CN112925901A - Evaluation resource recommendation method for assisting online questionnaire evaluation and application thereof - Google Patents
Evaluation resource recommendation method for assisting online questionnaire evaluation and application thereofDownload PDFInfo
- Publication number
- CN112925901A CN112925901ACN202110310227.6ACN202110310227ACN112925901ACN 112925901 ACN112925901 ACN 112925901ACN 202110310227 ACN202110310227 ACN 202110310227ACN 112925901 ACN112925901 ACN 112925901A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- resource
- index
- model
- questionnaire
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention relates to the technical field of information processing, in particular to an evaluation resource recommendation method for assisting on-line questionnaire evaluation and application thereof.
Background
Evaluation resource recommendations may be applied in questionnaire research for online questionnaire evaluation or in cleansing questionnaire data. For example, when sending a questionnaire to a subject, there may be a case where the questionnaire is not sure to select and fills in the positive data randomly or prefers to fill in the positive data, and to avoid this, evaluation resources such as historical data statistics, related media data, etc. related to the subject matter of the questionnaire may be recommended to the subject when the subject fills in the questionnaire, so as to help the subject fill in the data more objectively. Also for example, after completion of questionnaire data collection, an exception data cleansing is required, and providing assessment resource recommendations can help quickly identify exception data.
The evaluation resource recommendation can be applied in a plurality of fields, particularly in the field of education informatization. With the continuous development of education informatization, a large amount of education informatization online data with different sources, types and forms are accumulated, diversified information channels are provided for assessment of education informatization development level, and diversified data support is provided for the current mainstream online assessment questionnaire investigation form.
However, the currently acquired education informationization evaluation resources are various in types and numerous in data, and it is difficult to extract evaluation resource information related to the subject of the evaluation questionnaire from massive evaluation resource data by using a traditional database query mode.
Disclosure of Invention
Aiming at least one defect or improvement requirement in the prior art, the invention provides an assessment resource recommendation method for assisting online questionnaire assessment and application thereof, which can realize accurate recommendation and collaborative analysis of network resource data in the filling and processing processes of education informatization development level online assessment questionnaires.
To achieve the above object, according to a first aspect of the present invention, there is provided an evaluation resource recommendation method for assisting online questionnaire evaluation, including:
respectively defining a questionnaire, an evaluation index system and a semantic expression model of evaluation resource data in advance;
creating resource recommendation processing process objects, wherein the resource recommendation processing process objects comprise a network questionnaire analysis model, an evaluation index structured processing model, an evaluation resource corpus organization model and an evaluation resource index information extraction model, and attribute association is realized among the resource recommendation processing process objects through a mapping relation linked list;
converting the questionnaire expressed by the text, the evaluation index system and the evaluation resource data into structured standard data expressed by a semantic expression model by respectively utilizing a network questionnaire analysis model, an evaluation index structured processing model and an evaluation resource corpus organization model;
and inputting the structured standard data into an evaluation resource index information extraction model to obtain an evaluation recommendation data cube.
Preferably, the web questionnaire analysis model at least includes attributes: the questionnaire correlation index system, the answer area correlation index item and the name of the organization to be evaluated;
the evaluation index structured processing model at least comprises the following attributes: index system number, index item number, index system dimension and index item key word;
the evaluation resource corpus organizational model includes at least attributes: resource theme range, corpus keywords and evaluation resource application range;
the evaluation resource index information extraction model at least includes attributes: the system comprises a to-be-evaluated organization name, an index item to be extracted, a resource subject range, a resource space-time range and resource keywords.
Preferably, the attribute association between the resource recommendation processing procedure objects through the mapping relation linked list comprises the following steps:
associating an attribute questionnaire associated index system of the network questionnaire analysis model with an attribute index system number of the evaluation index structured processing model, and associating an attribute answer area associated index item of the network questionnaire analysis model with an attribute index item number of the evaluation index structured processing model;
associating the dimension of an attribute index system of the evaluation index structured processing model with the attribute resource theme range of the evaluation resource corpus organizational model, and associating the attribute index key word of the evaluation index structured processing model with the attribute corpus key word attribute of the evaluation resource corpus organizational model;
associating the name of the mechanism to be evaluated of the attribute of the resource index information extraction model with the name of the mechanism to be evaluated of the attribute of the network questionnaire analysis model, and associating the index item to be extracted of the attribute of the resource index information extraction model with the associated index item of the attribute answer area of the network questionnaire analysis model;
the attribute resource theme range of the evaluation resource index information extraction model is associated with the attribute evaluation resource application range of the evaluation resource corpus organization model, the attribute resource theme range and the resource space-time range of the evaluation resource index information extraction model are associated with the attribute evaluation resource application theme range and the space-time range of the evaluation resource corpus organization model, and the attribute resource keyword of the evaluation resource index information extraction model is associated with the attribute corpus keyword of the evaluation resource corpus organization model.
Preferably, the evaluation resource index information extraction model is used for implementing the step;
acquiring evaluation questionnaire keywords, evaluation index keywords, evaluation resource corpora and retrieval query conditions from the structured standard data;
generating an evaluation field dictionary according to the evaluation questionnaire keywords and the evaluation index keywords;
calculating the similarity of the assessment resource corpus and the retrieval query condition by using the assessment domain dictionary, and generating an assessment resource recommendation list according to the similarity;
index recommendation data are extracted from the evaluation resource recommendation list, and an index recommendation data cube is constructed, wherein the index recommendation data cube supports query of a predefined semantic framework.
Preferably, the evaluation domain dictionary includes a pointer system domain dictionary, a school information dictionary, a stop word dictionary, and a synonym dictionary.
Preferably, the calculating the similarity between the assessment resource corpus and the search query condition by using the assessment domain dictionary includes the steps of:
utilizing an assessment domain dictionary to perform word segmentation processing on assessment resource linguistic data to obtain a keyword set of the assessment resource linguistic data, and constructing an assessment resource linguistic data characteristic matrix of the assessment resource linguistic data, wherein the keyword set is marked as a matrix A;
performing singular value decomposition and clustering calculation on the matrix A to obtain a matrix with the semantic concept clustering relation of the evaluation resource keywords, and recording as the matrix Ak；
Converting search query conditions into an AND matrix AkFeature vectors with the same space, denoted as vector qk；
Computing the matrix AkSum vector qkThe similarity of (c).
Preferably, the matrix a is represented by:
wherein i is the index value of the key word of the evaluation resource corpus, j is the index value of the evaluation resource corpus, ai,jThe value of (1) is an integer of 0 or non-0, 0 represents that the evaluation resource corpus key word with the index value of i is not in the evaluation resource corpus with the index value of 'j', the non-0 integer represents the number of times that the evaluation resource corpus key word with the index value of i appears in the evaluation resource corpus with the index value of 'j', n represents the corpus number of all evaluation resource corpora, and m represents the number of deduplicated evaluation resource corpus key words in all evaluation resource corpora.
According to a second aspect of the present invention, there is provided an evaluation resource recommendation system that assists in online questionnaire evaluation, comprising:
the pre-defining module is used for respectively defining a questionnaire, an evaluation index system and a semantic expression model of evaluation resource data in advance;
the resource recommendation processing process object creating module is used for creating resource recommendation processing process objects, the resource recommendation processing process objects comprise a network questionnaire analysis model, an evaluation index structured processing model, an evaluation resource corpus organization model and an evaluation resource index information extraction model, and attribute association is realized among the resource recommendation processing process objects through a mapping relation linked list;
the data structuralization processing module is used for converting the questionnaire expressed by the text, the evaluation index system and the evaluation resource data into structuralization standard data expressed by a semantic expression model by respectively utilizing a network questionnaire analysis model, an evaluation index structuralization processing model and an evaluation resource corpus organization model;
and the execution module is used for inputting the structured standard data into the evaluation resource index information extraction model to obtain the evaluation recommendation data cube.
According to a third aspect of the invention, there is provided an electronic device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any of the preceding claims when executing the computer program.
According to a fourth aspect of the invention, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements any of the methods described above.
In general, compared with the prior art, the invention has the following beneficial effects: accurate recommendation and collaborative analysis of network resource data in the filling and processing processes of the education informatization development level online evaluation questionnaire can be realized. Preferably, through data aggregation of predefined semantic frames on education informationized evaluation resources, implicit semantic relation clustering is performed on collected evaluation resource linguistic data by using a potential semantic analysis model, semantic concept similarity calculation is performed on complex and diverse evaluation resource data and network questionnaire evaluation indexes by using cosine distances, an evaluation resource recommendation list with content similarity to the network questionnaire evaluation indexes is obtained, a network questionnaire evaluation index recommendation resource data cube is constructed around multiple predefined semantic frame dimensions such as evaluation resource types, evaluation resource application space-time ranges, evaluation resource application subject ranges and the like, and accurate recommendation and collaborative analysis of the network resource data in the process of filling and processing the education informationized development level online evaluation questionnaire are assisted.
Drawings
FIG. 1 is a flowchart of an evaluation resource recommendation method for assisting in online questionnaire evaluation according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a predefined semantic expression model according to an embodiment of the present invention;
FIG. 3 is a flowchart of a mapping relationship linked list construction between objects in a resource recommendation process according to an embodiment of the present invention;
FIG. 4 is a flowchart of index recommendation data cube generation, according to an embodiment of the invention;
fig. 5 is a schematic diagram of an application effect of resource recommendation for assisting online questionnaire evaluation according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The assessment resource recommendation method for assisting online questionnaire assessment is particularly suitable for the field of education informatization, but is not limited to the field of education informatization, and can also be applied to any other field for online questionnaire assessment.
As shown in fig. 1, taking the field of education informatization as an example, the evaluation resource recommendation method for assisting online questionnaire evaluation according to the embodiment of the present invention includes the steps of:
(1) and respectively defining a questionnaire, an evaluation index system and a semantic expression model of evaluation resource data in advance.
And establishing a semantic expression model of the network questionnaire data information supporting resource recommendation. The semantic description of the network evaluation questionnaire mainly comprises basic questionnaire information, basic questionnaire filling object information and questionnaire subject information. The basic questionnaire information includes questionnaire titles, questionnaire profiles, questionnaire keywords, questionnaire-related index systems, and the like. The basic information of the questionnaire filling object comprises a user name, an organization type, a contact way and the like. The questionnaire question information comprises question quantity and question object information, wherein the question object information is core data forming a conventional question type of the questionnaire and comprises question numbers, question types, question stems, question answering areas and the like; the answer area is used as a carrier for evaluating resource recommendation, the semantic description of the answer area comprises the number of the answer areas and the object information of the answer areas, wherein the object information of the answer areas comprises key information such as answer area numbers, answer area coordinates, answer area constraints and answer area associated index items. Different semantic levels are represented by different semantic tags, "Ln" represents nth level semantic information, for example, "L1" represents first level semantic information, "L2" represents second level semantic information, etc. The semantic conversion rules for the web evaluation questionnaire data are shown in table 1.
TABLE 1 semantic conversion rules for network evaluation of questionnaire data information
As shown in fig. 2, the step (1) includes the steps of:
(11) and establishing a semantic conversion model of the evaluation index system data information supporting resource recommendation. The evaluation index system semantic description mainly comprises index system dimensions, index system index depth and index item object information. The index item object information includes index item numbers, index item levels, index item names, index item descriptions, index item abstracts, index item keywords and the like. The semantic conversion rule of the evaluation index system data information is shown in table 2.
TABLE 2 evaluation of semantic conversion rules for index system data information
| Numbering | Semantic description | Description of English | Semantic identification | Semantic hierarchy |
| 2 | Evaluation index system | Index System | IS | L1 |
| 2.1 | Dimension of index system | IndexDimension | IS.dimen | L2 |
| 2.2 | Index depth of index system | IndexSystemDepth | IS.depth | L2 |
| 2.3 | Index item object information | IndexItemInfo | IS.item | L2 |
| 2.3.1 | Index item numbering | Index ItemID | IS.item.id | L3 |
| 2.3.2 | Index item hierarchy | IndexItemLevel | IS.item.level | L3 |
| 2.3.3 | Index item name | Index Item Name | IS.item.name | L3 |
| 2.3.4 | Description of the index item | Index Item Description | IS.item.description | L3 |
| 2.3.5 | Abstract of index items | Index Item Summary | IS.item.summary | L3 |
| 2.3.6 | Index key word | Index ItemKeyword | IS.item.keyword | L3 |
| -- | -- | -- | -- | -- |
(12) And establishing a semantic conversion model of the evaluation resource data information supporting resource recommendation. The semantic description of the evaluation resource mainly comprises the type, the application range and the resource object data of the evaluation resource. The evaluation resource type comprises a resource site type (such as official resources, school self-built resources, media resources, scientific research resources and the like) and a resource content type (such as education informatization policy files, school informatization development basic information, statistical data, analysis reports and the like). The assessment resource applicability range includes a spatiotemporal range (e.g., a spatial range and a temporal range in which assessment resource data has data validity) and a topic range (e.g., a topic dimension of education informatization development level assessment of infrastructure, education resources, teaching applications, management services, support mechanisms, etc.) in which assessment resources are applicable. The resource object data comprises corpus data, corpus abstract, corpus keywords and the like. The semantic conversion rules for evaluating the resource data information are shown in table 3.
TABLE 3 evaluation of semantic conversion rules for resource data information
| Numbering | Semantic description | Description of English | Semantic identification | Semantic hierarchy |
| 3 | Evaluating resources | Evaluation Resource | ER | L1 |
| 3.1 | Resource type | Resource Type | ER.type | L2 |
| 3.1.1 | Resource site types | Resource Site Type | ER.Type.site | L3 |
| 3.2.2 | Resource content type | Resource Content Type | ER.Type.content | L3 |
| 3.2 | Application scope | Application Range | ER.range | L2 |
| 3.2.1 | Space-time range | Spatial Range | ER.range.spatial | L3 |
| 3.3.2 | Scope of subject matter | Temporal Range | ER.range.temporal | L3 |
| 3.3 | Resource object data | Resource Corpus Infor | ER.corpus | L2 |
| 3.3.1 | Corpus data | CorpusData | ER.corpus.text | L3 |
| 3.3.2 | Corpus abstract | Corpus Summary | ER.corpus.summary | L3 |
| 3.3.3 | Corpus key words | CorpusKeyWord | ER.corpus.keyword | L3 |
| -- | -- | -- | -- | -- |
(13) The method comprises the steps of collecting a network questionnaire, an evaluation index system and evaluation resource data of online evaluation of education informatization development level, and converting the network questionnaire, the evaluation index system and the evaluation resource data into structured standard data with predefined semantic labels according to semantic conversion models of the network questionnaire, the evaluation index system and the evaluation resource data. According to the semantic conversion models in (11), (12) and (13), the structural relationship among different levels of semantic information is established, the incidence relationship among the evaluated questionnaire object, the basic questionnaire information, the basic questionnaire filling object information and the questionnaire subject information is established, the incidence relationship among the evaluation index system object, the index item number, the index item level, the index item name, the index item description, the index item abstract and the index item key word is established, and the incidence relationship among the evaluated resource object, the resource type, the application range and the resource object data is established.
(2) Creating resource recommendation processing process objects, wherein attribute association is realized among the resource recommendation processing process objects through a mapping relation linked list, and the resource recommendation processing process objects comprise a network questionnaire analysis model, an evaluation index structured processing model, an evaluation resource corpus organization model and an evaluation resource index information extraction model.
As shown in fig. 3, the specific implementation process of creating the resource recommendation processing procedure object and its attribute and constructing the resource recommendation processing procedure object mapping relationship linked list is as follows:
(21) and creating a resource recommendation processing process object, wherein the resource recommendation processing process object comprises a network questionnaire analysis model, an evaluation index structured processing model, an evaluation resource corpus organization model and an evaluation resource index information extraction model.
The network questionnaire analysis model carries out data analysis and data extraction on the questionnaire based on a semantic model of a network evaluation questionnaire, traditional evaluation questionnaire data is expressed by simple text information combination, the evaluation questionnaire is subjected to enhanced expression of predefined semantic information to support richer questionnaire information operation capability, semantic label positioning is provided for interactive operation of a recommended resource list and the questionnaire through the enhanced expression of the semantic information, for example, when a mouse cursor is positioned in an answer area of the questionnaire, an answer area associated index item can be obtained through the semantic label, and a mechanism name information in object basic information is filled in combination with the questionnaire, so that an evaluation resource information list related to the mechanism name and the index item can be obtained. The evaluation index structured processing model is based on a current education informatization evaluation index system, combines a predefined education informatization domain keyword library, converts the evaluation index system based on natural language description into a tree structure of index items expressed by keyword sequences, compresses text description of the index items into a series of keyword sets with grammar structures, and further supports accurate/fuzzy query of evaluation resource information based on evaluation index keyword/keyword combination. The assessment resource corpus organization model constructs an assessment resource corpus database from multiple dimensions such as assessment resource data themes, assessment indexes, assessment resource application space-time ranges and assessment resource keywords by importing and extracting text information related to the education informatization assessment field. The evaluation resource index information extraction model adaptively extracts and recommends an evaluation resource text information list related to indexes based on evaluation questionnaire filling object information and evaluation indexes related to the to-be-filled answer area. The definition of the resource recommendation process object is shown in table 4.
TABLE 4 resource recommendation process object
| Numbering | Object name | Object definition | Description of the invention |
| 1 | Network questionnaire analysis model | QNModel | For parsing web questionnaire data |
| 2 | Evaluation index structured processing model | ISModel | Tree structure for constructing evaluation index expressed by keyword sequence |
| 3 | Evaluating a resource corpus organizational model | ERModel | For constructing assessment resource corpus database |
| 4 | Evaluation resource index information extraction model | ExtractModel | Extracting and recommending evaluation resource text information related to indexes |
(22) And creating the attribute of the resource recommendation processing object. The attributes of the object of the network questionnaire parsing model may include a questionnaire title, a questionnaire brief introduction, a questionnaire keyword, a questionnaire associated index system, a mechanism name, a mechanism type, a question stem, answer area coordinates, answer area constraints, answer area associated index items, and the like, and the specific semantic information may refer to step (11). The evaluation index structured processing model object attributes can include index system numbers, index system dimensions, index system index depths, index item numbers, index item hierarchies, index item names, index item descriptions, index item abstracts, index item keywords and the like, and the specific semantic information can refer to step (12). The evaluation resource corpus organization model object attributes can include resource site types, resource content types, resource applicable space-time ranges, subject ranges, resource object corpus data, corpus abstract, corpus keywords and the like, and specific semantic information can refer to step (13). The evaluation resource index information extraction model object attributes can comprise names of organizations to be evaluated, index items to be extracted, resource subject ranges, resource space-time ranges, resource content types, resource keywords and the like.
(23) And constructing a mapping relation linked list between the resource recommendation processing process objects. The network questionnaire analysis model object attribute questionnaire associated index system and the answer area associated index item are respectively associated with the evaluation index structured processing model object attribute index system number and the index item number attribute, and the unbinding and flexible association of the evaluation questionnaire and the index system are realized through the mapping relation. The evaluation index structuralized processing model object attribute index system dimension and the index key word are associated with the evaluation resource corpus organization model object attribute resource theme range and the corpus key word attribute, and the unified management of the evaluation resource corpus resource classification information and the keyword label information is realized through the mapping relation. The evaluation resource index information extracts the name of a mechanism to be evaluated of the model object attribute, the index item to be extracted is associated with the name of the network questionnaire analysis model object attribute mechanism and the associated index item of the answer area, and the evaluation resource index information extracts the subject range of the model object attribute resource, the resource space-time range, the resource keyword and the like, evaluates the subject range, the space-time range and the attribute association of the corpus keyword.
(3) And respectively converting the questionnaire expressed by the text, the evaluation index system and the evaluation resource data into structured standard data expressed by a semantic expression model by using a network questionnaire analysis model, an evaluation index structured processing model and an evaluation resource corpus organization model.
And (3) acquiring a network questionnaire, an evaluation index system and evaluation resource data for online evaluation of education informatization development level, and converting the network questionnaire, the evaluation index system and the evaluation resource data into structured standard data with predefined semantic tags, wherein the format of the structured standard data is as described in the steps (1) and (2), and the description is omitted here.
(4) And inputting the structured standard data into an evaluation resource index information extraction model to obtain an evaluation recommendation data cube.
The display of the evaluation recommendation data on the interface may be as shown in fig. 5. For example, when the user is filling in the 2 nd question of the blank filling question, the value may not be determined so much, and the evaluation recommendation data can be extracted from the structured standard data through the above steps and displayed on the right side of the interface for the questionnaire filling person to refer to.
As shown in fig. 4, the specific implementation process of extracting online evaluation resource information and generating index recommendation data cubes is as follows:
(41) and obtaining evaluation questionnaire keywords, evaluation index keywords, evaluation resource corpora and retrieval query conditions from the structured standard data.
Specifically, the information is obtained through the resource recommendation processing procedure object and the mapping relation linked list.
(42) And inputting the evaluation questionnaire keywords and the evaluation index keywords into a domain dictionary construction model to generate an education informatization evaluation domain dictionary. Preferably, the dictionary comprises a dictionary of index system fields, a dictionary of school information, a dictionary of stop words, a dictionary of synonyms and the like. The index system dictionary and the school information dictionary are used for improving the recognition rate of proper nouns in the field of education informatization and the accuracy rate of word segmentation. The synonym dictionary is used for word disambiguation, and reduces errors of characteristic value vectors generated by text word segmentation. The stop word dictionary is used for eliminating invalid information in the evaluation resource text.
(43) And calculating the similarity of the evaluation resource corpus and the retrieval query condition by using the evaluation field dictionary, and generating an evaluation resource recommendation list according to the similarity.
Preferably, step (43) comprises the steps of:
(431) and importing the assessment resource corpus database in the relation linked list into an assessment resource feature matrix construction model to construct an assessment resource corpus feature matrix.
And (4) performing word segmentation processing on the assessment resource data information by using a jieba tool based on the generated education informationization assessment field dictionary in the step (42). And introducing an index system dictionary and a school information dictionary, and segmenting the evaluation resource text by using a segmentation tool. And introducing a stop word dictionary, and removing invalid text information from the word segmentation vector. And introducing a synonym dictionary, and performing synonym replacement on texts with similar word meanings to reduce the error of the characteristic value vector. And finally generating a keyword set of the evaluation resources.
Further, importing a keyword set of the assessment resources into an assessment resource feature matrix construction model, constructing text feature vectors of each assessment resource corpus based on a doc2bow algorithm, and constructing a feature sparse matrix 'A' between the assessment resource corpus and the keywords of the dictionary corpus in the education information assessment field:
for "ai,j"," i "is the index value of the corpus key word, and" j "is the index value of the evaluation resource corpus. "a" isi,j"is an integer of 0 or non-0, where 0 indicates that the corpus keyword with index value" i "is not in the evaluation resource corpus with index value" j ", and a non-0 integer indicates the number of times that the corpus keyword with index value" i "appears in the evaluation resource corpus with index value" j ". For "am,n"," n "indicates the number of corpus in the evaluation resource corpus, and" m "indicates the number of corpus keywords for deduplication in the evaluation resource corpus.
Row vector of matrix "A
Indicating the existence of the corpus keyword with the index value of "i" in the "n" assessment resource corpuses. Column vector of matrix "A
Indicating an index value of "jAnd (4) evaluating the inclusion condition of the resource corpus to the m evaluation resource keywords.
(432) And inputting the sparse matrix of the evaluated resource corpus features in the relation linked list into a latent semantic analysis model (LSA for short), and performing singular value decomposition and clustering calculation on the evaluated resource corpus feature matrix.
And (3) performing tfidf processing on the sparse matrix "A" of the evaluated resource features (tfidf is the weight calculation of the keywords of the evaluated resource in the corpus of the evaluated resource), calculating the tfidf value of the keywords of the corpus in each evaluated corpus resource, and generating a tfidf matrix "tfidf [ A ]" of the matrix "A".
Further, the matrix "tfidf [ A ] is modeled using an LSA]"according to" tfidf [ A ]]＝U∑VT"is subjected to singular value decomposition. The three matrices generated after singular value decomposition are respectively a singular value diagonal matrix sigma, and orthogonal matrices U and V. Wherein "U" is represented by left singular vector
Composition, reflecting the semantic conceptual characteristics of the evaluation resource keywords, V being a right singular vectorj"composition, which reflects the semantic concept characteristics of the assessment resource corpus.
Further, the first k singular values are selected to construct a singular value matrix sigmak"and its corresponding matrix" Uk"and" Vk", where k is the coordinate value satisfying the maximum tangent slope of the singular value change function curve, and finally" U "is usedk”、“Vk' andk'reverse generation of matrix with evaluation resource keyword semantic concept clustering relation' Ak"(matrix" A)k"the calculation formula is
) And realizing semantic concept clustering of the synonymous keywords of the evaluation resources.
(433) And importing the basic information of the network questionnaire filling object and the object information of the answer area in the relation linked list into an evaluation resource retrieval model, and inquiring evaluation resource information related to the evaluation index content related to the answer area.
Importing the organization name in the basic information of the network questionnaire filling object and the associated evaluation index information in the answer area object into a doc2bow algorithm, and constructing a characteristic vector between a query condition and a corpus keyword of a dictionary in the education informatization evaluation field
The feature vector "dj+1The "and the matrix" A "are merged to generate" A ' ", tfidf processing is performed on the matrix" A ' ", and the" j +1 "th column data is extracted from A '", thereby generating "q". Using conversion formulae
Converting "q" to "qk". Wherein
Is a matrix of said singular values [ ∑ ]kThe "inverse matrix" is then used to determine,
is the above-mentioned "Uk"is a transposed matrix.
(444) Calculating vector 'q' by using cosine similarity calculation formulak"sum matrix" AkAnd screening an evaluation resource recommendation list with content similarity according to the cosine distance of the characteristic vector of each evaluation resource corpus.
(44) And inputting the index information related to the evaluation resource recommendation list and the evaluation question answer area obtained by retrieval into an index information filtering model, extracting the index information in the evaluation resources according to a predefined index data extraction rule, and constructing an evaluation index recommendation data cube, wherein the recommendation data cube comprises attribute information such as an evaluation resource type, an evaluation resource application space-time range, an evaluation resource application subject range and the like, and supports filtering query of a predefined semantic framework.
The evaluation resource recommendation system for assisting online questionnaire evaluation in the embodiment of the invention comprises:
the pre-defining module is used for respectively defining a questionnaire, an evaluation index system and a semantic expression model of evaluation resource data in advance;
the resource recommendation processing process object creating module is used for creating resource recommendation processing process objects, the resource recommendation processing process objects comprise a network questionnaire analysis model, an evaluation index structured processing model, an evaluation resource corpus organization model and an evaluation resource index information extraction model, and attribute association is realized among the resource recommendation processing process objects through a mapping relation linked list;
the data structuralization processing module is used for converting the questionnaire expressed by the text, the evaluation index system and the evaluation resource data into structuralization standard data expressed by a semantic expression model by respectively utilizing a network questionnaire analysis model, an evaluation index structuralization processing model and an evaluation resource corpus organization model;
and the execution module is used for inputting the structured standard data into the evaluation resource index information extraction model to obtain the evaluation recommendation data cube.
The implementation principle and technical effect of the evaluation resource recommendation system are similar to those of the evaluation resource recommendation method, and are not described herein again.
The embodiment also provides an electronic device, which includes at least one processor and at least one memory, where the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to execute the steps of the resource recommendation evaluation method in the first embodiment, and the specific steps refer to the method embodiments and are not described herein again; in this embodiment, the types of the processor and the memory are not particularly limited, for example: the processor may be a microprocessor, digital information processor, on-chip programmable logic system, or the like; the memory may be volatile memory, non-volatile memory, a combination thereof, or the like.
The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement any of the above technical solutions of the embodiments of the method for recommending an evaluation resource. The implementation principle and technical effect are similar to those of the above method, and are not described herein again.
It must be noted that in any of the above embodiments, the methods are not necessarily executed in order of sequence number, and as long as it cannot be assumed from the execution logic that they are necessarily executed in a certain order, it means that they can be executed in any other possible order.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
Translated fromChinese
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110310227.6ACN112925901B (en) | 2021-03-23 | 2021-03-23 | An evaluation resource recommendation method for assisting online questionnaire evaluation and its application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110310227.6ACN112925901B (en) | 2021-03-23 | 2021-03-23 | An evaluation resource recommendation method for assisting online questionnaire evaluation and its application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112925901Atrue CN112925901A (en) | 2021-06-08 |
| CN112925901B CN112925901B (en) | 2022-07-19 |
Family
ID=76175688
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110310227.6AActiveCN112925901B (en) | 2021-03-23 | 2021-03-23 | An evaluation resource recommendation method for assisting online questionnaire evaluation and its application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112925901B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114564626A (en)* | 2021-12-23 | 2022-05-31 | 中国电子科技集团公司第二十九研究所 | A method and storage medium for filtering special situation of electronic reconnaissance |
| CN114936796A (en)* | 2022-06-15 | 2022-08-23 | 中国建设银行股份有限公司 | Project evaluation method and device, electronic equipment and computer readable medium |
| CN116307792A (en)* | 2022-10-12 | 2023-06-23 | 广州市阿尔法软件信息技术有限公司 | Urban physical examination subject scene-oriented evaluation method and device |
| CN116415047A (en)* | 2023-06-09 | 2023-07-11 | 湖南师范大学 | Resource screening method and system based on national image resource recommendation |
| CN116823406A (en)* | 2023-08-24 | 2023-09-29 | 国品优选(北京)品牌管理有限公司 | Nutrient tablet recommendation method and system based on big data |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090100094A1 (en)* | 2007-10-15 | 2009-04-16 | Xavier Verdaguer | Recommendation system and method for multimedia content |
| CN103049528A (en)* | 2012-12-24 | 2013-04-17 | 北京信息科技大学 | Personalized web page searching and sorting method on basis of interest vectors of user |
| CN106844787A (en)* | 2017-03-16 | 2017-06-13 | 四川大学 | It is a kind of for automobile industry finds targeted customer and matches the recommendation method of target product |
| CN110610002A (en)* | 2019-08-12 | 2019-12-24 | 华中师范大学 | Questionnaire information processing method, device, computer equipment and storage medium |
| US20190392541A1 (en)* | 2018-06-20 | 2019-12-26 | Dataco Gmbh | Method and system for generating reports |
| CN110866180A (en)* | 2019-10-12 | 2020-03-06 | 平安国际智慧城市科技股份有限公司 | Resource recommendation method, server and storage medium |
| CN111079387A (en)* | 2019-11-29 | 2020-04-28 | 华中师范大学 | A method, device, computer equipment and storage medium for automatically generating a questionnaire |
| CN111192176A (en)* | 2019-12-30 | 2020-05-22 | 华中师范大学 | Online data acquisition method and device supporting education informatization assessment |
| CN111966913A (en)* | 2020-10-21 | 2020-11-20 | 拼说说(深圳)网络科技有限公司 | Education resource recommendation processing method and device and computer equipment |
- 2021
- 2021-03-23CNCN202110310227.6Apatent/CN112925901B/enactiveActive
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090100094A1 (en)* | 2007-10-15 | 2009-04-16 | Xavier Verdaguer | Recommendation system and method for multimedia content |
| CN103049528A (en)* | 2012-12-24 | 2013-04-17 | 北京信息科技大学 | Personalized web page searching and sorting method on basis of interest vectors of user |
| CN106844787A (en)* | 2017-03-16 | 2017-06-13 | 四川大学 | It is a kind of for automobile industry finds targeted customer and matches the recommendation method of target product |
| US20190392541A1 (en)* | 2018-06-20 | 2019-12-26 | Dataco Gmbh | Method and system for generating reports |
| CN110610002A (en)* | 2019-08-12 | 2019-12-24 | 华中师范大学 | Questionnaire information processing method, device, computer equipment and storage medium |
| CN110866180A (en)* | 2019-10-12 | 2020-03-06 | 平安国际智慧城市科技股份有限公司 | Resource recommendation method, server and storage medium |
| CN111079387A (en)* | 2019-11-29 | 2020-04-28 | 华中师范大学 | A method, device, computer equipment and storage medium for automatically generating a questionnaire |
| CN111192176A (en)* | 2019-12-30 | 2020-05-22 | 华中师范大学 | Online data acquisition method and device supporting education informatization assessment |
| CN111966913A (en)* | 2020-10-21 | 2020-11-20 | 拼说说(深圳)网络科技有限公司 | Education resource recommendation processing method and device and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 王凯: "融合SNS的区域教育信息化水平评估系统设计与实现", 《中国优秀硕士论文电子期刊网》* |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114564626A (en)* | 2021-12-23 | 2022-05-31 | 中国电子科技集团公司第二十九研究所 | A method and storage medium for filtering special situation of electronic reconnaissance |
| CN114564626B (en)* | 2021-12-23 | 2023-04-21 | 中国电子科技集团公司第二十九研究所 | A method and storage medium for filtering special situation of electronic reconnaissance |
| CN114936796A (en)* | 2022-06-15 | 2022-08-23 | 中国建设银行股份有限公司 | Project evaluation method and device, electronic equipment and computer readable medium |
| CN116307792A (en)* | 2022-10-12 | 2023-06-23 | 广州市阿尔法软件信息技术有限公司 | Urban physical examination subject scene-oriented evaluation method and device |
| CN116307792B (en)* | 2022-10-12 | 2024-03-12 | 广州市阿尔法软件信息技术有限公司 | Urban physical examination subject scene-oriented evaluation method and device |
| CN116415047A (en)* | 2023-06-09 | 2023-07-11 | 湖南师范大学 | Resource screening method and system based on national image resource recommendation |
| CN116415047B (en)* | 2023-06-09 | 2023-08-18 | 湖南师范大学 | A resource screening method and system based on national image resource recommendation |
| CN116823406A (en)* | 2023-08-24 | 2023-09-29 | 国品优选(北京)品牌管理有限公司 | Nutrient tablet recommendation method and system based on big data |
| CN116823406B (en)* | 2023-08-24 | 2023-11-14 | 国品优选(北京)品牌管理有限公司 | Nutrient tablet recommendation method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112925901B (en) | 2022-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Da | The computational case against computational literary studies | |
| Zubrinic et al. | The automatic creation of concept maps from documents written using morphologically rich languages | |
| Lerman et al. | Using the structure of web sites for automatic segmentation of tables | |
| CN112925901B (en) | An evaluation resource recommendation method for assisting online questionnaire evaluation and its application | |
| CN114595344B (en) | Method and device for constructing knowledge graph for crop variety management | |
| CN106776711A (en) | A kind of Chinese medical knowledge mapping construction method based on deep learning | |
| CN107122413A (en) | A kind of keyword extracting method and device based on graph model | |
| US20150006528A1 (en) | Hierarchical data structure of documents | |
| CN103838789A (en) | A Calculation Method of Text Similarity | |
| CN108319583B (en) | Method and system for extracting knowledge from Chinese language material library | |
| CN101777042A (en) | Neural network and tag library-based statement similarity algorithm | |
| CN113239111B (en) | Knowledge graph-based network public opinion visual analysis method and system | |
| CN112800244B (en) | Method for constructing knowledge graph of traditional Chinese medicine and national medicine | |
| CN114722836A (en) | Abstract generation method, apparatus, device and medium | |
| CN113946686A (en) | Construction method and system of electricity marketing knowledge graph | |
| CN109522396B (en) | Knowledge processing method and system for national defense science and technology field | |
| CN118627619A (en) | A method for extracting legal document information | |
| CN118733860A (en) | A method for constructing a media influence evaluation model based on multi-dimensional feature optimization | |
| Hasegawa et al. | Extracting conceptual graphs from Japanese documents for software requirements modeling | |
| CN119807229A (en) | Resume screening method, device and medium based on large model prompt instructions | |
| Azeroual | A text and data analytics approach to enrich the quality of unstructured research information | |
| Phan et al. | Automated data extraction from the web with conditional models | |
| Dai | Construction of English and American literature corpus based on machine learning algorithm | |
| Denisova et al. | Ontology engineering based on spreadsheet data transformation | |
| Zhang | Text Complexity Classification Data Mining Model Based on Dynamic Quantitative Relationship between Modality and English Context |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |