equipment and readable storage medium |
| WO2022237400A1 (en) * | 2021-05-11 | 2022-11-17 | 浙江吉利控股集团有限公司 | Online and offline hybrid education method and system, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909248A (en) | Teacher recommendation method and device | |
| CN109359215B (en) | Video intelligent pushing method and system | |
| CN115329200B (en) | Teaching resource recommendation method based on knowledge graph and user similarity | |
| Hamada et al. | Behavior analysis in a learning environment to identify the suitable learning style | |
| Lee et al. | Machine learning approaches for learning analytics: Collaborative filtering or regression with experts | |
| CN112784608A (en) | Test question recommendation method and device, electronic equipment and storage medium | |
| Bonney et al. | Citizen science and youth education | |
| CN111597305B (en) | Entity marking method, entity marking device, computer equipment and storage medium | |
| Ikawati et al. | Student behavior analysis to detect learning styles in Moodle learning management system | |
| CN111259240A (en) | Test question recommendation method and device | |
| Agarwal et al. | Autoeval: A nlp approach for automatic test evaluation system | |
| CN111160606B (en) | Test question difficulty prediction method and related device | |
| CN110852071B (en) | Knowledge point detection method, device, equipment and readable storage medium | |
| CN113283488B (en) | Learning behavior-based cognitive diagnosis method and system | |
| JP7293658B2 (en) | Information processing device, information processing method and program | |
| Gamie et al. | Multi-Dimensional Analysis to Predict Students' Grades in Higher Education. | |
| CN111639485A (en) | Course recommendation method based on text similarity and related equipment | |
| Yunitasari et al. | Implementation challenges of merdeka curriculum in primary schools | |
| Chaudhuri et al. | Automating assessment of design exams: a case study of novelty evaluation | |
| JP6161534B2 (en) | Teaching quality estimation device, teaching quality estimation method and program | |
| CN112785039B (en) | Prediction method and related device for answer score rate of test questions | |
| US20170193620A1 (en) | Associate a learner and learning content | |
| CN113888021A (en) | Intelligent learning evaluation method and system based on knowledge graph | |
| CN113934922A (en) | Intelligent recommendation method, device, equipment and computer storage medium | |
| Trewinnard et al. | Social media verification: assessing sources and visual content |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200324 |
|
| WD01 | Invention patent application deemed withdrawn after publication |