CN115357632A - Learner personalized interpretable potential friend recommendation method and device - Google Patents
Learner personalized interpretable potential friend recommendation method and device Download PDFInfo
- Publication number
- CN115357632A CN115357632A CN202210859182.2A CN202210859182A CN115357632A CN 115357632 A CN115357632 A CN 115357632A CN 202210859182 A CN202210859182 A CN 202210859182A CN 115357632 A CN115357632 A CN 115357632A
- Authority
- CN
- China
- Prior art keywords
- learners
- learner
- trust
- similarity
- degree
- 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 58
- 230000002452 interceptive effect Effects 0.000 claims abstract description 41
- 238000010586 diagram Methods 0.000 claims abstract description 13
- 230000001149 cognitive effect Effects 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims description 42
- 230000006399 behavior Effects 0.000 claims description 8
- 238000005065 mining Methods 0.000 claims description 5
- 230000019771 cognition Effects 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Remote Sensing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for recommending personalized interpretable potential friends of learners, wherein the method comprises the following steps: performing modeling processing on the socialized online course platform to obtain a multidirectional complex network diagram structure; acquiring three-degree friend relationships of all learners in the socialized online course platform according to the complex network diagram structure; calculating the trust degree among all friends by mixed weighting of cognitive trust and interactive trust; calculating to obtain academic interest similarity between learners; acquiring the geographical position information of each learner; calculating the comprehensive similarity of the learner within three degrees according to the trust degree and academic interest similarity among the friends and the geographic position information of the learner; and selecting a plurality of learners with highest comprehensive similarity as potential friends to recommend and generate a recommendation reason. The method has high efficiency and high accuracy, can solve the problem that data is sparse and potential friend recommendation cannot be provided for cold-start learners, and can be widely applied to the technical field of computers.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for recommending personalized interpretable potential friends of learners.
Background
The problems of data sparseness and cold start are the difficult problems faced by a recommendation system, how to accurately mine potential friends of learners in a socialized online course platform, a potential learning group is built for the learners, and according to learning contents interested by group members, personalized collaborative recommendation of similar learners is realized, so that the viscosity and the interest degree of the learners on the online course platform are improved, and the problem of high loss rate of the learners of the online course platform is solved.
In the related art, the social online course platform has the problems of sparse learner interaction data and inexplicability of a recommendation algorithm.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method and an apparatus for recommending potential friends through personalized interpretability by a learner, so as to solve the problem that data sparsity cannot provide potential friend recommendations for a cold-start learner.
One aspect of the embodiments of the present invention provides a method for recommending personalized interpretable potential friends of a learner, including:
performing modeling processing on the socialized online course platform to obtain a multidirectional complex network diagram structure;
acquiring three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure;
calculating the trust degree among all friends by mixed weighting of cognitive trust and interactive trust;
calculating the similarity of texts among the learner interest and hobby data by adopting a cosine similarity method, calculating the similarity of academic achievements recently published by a learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners;
acquiring the geographic position information of each learner;
calculating the comprehensive similarity of the learner within three degrees by combining the geographic position information of the learner according to the trust between the friends and the academic interest similarity;
and selecting a plurality of learners with highest comprehensive similarity as potential friends to recommend and generate a recommendation reason.
Optionally, the obtaining three-degree friend relationships of all learners in the social online course platform according to the complex network graph structure includes:
constructing a direct friend relationship set of the learner according to the complex network graph structure;
forming friend node pairs by nodes which become friends in the complex network graph structure;
searching friend node pairs of two non-friend relationship nodes through the friend node pairs, mining public nodes existing between the two non-friend relationship nodes, and further obtaining a second-degree friend relationship set between all learners of the socialized online course platform;
and performing head node pairing on the obtained second-degree friend relationship and the existing first-degree friend relationship to obtain the third-degree friend relationship among learners, and further obtaining the third-degree friend relationships of all learners in the socialized online course platform.
Optionally, the calculating the trust level between the friends by hybrid cognitive trust and interactive trust weighting includes:
determining two learners who have established friend relationships as cognition trust;
determining two learners of which the communication frequency of a pair of friends in the socialized online course platform is higher than a preset condition as interactive trust;
after the trust degree of the cognition trust between the two learners or the trust degree of the interaction trust between the two learners is calculated, weight adjustment is carried out according to the interaction behaviors of the two learners in the socialized online course platform, and the trust degree between friends is calculated.
Optionally, the calculation formula of the trust level between the friends is as follows:
Fr(u,v)＝Kr(u,v)+Ir(u,v)
fr (u, v) represents the trust degree of the learner u to the learner v, and Kr (u, v) represents the trust degree of two learners for knowing and trusting; ir (u, v) represents the trust degree of two learners when the two learners are in interactive trust;
wherein the trust level of the two learners when the two learners are interactive trust is determined according to the access interactive trust and the praise interactive trust of the two learners;
and determining the trust degree between friends of the learner within three degrees by calculating the trust degree values of friends of two degrees and friends of three degrees between different learners.
Optionally, the formula for calculating the similarity of the texts between the learner interest and preference data by using a cosine similarity method is as follows:
wherein S is cos (u, v) similarity value representing interest and hobbies between learner u and learner v, u i And v i Respectively representing the interests and hobbies of different learners;
the calculation formula for calculating the similarity of recently published academic achievements of the learner by using the TF-IDF model is as follows:
wherein S is TF-IDF (u, v) similarity value, p, representing academic achievement of learner u and learner v ui And p vi Respectively representing the feature directions of learner u and learner vThe value of the ith of the amount;
the calculation formula for obtaining the academic interest similarity between learners by performing weighted mixed calculation on the two similarities is as follows:
S(u,v)＝βS cos (u,v)+(1-β)S TF-IDF (u,v)
wherein S (u, v) represents academic interest similarity obtained by final calculation; beta represents the corresponding weight value.
Optionally, the method further comprises:
calculating the distance between two learners according to a longitude and latitude difference value calculation formula of any two points on the earth;
wherein, the calculation formula of the distance between the two learners is as follows:
wherein D (u, v) represents the distance between learners u and v; r represents the average radius of the earth; c (u, v) represents the latitude and longitude difference between learners u and v.
Optionally, the calculation formula of the comprehensive similarity is:
wherein Sim (u, v) represents the integrated similarity between learners u and v; d (u, v) represents the distance between learners u and v; s (u, v) represents the academic interest similarity between learners u and v; t (u, v) represents the degree of confidence between learners u and v.
Another aspect of the embodiments of the present invention further provides a device for recommending personalized interpretable potential friends of a learner, including:
the first module is used for performing modeling processing on the socialized online course platform to obtain an undirected complex network diagram structure;
the second module is used for acquiring the three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure;
the third module is used for calculating the trust degree among the friends through mixed weighting of the cognitive trust and the interactive trust;
the fourth module is used for calculating the similarity of texts among the interest and hobby data of the learner by adopting a cosine similarity method, calculating the similarity of academic results recently published by the learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners;
the fifth module is used for acquiring the geographical position information of each learner;
a sixth module, configured to calculate, according to the trust degrees among the friends and the academic interest similarity, a comprehensive similarity of the learner within three degrees in combination with the geographic location information of the learner;
and the seventh module is used for selecting a plurality of learners with the highest comprehensive similarity as potential friends to recommend and generate a recommendation reason.
Another aspect of the embodiments of the present invention further provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Another aspect of the embodiments of the present invention also provides a computer-readable storage medium, which stores a program, and the program is executed by a processor to implement the method as described above.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.
The embodiment of the invention carries out modeling processing on the socialized online course platform to obtain an undirected complex network diagram structure; acquiring three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure; calculating the trust degree among all friends by mixed weighting of cognitive trust and interactive trust; calculating the similarity of texts among the learner interest and hobby data by adopting a cosine similarity method, calculating the similarity of academic achievements recently published by a learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners; acquiring the geographical position information of each learner so as to solve the problem of low recommendation accuracy caused by data sparsity of cold-start learners; according to the trust degrees among all friends and the academic interest similarity, the comprehensive similarity of the learner within three degrees is calculated by combining the geographic position information of the learner; and selecting a plurality of learners with highest comprehensive similarity as potential friends to recommend and generate a recommendation reason. The method has high efficiency and high accuracy, and can solve the problem that the data is sparse and the potential friend recommendation can not be provided for the cold-start learner.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a diagram of a social online lesson platform;
fig. 2 is a flowchart of an overall implementation procedure in a specific application scenario according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a recommendation effect in a specific application scenario of the embodiment;
FIG. 4 is a flowchart illustrating the overall steps provided by an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application 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 and not restrictive on the broad application.
In view of the problems in the prior art, an aspect of the embodiments of the present invention provides a method for a learner to recommend personalized interpretable potential friends, and with reference to fig. 4, the method includes:
performing modeling processing on the socialized online course platform to obtain a multidirectional complex network diagram structure;
acquiring three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure;
calculating the trust degree among all friends by mixed weighting of cognitive trust and interactive trust;
calculating the similarity of texts among the learner interest and hobby data by adopting a cosine similarity method, calculating the similarity of academic achievements recently published by a learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners;
acquiring the geographical position information of each learner;
calculating the comprehensive similarity of the learner within three degrees by combining the geographic position information of the learner according to the trust between the friends and the academic interest similarity;
and selecting a plurality of learners with highest comprehensive similarity as potential friends to recommend and generate a recommendation reason.
Optionally, the obtaining three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure includes:
constructing a direct friend relationship set of the learner according to the complex network graph structure;
forming friend node pairs by nodes which become friends in the complex network graph structure;
searching friend node pairs of two non-friend relationship nodes through the friend node pairs, mining public nodes existing between the two non-friend relationship nodes, and further obtaining a second-degree friend relationship set between all learners of the socialized online course platform;
and performing head node pairing on the obtained second-degree friend relationship and the existing first-degree friend relationship to obtain the third-degree friend relationship among learners, and further obtaining the third-degree friend relationship of all learners in the socialized online course platform.
Optionally, the calculating the trust level between the friends through mixed weighting of recognition trust and interactive trust includes:
determining two learners who have established friend relationships as cognition trust;
determining two learners of which the communication frequency of a pair of friends in the socialized online course platform is higher than a preset condition as interactive trust;
after the recognition trust degree or the interactive trust degree between the two learners is calculated, the weight adjustment is carried out according to the interactive behaviors of the two learners in the socialized online course platform, and the trust degree between friends is calculated.
Optionally, the calculation formula of the trust level between the friends is as follows:
Fr(u,v)＝Kr(u,v)+Ir(u,v)
fr (u, v) represents the trust degree of the learner u to the learner v, and Kr (u, v) represents the trust degree of two learners for knowing and trusting; ir (u, v) represents the trust degree of two learners when the two learners are in interactive trust;
wherein the trust level of the two learners when the two learners are interactive trust is determined according to the access interactive trust and the praise interactive trust of the two learners;
and determining the trust level between friends of the learner within three degrees by calculating the trust level of the second-degree friends and the trust level of the third-degree friends between different learners.
Optionally, the formula for calculating the similarity of the texts between the learner interest and preference data by using a cosine similarity method is as follows:
wherein S is cos (u, v) similarity value representing interest and hobbies between learner u and learner v, u i And v i Respectively representing the interests and hobbies of different learners;
the calculation formula for calculating the similarity of recently published academic achievements of the learner by using the TF-IDF model is as follows:
wherein S is TF-IDF (u, v) similarity value, p, representing academic achievement of learner u and learner v ui And p vi Values representing the ith of the learner u and learner v feature vectors, respectively;
the calculation formula for obtaining the academic interest similarity between learners by performing weighted mixed calculation on the two similarities is as follows:
S(u,v)＝βS cos (u,v)+(1-β)S TF-IDF (u,v)
wherein S (u, v) represents academic interest similarity obtained through final calculation; beta represents the corresponding weight value.
Optionally, the method further comprises:
calculating the distance between two learners according to a longitude and latitude difference value calculation formula of any two points on the earth;
wherein, the calculation formula of the distance between the two learners is as follows:
wherein D (u, v) represents the distance between learners u and v; r represents the average radius of the earth; c (u, v) represents the latitude and longitude difference between learners u and v.
Optionally, the calculation formula of the comprehensive similarity is:
wherein Sim (u, v) represents the integrated similarity between learners u and v; d (u, v) represents the distance between learners u and v; s (u, v) represents the academic interest similarity between learners u and v; t (u, v) represents the degree of confidence between learners u and v.
In another aspect, an embodiment of the present invention further provides a device for recommending potential friends to a learner, where the device includes:
the first module is used for performing modeling processing on the socialized online course platform to obtain a multidirectional complex network diagram structure;
the second module is used for acquiring the three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure;
the third module is used for calculating the trust degree among all friends through mixed weighting of recognition trust and interactive trust;
the fourth module is used for calculating the similarity of texts among the learner interest and hobby data by adopting a cosine similarity method, calculating the similarity of academic achievements recently published by a learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners;
the fifth module is used for acquiring the geographical position information of each learner;
a sixth module, configured to calculate, according to the trust degrees among the friends and the academic interest similarity, a comprehensive similarity of the learner within three degrees in combination with the geographic location information of the learner;
and the seventh module is used for selecting a plurality of learners with the highest comprehensive similarity as potential friends to recommend and generate a recommendation reason.
Another aspect of the embodiments of the present invention further provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Yet another aspect of the embodiments of the present invention provides a computer-readable storage medium, which stores a program, which is executed by a processor to implement the method as described above.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.
The following detailed description of the invention is made with reference to the accompanying drawings:
aiming at the problems in the prior art, the learner with similar professional background, learning interest, knowledge level and even similar geographical position is taken as a research object, potential friends are recommended for the learner according to the relevant data information of the learner in the socialized online course platform, a recommendation reason is provided, the acceptance degree of the learner on the recommended friends is enhanced, and the learning behavior of the learner/especially a cold-start learner is correctly guided and normalized, so that the learner can effectively learn. The method is also helpful for evaluating and predicting potential problems of learners, and provides decision support for the functional evolution and prediction of the socialized online course platform. In the existing research on personalized recommendation algorithms of learners, most learners are provided with resource recommendation services. This type of recommendation service has difficulty in solving personalized recommendation problems for cold-start learners and has no way to assess and predict the developmental trends/potential problems of learner learning.
Aiming at the problems of sparse interaction data and unexplainable property of recommendation of learners in the social online course platform, particularly the problem that a cold-start learner cannot provide accurate friend recommendation of the learner and the like, the invention uses three-degree influence friend relationship and learner IP sign-in information of the learner in the social online course platform to mine potential friends of the learner, calculates the mixed similarity between the learners by combining the learning interest of the learner, carries out the potential friend recommendation of the learner, and provides decision support for the personalized learning content collaborative recommendation of the learner, platform evolution, learner learning trend prediction and the like of the social online course platform.
The method completes learning data missing from the learner in the socialized online course platform by using social data and sign-in data of the learner, and carries out friend recommendation on the learner by using the data, so that the problems that potential friend recommendation cannot be provided for a cold-start learner due to data sparseness are solved. The data completion comprises two parts (friend relationship within three degrees and IP sign-in information), the trust and the similarity between the learners are calculated by utilizing the extracted friend relationship within three degrees and academic interest and hobbies, finally, a final similarity matrix is obtained by a distance matrix obtained by the IP sign-in information and the trust and the similarity between the learners, potential friends of the learners are mined, and a recommendation reason is given. The method comprises the following concrete steps:
step 1: the social online lesson platform is modeled in the form of a undirected complex network graph structure G (V, E), where V represents the set of learners in the social online lesson platform and E represents the set of friend relationships between learners, and if a friend relationship exists between two learners, then a direct relationship (edge) exists between the two vertices in fig. 1. In FIG. 1, U 1 ～U 7 Representing a learner, the lines between the nodes represent direct friend relationships between the learners.
Step 2: and searching second-degree friends and third-degree friends through third-degree influence. In real life, two users who have a common friend are more likely to become friends. For example teacher U 1 U with teacher 3 Mutual friends, student U 2 U as teacher 1 Students, possibly to teacher U 3 Are also of interest, therefore, teacher U 3 Can be used as student U 2 The recommendation target of (2). According to the invention, firstly, a learner direct friend relationship set is obtained through a complex network graph structure of a socialized online course platform, and nodes which are already friends in a complex network form friend node pairs. E.g. learner U 1 The friend set of is { U 2 ,U 3 Is about learner U 1 The friend node pair exists as<U 1 ,U 2 >,<U 1 ,U 3 >. Finding friend node pairs of two non-friend relationship nodes by known friend node pairs, mining common nodes existing between them, e.g. friend node pairs<U 1 ,U 2 >,<U 1 ,U 3 >Presence of a common node U 1 And U is 2 And U 3 Not in friend relationship, the invention can obtain a relation of U 1 Second degree friend relationship of public node, note<U 2 ,U 1 ,U 3 >. By analogy, a two-degree friend relationship set among all learners of the socialized online course platform can be obtained. The invention matches the acquired second-degree friend relationship with the existing first-degree friend relationship to obtain the third-degree friend relationship between learners. Such as a one-degree buddy relationship<U 2 ,U 7 >One degree two friend relationship<U 2 ,U 1 ,U 3 >Will U is 2 As the matched public head node, a three-degree friend relationship is obtained<U 7 ,U 2 ,U 1 ,U 3 >. And in this way, the three-degree friend relationships of all learners in the socialized online course platform are obtained.
And 3, step 3: and calculating the trust degree between friends by mixed weighting of cognitive trust and interactive trust. Wherein in practice a friend relationship has been established between two learners, the present invention defines such friend relationship as cognitive trust. A pair of friends typically communicate frequently in a social online course platform, such as: access home pages, dynamic praise, etc. The present invention defines such behavior as interactive trust between friends. Note that: the interactive trust does not need to be based on the cognitive trust, and can be some accidental information exchange between two strangers. The calculation method is shown in formula (1):
Fr(u,v)＝Kr(u,v)+Ir(u,v) (1)
in the formula (1), fr (u, v) represents the trust of the learner u on the learner v, kr (u, v) is recognition trust and represents whether the learner u and the learner v are already in a friend relationship, if yes, kr (u, v) is set to be a constant value of 0.1, otherwise, 0 and ir (u, v) is interactive trust and represents the interactive behavior of the learner u on the learner v. The invention uses the homepage access and dynamic praise in the interactive behavior to calculate the trust between learners, and each interactive trust calculation method is shown as a formula (2) and a formula (3).
Wherein Ar (u, v) and Zr (u, v) respectively represent the access interactive trust and the like interactive trust of the learner u to the learner v, ia (u, v) and Iz (u, v) respectively represent the access times and the dynamic like times of the learner u to the homepage of the learner v, and Sum (Ia (u, v)) and Sum (Iz (u, v)) respectively represent the total access times and the total like times of the learner u to all the learners. And (4) comprehensively obtaining a calculation method of the interactive trust degree Ir (u, v) according to the notations (2) and (3), as shown in a formula (4).
Wherein
And (3) adjusting the interactive behavior weights in different socialized online course platforms according to actual requirements as parameters, and substituting the weights into a formula (1) through the formula to obtain the trust value among learners.
And (3) calculating the trust between the friends of the learner within the third degree through the second-degree friends and the third-degree friends obtained through the influence of the third degree, wherein the specific calculation method is shown in formulas (5) and (6).
Wherein T is 2 (u, v) represents a second degree friend confidence value between learner u and learner v; s represents a set of second degree friends about learner uIn sum, fr (u, i) represents the confidence value between learner u and learner i, and the denominator 2 represents the number of paths between learner u and learner v.
Wherein T is 3 (u, v) represents a three degree friend confidence value between learner u and learner v; t represents a three degree friend set for learner u, and denominator 3 represents the number of paths between learner u and learner v.
And (4) carrying out mixed weighting on the friend trust degrees within three degrees to obtain the final trust degree of the learner u to the learner v
T (u, v), as shown in equation (7).
T(u,v)＝αT 2 (u,v)+(1-α)T 3 (u,v) (7)
Wherein alpha is a parameter for adjusting the confidence of second-degree and third-degree friends and alpha>0.5. Because second degree buddies tend to be easier to reach than third degree buddies in real life. However, in the social online course platform, it often appears that the friend is a friend of the learner, i.e. a second degree friend of the learner, or a third degree friend of the learner, as shown in fig. 1, the learner U 1 And U 7 . From the perspective of a two-degree friend<U 1 ,U 2 ,U 7 >From the perspective of a friend of three degrees<U 1 ,U 3 ,U 4 ,U 7 >. In the case of this situation, the present invention considers learner U only 1 And U 7 The situation of being a second degree friend relation is just enough.
And 4, step 4: the method comprises the steps of calculating text similarity among learner interest and preference data by adopting a cosine similarity method, calculating similarity of recently published academic achievements (papers) of a learner by using a TF-IDF model, and finally performing weighted mixing on the two methods to calculate the academic interest similarity among learners. Before text calculation is carried out by using cosine similarity, word segmentation processing is carried out on the interest and hobbies of each learner, then word segmentation is carried out, word frequency vectorization is carried out, and finally the text similarity among learners is calculated through a cosine function. The calculation method is shown in formula (8):
wherein S cos (u, v) similarity value u representing interest and hobbies of learner u and learner v, u i And v i Representing the learner's hobbies and interests.
The similarity of recent academic achievements (published papers) of each learner is calculated through the TF-IDF model. The TF-IDF model distinguishes by the frequency with which a word appears in one article and less in other articles. Firstly, traversing all learners to obtain corresponding academic achievement data, then calculating academic achievement vectors of the learners by using a TF-IDF algorithm, and finally calculating the similarity of two learners. The calculation method is shown in formula (9):
wherein S TF-IDF (u, v) similarity values, p, representing academic achievements of learner u and learner v ui And p vi Values representing the ith of learner u and learner v feature vectors. The similarity S of interests and hobbies is obtained cos (u, v) similarity to academic results S TF-IDF (u, v) the final similarity S (u, v) is obtained by weighted mixing, and the calculation formula is shown in formula (10):
S(u,v)＝βS cos (u,v)+(1-β)S TF-IDF (u,v) (10)
and 5: and obtaining corresponding IP information through the check-in information of each learner to determine the geographic position of the learner, for example: schools, companies, communities and the like search the longitude and latitude of the units, calculate the geographic distance between two learners through the longitude and latitude, recommend the learners nearby and facilitate offline communication and cooperation. The method and the device acquire the learner information near the new user through the IP sign-in information, and solve the recommendation problem of the cold-start learner without more available information. The calculation formula of the longitude and latitude difference value of any two points on the earth is shown as a formula (11):
C(u,v)＝sin(MLat(u)×sin(MLat(v))×cos(MLon(u)-MLon(v))+cos(MLat(u))×cos(MLat(v)) (11)
wherein C (u, v) represents the difference in longitude and latitude between learners u and v; MLat (u) represents the latitude of learner u; MLat (v) represents the latitude of learner v; MLon (u) represents the longitude of learner u; MLon (v) represents the longitude of learner v. The final distance between learners u and v is shown in equation (12):
where D (u, v) represents the distance (km) between learners u and v, and R represents the average radius of the earth.
Step 6: after the friend trust and the similarity in three degrees are obtained through the formula (7) and the formula (10), the friend trust and the similarity in three degrees are weighted and mixed, and the comprehensive similarity Sim (u, v) of the learners in three degrees is calculated by combining the geographic distance between the two learners. The integrated similarity calculation formula is shown in formula (13):
and theta is a mixed parameter fusing the confidence and the similarity.
And 7: and selecting the Top-N learner with the highest similarity as a potential friend to recommend, forming a recommendation statement according to the trust degree, the academic interest similarity and the geographic distance, and explaining a recommendation reason to the learner. The recommendation statement is constructed with a complete semantically coherent sentence template, e.g., "there are () bits of common friends interested in () the study, and you are () kilometers away. And selecting features according to a personalized algorithm to construct an interpretation statement, so that the acceptability of a recommendation result is enhanced.
Referring to fig. 2, the embodiment of the present invention takes a social online course platform student network as an embodiment, and extracts data such as friend relationships, access information, like information, hobby information, interests, academic achievement, check-in information, and the like of some users in the student network. Firstly, the invention constructs a friend relation matrix, an access matrix and a praise matrix to calculate the trust of the learner, and obtains the trust of the learner matrix. And secondly, mixing and weighting the learner interest similarity matrix and the academic achievement similarity matrix to obtain an academic interest similarity matrix. And thirdly, converting the sign-in information into longitude and latitude information to calculate a distance matrix between learners. And finally, combining the three to obtain a final learner similarity matrix, and combining a recommendation reason to carry out TOP-N recommendation. The method verifies the performance of the method through accuracy, recall rate, harmonic mean value F1-measure and the like, and a specific flow chart is shown in figure 2.
When the algorithm stops, the effect of the learner's potential friend recommendation in FIG. 1 is shown in FIG. 3.
In summary, the present invention has the following features:
(1) Potential friends are mined, nodes which can become friends of learners are extracted through friend relation information and IP check-in information of third degree influence of learners in a social online course platform, because the direct association relation network of learners is sparse, learners which can become friends are predicted through the method, and therefore the learning relation network of learners in the social online course platform is completed. Meanwhile, the method can effectively solve the recommendation problem of the cold start learner.
(2) And (4) integrating the trust degree, the similarity and the mixed recommendation of the IP information, predicting the preference of the learners by utilizing the social network information, and screening out the learners with higher similarity by combining the academic interest among the learners. In consideration of the actual situation, the learner prefers to be a friend with a closely spaced person or is somewhat more likely to be interested in a similar degree, such as a classmate with city, school, or even dormitory. Therefore, the invention takes the learner check-in information as the influence factor of the recommendation.
(3) Interpretability recommendation, in past socialized online course platform recommendation, recommendation interpretability is not mentioned yet, and the method provides comprehensive recommendation reasons for the combination of the learner trust, academic interest similarity and geographic distance, so that the reliability of the learner on recommendation effect is enhanced.
Compared with the prior art, the invention has the following advantages:
the method and the system have the advantages that association relation data of learners, particularly inert learners and cold-start learners are sparse, and accurate recommendation is difficult to perform. The learner potential friend mining method can better describe the potential association relationship between learners, and particularly for cold-starting learners, the data sparsity problem in a socialized online course platform is effectively relieved, so that learners obtain more accurate and efficient service and management in the socialized online course platform.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. 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/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units 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 or a part thereof which substantially contributes to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute 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.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A method for a learner to personalize interpretable potential friend recommendations, comprising:
performing modeling processing on the socialized online course platform to obtain a multidirectional complex network diagram structure;
acquiring three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure;
calculating the trust degree among all friends by mixed weighting of cognitive trust and interactive trust;
calculating the similarity of texts among the learner interest and hobby data by adopting a cosine similarity method, calculating the similarity of academic achievements recently published by a learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners;
acquiring the geographical position information of each learner;
calculating the comprehensive similarity of the learner within three degrees by combining the geographic position information of the learner according to the trust between the friends and the academic interest similarity;
and selecting a plurality of learners with highest comprehensive similarity as potential friends to recommend and generate a recommendation reason.
2. The method as claimed in claim 1, wherein the step of obtaining three-degree friend relationships of all learners in a social online lesson platform according to the complex network diagram structure comprises:
constructing a direct friend relationship set of the learner according to the complex network graph structure;
forming friend node pairs by nodes which become friends in the complex network graph structure;
searching friend node pairs of two non-friend relationship nodes through the friend node pairs, mining public nodes existing between the two non-friend relationship nodes, and further obtaining a second-degree friend relationship set between all learners of the socialized online course platform;
and performing head node pairing on the obtained second-degree friend relationship and the existing first-degree friend relationship to obtain the third-degree friend relationship among learners, and further obtaining the third-degree friend relationships of all learners in the socialized online course platform.
3. The method as claimed in claim 1, wherein the calculating the trust degree between friends through mixed weight of cognitive trust and interactive trust comprises:
determining two learners who have established friend relationships as cognition trust;
determining two learners with communication frequency higher than a preset condition of a pair of friends in a socialized online course platform as interactive trust;
after the recognition trust degree or the interactive trust degree between the two learners is calculated, the weight adjustment is carried out according to the interactive behaviors of the two learners in the socialized online course platform, and the trust degree between friends is calculated.
4. The learner personalized interpretable potential friend recommendation method of claim 3,
the calculation formula of the trust between the friends is as follows:
Fr(u，v)＝Kr(u，v)+Ir(u，v)
fr (u, v) represents the trust degree of the learner u to the learner v, and Kr (u, v) represents the trust degree of two learners for knowing and trusting; ir (u, v) represents the trust degree of two learners when the two learners are in interactive trust;
wherein the trust level of the two learners when the two learners are interactive trust is determined according to the access interactive trust and the like interactive trust of the two learners;
and determining the trust level between friends of the learner within three degrees by calculating the trust level of the second-degree friends and the trust level of the third-degree friends between different learners.
5. The method as claimed in claim 1, wherein the learner's personalized interpretable potential friend recommendation method,
the calculation formula for calculating the similarity of the texts among the learner interest and hobby data by adopting a cosine similarity method is as follows:
wherein S is cos (u, v) similarity value representing interest and hobbies between learner u and learner v, u i And v i Respectively representing the interests and hobbies of different learners;
the calculation formula for calculating the similarity of recently published academic achievements of the learner by using the TF-IDF model is as follows:
wherein S is TF-IDF (u, v) similarity value, p, representing academic achievement of learner u and learner v ui And p vi Values representing the ith of the learner u and learner v feature vectors, respectively;
the calculation formula for obtaining the academic interest similarity between learners by performing weighted mixed calculation on the two similarities is as follows:
S(u，v)＝βS cos (u，v)+(1-β)S TF-IDF (u，v)
wherein S (u, v) represents academic interest similarity obtained through final calculation; beta represents the corresponding weight value.
6. The learner-customized interpretable potential friend recommendation method of claim 1, further comprising:
calculating the distance between two learners according to a longitude and latitude difference value calculation formula of any two points on the earth;
wherein, the calculation formula of the distance between the two learners is as follows:
wherein D (u, v) represents the distance between learners u and v; r represents the average radius of the earth; c (u, v) represents the latitude and longitude difference between learners u and v.
7. The learner personalized interpretable potential friend recommendation method of claim 1,
the calculation formula of the comprehensive similarity is as follows:
wherein Sim (u, v) represents the integrated similarity between learners u and v; d (u, v) represents the distance between learners u and v; s (u, v) represents the academic interest similarity between learners u and v; t (u, v) represents the degree of confidence between learners u and v.
8. A learner personalized interpretable potential friend recommendation device comprising:
the first module is used for performing modeling processing on the socialized online course platform to obtain a multidirectional complex network diagram structure;
the second module is used for acquiring the three-degree friend relationships of all learners in the socialized online course platform according to the complex network graph structure;
the third module is used for calculating the trust degree among the friends through mixed weighting of the cognitive trust and the interactive trust;
the fourth module is used for calculating the similarity of texts among the learner interest and hobby data by adopting a cosine similarity method, calculating the similarity of academic achievements recently published by a learner by using a TF-IDF model, and performing weighted mixed calculation on the two similarities to obtain the academic interest similarity among the learners;
the fifth module is used for acquiring the geographical position information of each learner;
a sixth module, configured to calculate, according to the trust degrees among the friends and the academic interest similarity, a comprehensive similarity of the learner within three degrees in combination with the geographic location information of the learner;
and the seventh module is used for selecting a plurality of learners with the highest comprehensive similarity as potential friends to recommend and generate a recommendation reason.
9. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program implements the method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859182.2A CN115357632A (en) | 2022-07-21 | 2022-07-21 | Learner personalized interpretable potential friend recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210859182.2A CN115357632A (en) | 2022-07-21 | 2022-07-21 | Learner personalized interpretable potential friend recommendation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115357632A true CN115357632A (en) | 2022-11-18 |
Family
ID=84031084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210859182.2A Pending CN115357632A (en) | 2022-07-21 | 2022-07-21 | Learner personalized interpretable potential friend recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115357632A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102695121A (en) * | 2011-03-25 | 2012-09-26 | 北京千橡网景科技发展有限公司 | Method and system for pushing friend information for user in social network |
| CN104202319A (en) * | 2014-08-28 | 2014-12-10 | 北京淘友天下科技发展有限公司 | Method and device for social relation recommendation |
| CN105893639A (en) * | 2016-06-29 | 2016-08-24 | 合肥民众亿兴软件开发有限公司 | Network service recommending method based on position of mobile user |
| CN107506455A (en) * | 2017-08-29 | 2017-12-22 | 重庆邮电大学 | A kind of friend recommendation method for merging user social contact circle similarity |
| CN108427715A (en) * | 2018-01-30 | 2018-08-21 | 重庆邮电大学 | A kind of social networks friend recommendation method of fusion degree of belief |
| CN108874821A (en) * | 2017-05-11 | 2018-11-23 | 腾讯科技（深圳）有限公司 | A kind of application recommended method, device and server |
| CN109190033A (en) * | 2018-08-23 | 2019-01-11 | 微梦创科网络科技（中国）有限公司 | A kind of user's friend recommendation method and system |
| CN110929171A (en) * | 2019-11-26 | 2020-03-27 | 湖南科技职业学院 | Interest point recommendation method based on scene and social network location |
-
2022
- 2022-07-21 CN CN202210859182.2A patent/CN115357632A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102695121A (en) * | 2011-03-25 | 2012-09-26 | 北京千橡网景科技发展有限公司 | Method and system for pushing friend information for user in social network |
| CN104202319A (en) * | 2014-08-28 | 2014-12-10 | 北京淘友天下科技发展有限公司 | Method and device for social relation recommendation |
| CN105893639A (en) * | 2016-06-29 | 2016-08-24 | 合肥民众亿兴软件开发有限公司 | Network service recommending method based on position of mobile user |
| CN108874821A (en) * | 2017-05-11 | 2018-11-23 | 腾讯科技（深圳）有限公司 | A kind of application recommended method, device and server |
| CN107506455A (en) * | 2017-08-29 | 2017-12-22 | 重庆邮电大学 | A kind of friend recommendation method for merging user social contact circle similarity |
| CN108427715A (en) * | 2018-01-30 | 2018-08-21 | 重庆邮电大学 | A kind of social networks friend recommendation method of fusion degree of belief |
| CN109190033A (en) * | 2018-08-23 | 2019-01-11 | 微梦创科网络科技（中国）有限公司 | A kind of user's friend recommendation method and system |
| CN110929171A (en) * | 2019-11-26 | 2020-03-27 | 湖南科技职业学院 | Interest point recommendation method based on scene and social network location |
Non-Patent Citations (1)
| Title |
|---|
| 孙赛美 等: "一种基于信任度和研究兴趣的学者推荐方法" * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Students' learning style detection using tree augmented naive Bayes | |
| Abech et al. | A model for learning objects adaptation in light of mobile and context-aware computing | |
| Bordogna et al. | On predicting and improving the quality of Volunteer Geographic Information projects | |
| Fogli et al. | Exploiting semantics for context-aware itinerary recommendation | |
| US20190354887A1 (en) | Knowledge graph based learning content generation | |
| Meehan et al. | Aggregating social media data with temporal and environmental context for recommendation in a mobile tour guide system | |
| CN111061946A (en) | Scenario content recommendation method and device, electronic equipment and storage medium | |
| CN109635206B (en) | Personalized recommendation method and system integrating implicit feedback and user social status | |
| Smith | Macrostructure from microstructure: Generating whole systems from ego networks | |
| Braunhofer et al. | STS: A Context-Aware Mobile Recommender System for Places of Interest. | |
| Berkani | A semantic and social‐based collaborative recommendation of friends in social networks | |
| Kearney et al. | The iPAC scale: A survey to measure distinctive mobile pedagogies | |
| Hassan et al. | Smart media-based context-aware recommender systems for learning: A conceptual framework | |
| da S Dias et al. | Recommender system for learning objects based in the fusion of social signals, interests, and preferences of learner users in ubiquitous e-learning systems | |
| US20180247214A1 (en) | Network node analysis and link generation system | |
| CN115146161A (en) | Personalized learning resource recommendation method and system based on content recommendation | |
| CN114398556A (en) | Learning content recommendation method, device, equipment and storage medium | |
| Bueno et al. | Intellectual capital as a strategic model to create innovation in new technology based firms | |
| Halimi et al. | Semantic web based learning styles identification for social learning environments personalization | |
| de Graaff et al. | Towards geosocial recommender systems | |
| CN115357632A (en) | Learner personalized interpretable potential friend recommendation method and device | |
| Fisher | Social space diffusion: applications of a latent space model to diffusion with uncertain ties | |
| Ramírez-Noriega et al. | Determination of the course sequencing to intelligent tutoring systems using an ontology and Wikipedia | |
| CN112818196B (en) | Data processing method, equipment, electronic device and storage medium based on electronic learning platform | |
| Wang et al. | Matching area selection of an underwater terrain navigation database with fuzzy multi-attribute decision making method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221118 |