Disclosure of Invention
In view of the above, the present invention provides a method and a system for personalized recommendation of online medical education resources, so as to solve or at least partially solve the technical problem that the method in the prior art needs to actively search and acquire learning resources, and thus cannot perform personalized recommendation of the learning resources.
The invention provides a personalized recommendation method of online medical education resources in a first aspect, which comprises the following steps:
step S1: acquiring original data of a user, and labeling the original data, wherein the original data comprises a case, learning resources and user behavior data;
step S2: constructing an individualized recommendation model according to the labeled data, wherein the individualized recommendation model comprises a case recommendation model and a learning resource recommendation model, the case recommendation model adopts a content-based collaborative filtering recommendation algorithm, the degree of interest of a user in a case is determined according to first behavior data of the user in the case, and the learning resource recommendation model adopts a label-based algorithm and is constructed after determining a label of a learning resource of interest of the user according to second behavior data of the user in the learning resource;
step S3: and generating a recommendation result for the target user according to the personalized recommendation model.
In one embodiment, step S1 specifically includes:
and manually marking the original data according to the dimensions of departments, diseases, scenes, difficulties and purposes, and constructing a user data dictionary and a content data dictionary.
In one embodiment, in step S2, the case recommendation model is constructed by:
acquiring first behavior data of a user on a case, wherein the first behavior data comprises a user purchase case, a user evaluation case and a user learning case;
according to a preset rule, weights are given to a user purchase case, a user evaluation case and a user learning case;
adopting a collaborative filtering recommendation algorithm based on content and constructing a user-case interest degree model according to the given weight;
and constructing a case recommendation model based on the user-case interestingness model and the first behavior data of the user on the case.
In one embodiment, in step S2, the resource recommendation model is learned and constructed by:
acquiring second behavior data of the user on the case, wherein the second behavior data comprises user click, user learning and user evaluation;
counting the occurrence times of the classification labels corresponding to the second behavior data;
and constructing a learning resource recommendation model according to the occurrence times of the classification labels and the threshold value.
In one embodiment, step S3 specifically includes:
recommending relevant cases for the user based on the case recommendation model, and recommending a learning plan for the user based on the learning resource recommendation model.
In one embodiment, the user behavior data further includes a user representation, and when the target user is a new user, the method further comprises:
classifying the user portrait data according to the user identity, the academic calendar, the gender and the job title;
and recommending the learning resources corresponding to the classified categories for the target user.
In one embodiment, the case has a corresponding lesion and disease type, the method further comprising:
combining a plurality of cases under the same disease category to construct the similarity among the cases;
and generating a recommendation result for the target user by combining the similarity between the cases and the case recommendation model.
Based on the same inventive concept, the second aspect of the present invention provides a personalized recommendation system for online medical education resources, comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring original data of a user and marking the original data, and the original data comprises a case, learning resources and user behavior data;
the construction module is used for constructing an individualized recommendation model according to the labeled data, wherein the individualized recommendation model comprises a case recommendation model and a learning resource recommendation model, the case recommendation model adopts a content-based collaborative filtering recommendation algorithm, the degree of interest of a user in a case is determined according to first behavior data of the user in the case, and the learning resource recommendation model adopts a label-based algorithm, and the label of the learning resource in which the user is interested is determined according to second behavior data of the user in the learning resource;
and the recommendation module is used for generating a recommendation result for the target user according to the personalized recommendation model.
In one embodiment, the acquisition module is specifically configured to:
and manually marking the original data according to the dimensions of departments, diseases, scenes, difficulties and purposes, and constructing a user data dictionary and a content data dictionary.
Based on the same inventive concept, a third aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed, performs the method of the first aspect.
One or more technical solutions in the embodiments of the present application have at least one or more of the following technical effects:
according to the method provided by the invention, after the original data of the collected user are labeled, the personalized recommendation model is constructed, and then the recommendation result is generated for the target user according to the personalized recommendation model.
Compared with the prior art, the method has the advantages that the user needs to actively search the education resources, the personalized recommendation model comprises a case recommendation model and a learning resource recommendation model, the case recommendation model adopts a content-based collaborative filtering recommendation algorithm, the degree of interest of the user in the case is determined according to the first behavior data of the user in the case, the learning resource recommendation model is constructed by adopting a label-based algorithm and the label of the learning resource interested by the user is determined according to the second behavior data of the user in the learning resource, namely, different recommendation models are adopted according to different learning contents, and the personalized recommendation of the resources is realized. The method can be used for recommending the target user in multiple aspects, so that the time consumed by the target user for actively searching is reduced, the learning cost of the user is reduced, and the fragmented learning requirement of the user is really met.
Furthermore, original data are manually marked according to dimensions of departments, diseases, scenes, difficulty and purposes, a user data dictionary and a content data dictionary are built, and a basis is provided for the subsequent building of a recommendation model.
Furthermore, a collaborative filtering recommendation algorithm based on content is adopted, a user-case interest degree model is constructed according to the given weight and is used as a case recommendation model, and the recommendation of related cases can be carried out according to the interest degree of the user to the learned cases, so that personalized recommendation can be further realized. In addition, the similarity of the disease area and disease species is constructed, and the user-case interest degree model is supplemented, so that recommended resources are closer to user behaviors, and case coverage is increased.
Furthermore, a learning resource recommendation model is constructed according to the occurrence times of the classification labels and the threshold value by adopting a label-based recommendation algorithm, so that the occurrence times of the recommendation labels can meet the resources corresponding to the threshold value, and the individual requirements of the user are met. In order to avoid the problem of cold start, the invention provides primary learning plans aiming at users in different levels through statistics and label discrimination, greatly meets the requirement of users on fragmented learning, and increases the possibility of active learning of the users.
Detailed Description
The invention provides an on-line medical education resource personalized recommendation method and system, which are used for solving the technical problem that the learning resources are required to be obtained through active search and cannot be personalized and recommended in the prior art. The concept of personalized recommendation is introduced into the field of medical education, cases, learning resources and user behavior data of the user are obtained, analysis and modeling are carried out, so that directional pushing of the education resources is constructed, the learning condition of the user can be analyzed in real time, data driving is achieved, the learning cost of the user is reduced, and the technical effect of personalized recommendation is achieved.
In order to achieve the technical effects, the general idea of the invention is as follows:
the method comprises the steps of firstly, collecting original data of a user, manually marking knowledge point labels to which resources in the original data belong to form a data set with an effective scale, actively collecting user behavior data of online users, carrying out effective analysis, forming preference degrees of the users to the resources through statistical analysis, adopting content-based recommendation algorithm and label-based recommendation algorithm to carry out hybrid calculation, and respectively constructing a case recommendation model and a learning resource recommendation model so as to recommend optimal learning resources for the users. The technical effect of intelligently and efficiently generating recommended resources for the target user is achieved.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The embodiment provides a personalized recommendation method for online medical education resources, please refer to fig. 1, and the method comprises the following steps:
step S1 is first executed: the method comprises the steps of collecting original data of a user and marking the original data, wherein the original data comprise a case, learning resources and user behavior data.
Specifically, the learning resources include learning contents other than cases, such as lessons, examination exercises, knowledge documents, and the like. The user behavior data is divided into behaviors for cases and behaviors for learning resources according to different learning contents. The original data of the user can be obtained through the buried points, and for example, the original data comprises the learning achievement, the effective learning duration, the click times and the like of the user.
In one embodiment, step S1 specifically includes:
and manually marking the original data according to the dimensions of departments, diseases, scenes, difficulties and purposes, and constructing a user data dictionary and a content data dictionary.
Specifically, the original data are manually labeled according to dimensions of departments, diseases and the like, so as to determine labels corresponding to the data contents, and then different data are adopted for training according to business needs at a later stage.
The user data dictionary comprises tag names and tags, for example, the tag names comprise platform user classifications, organization identities, user identities and scholarship, and tag values under the platform user classification tags comprise: 1 medical worker, 2 medical students, 3 medical health practitioners and 4 ordinary users. The tag values under the institution identity tag include: 1. student, 2, teacher. The user identity may be further subdivided according to the job title, for example, into physicians, nurses, pharmacists, etc., and the physicians may be further subdivided into doctors, resident physicians, treating physicians, vice-chief physicians, etc.
And the content data dictionary also comprises tag names and tag values, and the tag names comprise: examination, subject, department, question type, content quality, etc. The label values of the test include: the system comprises 1 department examination of an institution, 2 transfer training examination, 3 graduation examination, 4 medical practitioner examination and the like.
Then, step S2 is executed: and constructing an individualized recommendation model according to the labeled data, wherein the individualized recommendation model comprises a case recommendation model and a learning resource recommendation model, the case recommendation model adopts a content-based collaborative filtering recommendation algorithm, the degree of interest of a user in a case is determined according to first behavior data of the user in the case, and the learning resource recommendation model adopts a label-based algorithm and is constructed after a label of a learning resource which the user is interested in is determined according to second behavior data of the user in the learning resource.
Specifically, the personalized recommendation model may be constructed according to the original data labeled in step S1, for example, the labeled data is divided into a training set, a test set, and a verification set according to a certain proportion, and then the model is constructed by using a neural network method. The method specifically comprises the steps of constructing different models on a training set by continuously adjusting algorithm parameters, predicting each model on a test set, selecting an optimal model through result comparison, and testing the algorithm models through recall ratio and precision ratio on a verification set.
In the embodiment, when the personalized recommendation model is constructed, the content-based collaborative filtering recommendation algorithm and the tag-based recommendation algorithm are comprehensively adopted for mixed calculation. For case resources, a collaborative filtering algorithm based on content is adopted, and for other learning resources, a recommendation algorithm based on labels is adopted.
In one embodiment, in step S2, the case recommendation model is constructed by:
acquiring first behavior data of a user on a case, wherein the first behavior data comprises a user purchase case, a user evaluation case and a user learning case;
according to a preset rule, weights are given to a user purchase case, a user evaluation case and a user learning case;
adopting a collaborative filtering recommendation algorithm based on content and constructing a user-case interest degree model according to the given weight;
and constructing a case recommendation model based on the user-case interestingness model and the first behavior data of the user on the case.
Specifically, the first behavior data of the case of the user is stored in the database, and the user evaluation case is that the mental experience preset rule of the user in the whole case learning process can be set according to the actual situation, for example, the weights of the user purchase case, the user evaluation case and the user learning case are respectively set to 3, 4 and 3, which shows that the user purchase case is as important as the user learning case, and the user evaluation case is more important than the other two cases.
For example, please refer to fig. 2, which is a schematic diagram of a user-case interest degree model constructed in the embodiment of the present invention, a user preference score matrix is an embodiment of quantification of interest degree of a user on learning resources, and is implemented by quantifying the user preference score matrix, so as to more clearly distinguish real interest degree caused by user behavior, and thus, better similarity quantification can be obtained. The user purchases a case score of 3, learns the case score of 3 and evaluates and reviews the case score of 4, namely a preference score matrix of the user for the case is constructed, and the user learns the scores of five scores (mark), 0, 1-30, 30-70, 70-90 and 90-100 through the historical data statistical analysis of the user, wherein each score has a corresponding interest degree score (score). Wherein, when the mark is 0 time division, the corresponding score is 1, and when the mark is 1-30 time division, the corresponding score is 2. And the user evaluation means that the user actively scores learned cases in a star scale (comment _ score), and the user evaluation score is divided into five grades, and the user evaluation score is 0.8, namely the score of the interest degree of the user evaluation behavior to the cases. comment-score is 1 min, corresponding to a score of 0.8, mark is 2 min, corresponding to a score of 1.6. Then, the product is processed
And then, constructing a case recommendation model based on the user-case interestingness model and the first behavior data of the user on the case, so as to find the similarity degree of two cases, wherein if the case is taken as the score of 1, the user 1 purchases the case A, learns the case B and learns the case C, the user 2 purchases the case A and learns the case C, and the user 3 purchases the case A and learns the case C, the highest similarity degree of the case A and the case C can be obtained, so that the case C can be recommended to other users who only learn the case A.
In one embodiment, in step S2, the resource recommendation model is learned and constructed by:
acquiring second behavior data of the user on the case, wherein the second behavior data comprises user click, user learning and user evaluation;
counting the occurrence times of the classification labels corresponding to the second behavior data;
and constructing a learning resource recommendation model according to the occurrence times of the classification labels and the threshold value.
Specifically, the main ideas of construction are: firstly, counting the most frequently used labels of each user, then counting the learning resources with the most frequency of being marked by the labels for each label, firstly finding the frequently used labels of a target user, then finding the relevant learning resources with the labels and recommending the learning resources to the target user. Preferably, each behavior can be given different weights, and the current label list with the strongest user association is counted, so that the hottest educational resources in the labels with the strongest user association can be formed and integrated into a learning plan to be pushed to the user.
For example, a user identity is that a student user is reading in the subject, clicks a medical examination question and learns, a classification label corresponding to a corresponding question bank can be obtained, the occurrence frequency is recorded for 1 time, in addition, the times of the label are accumulated in clicking and learning, then the times of learning and clicking of various resources are counted to perform sorting, and therefore the resources with the top sorting can be recommended.
In addition, the user can actively add some labels to the courses or cases, and the real interest of the user can be reflected better. For example, if a student user is reading the identity of the student, frequently clicks and learns the examination questions of the medical practitioners by analyzing the behavior data of the student user, and learns some cases related to appendicitis in general surgery, the student user is firstly recommended the examination questions of the medical practitioners in recent years, and relevant surgical appendicitis learning courses are selected for recommendation, and some knowledge documents are attached to the study courses for free downloading.
Step S3 is executed next: and generating a recommendation result for the target user according to the personalized recommendation model.
Specifically, relevant cases are recommended for the user based on a case recommendation model, and a learning plan is recommended for the user based on a learning resource recommendation model.
In one embodiment, the user behavior data further includes a user representation, and when the target user is a new user, the method further comprises:
classifying the user portrait data according to the user identity, the academic calendar, the gender and the job title;
and recommending the learning resources corresponding to the classified categories for the target user.
Specifically, data may be gathered by logic that lets users fill in questionnaire information, and the users are subdivided into categories that are already in the user data dictionary using a DB-SCAN (sensitivity-Based Clustering of Applications with Noise) Density-Based Clustering algorithm. Therefore, when the target user is a new user, appropriate learning resources can be recommended for the target user according to the subdivided classification, and the problem of cold start is solved.
In one embodiment, the case has a corresponding lesion and disease type, the method further comprising:
combining a plurality of cases under the same disease category to construct the similarity among the cases;
and generating a recommendation result for the target user by combining the similarity between the cases and the case recommendation model.
Please refer to fig. 3, which is a schematic structural diagram of a case recommendation model, and the case knowledge is covered mainly through three dimensions to realize effective recommendation, specifically including three aspects of user cold start, user-case collaborative filtering, and case content similarity.
Specifically, the user-case collaborative filtering is recommendation based on behavior similarity, specifically including user-case behavior, user-case interest, and case a-case B similarity, which is a recommendation method mainly adopted by a case recommendation model. In order to further improve the recommendation effect, recommendations similar to the case content are also proposed for cold start.
Because all cases are divided into the ward and the disease category, different disease categories are arranged under each ward, and a plurality of cases are arranged under each disease category, other cases with higher similarity can be recommended for the user by constructing the similarity among the cases. For example, when the user learns the a1 case, the user may also be interested in other cases (a2) that are of the same disease species as the a1 case. In a specific implementation process, a score is calculated for the interest degree of each case of a user by a content-based recommendation algorithm, then a plurality of cases under the same disease category are combined and comprehensively sequenced to form a final recommendation list of the user and the cases, and the final recommendation list is presented to the user according to a score reverse-order display method in a display process.
In order to solve the problem of cold start, the new user may also create a ranking list of the degree of popularity (for example, a purchase ranking list of the week, a ranking list of the degree of popularity, and a ranking list of new cases) by counting the number of times of purchase of each case and the number of times of evaluation of each case by time in the last week or month, and perform indiscriminate recommendation to increase the user behavior.
Generally speaking, the invention adopts different recommendation models aiming at different learning contents, and realizes the personalized recommendation of resources. The method can be used for recommending the target user in multiple aspects, so that the time consumed by the target user for actively searching is reduced, the learning cost of the user is reduced, and the fragmented learning requirement of the user is really met.
Furthermore, original data are manually marked according to dimensions of departments, diseases, scenes, difficulty and purposes, a user data dictionary and a content data dictionary are built, and a basis is provided for the subsequent building of a recommendation model.
Furthermore, a collaborative filtering recommendation algorithm based on content is adopted, a user-case interest degree model is constructed according to the given weight and is used as a case recommendation model, and the recommendation of related cases can be carried out according to the interest degree of the user to the learned cases, so that personalized recommendation can be further realized. In addition, the similarity of the disease area and disease species is constructed, and the user-case interest degree model is supplemented, so that recommended resources are closer to user behaviors, and case coverage is increased.
Furthermore, a learning resource recommendation model is constructed according to the occurrence times of the classification labels and the threshold value by adopting a label-based recommendation algorithm, so that the occurrence times of the recommendation labels can meet the resources corresponding to the threshold value, and the individual requirements of the user are met. In order to avoid the problem of cold start, the invention provides primary learning plans aiming at users in different levels through statistics and label discrimination, greatly meets the requirement of users on fragmented learning, and increases the possibility of active learning of the users.
Example two
Based on the same inventive concept as the embodiment, the present application also provides a personalized recommendation system for online medical education resources, please refer to fig. 4, the system includes:
the acquisition module 201 is configured to acquire original data of a user and label the original data, where the original data includes a case, a learning resource, and user behavior data;
the construction module 202 is used for constructing an individualized recommendation model according to the labeled data, wherein the individualized recommendation model comprises a case recommendation model and a learning resource recommendation model, the case recommendation model adopts a content-based collaborative filtering recommendation algorithm, the degree of interest of a user in a case is determined according to first behavior data of the user in the case, and the learning resource recommendation model adopts a label-based algorithm, and the label of the learning resource in which the user is interested is determined according to second behavior data of the user in the learning resource;
and the recommending module 203 is used for generating a recommending result for the target user according to the personalized recommending model.
In a specific implementation process, the architecture of the personalized recommendation system for online medical education resources is shown in fig. 5, and the recommendation system can be integrated into an educational medical APP. The method mainly comprises two processes of off-line training and on-line recommendation. The off-line training is mainly to construct a good personalized recommendation model, and the on-line recommendation is to calculate the on-line data according to the model parameters stored in the redis cache database and obtain a recommendation result.
Wherein, the off-line training process is as follows:
1. the method comprises the steps of data sample extraction and feature extraction, wherein existing historical data (original data of a user), namely cases, learning resources and user behavior data, are collected from a database, data screening processing is carried out, such as the cleaning of missing values and dirty data, so that a good data sample is constructed, then the data sample is divided into a training set and a test set according to a proportion, the test process of an algorithm model is carried out through the recall ratio and the precision ratio of the verification set, and the verification set is a feature vector.
2. And in the model training process, different models are constructed on a training set by continuously adjusting algorithm parameters, the prediction of each model (a case recommendation model and a learning resource recommendation model) is carried out on a test set, and an optimal model is selected by result comparison, so that the parameters of the models are stored in a redis database for online recommendation.
The online recommendation process is as follows:
1. formatting the on-line data and generating a feature vector of each piece of data, wherein the on-line data needs to be formatted according to a training set generation mode because the original data is not finally required, and the adjusted model can be directly called for calculation;
2. the prediction scores of the resources are the model calculation results, the recommendation algorithm aims to calculate the interest degree of the user on the learning resources through the historical behavior data of the user, the interested quantitative standard is the prediction score, and therefore the learning resources which are considered to be really interested by the user and have high prediction scores are selected. The formed recommendation service can be pushed to the user through the APP.
In an embodiment, the acquisition module 201 is specifically configured to:
and manually marking the original data according to the dimensions of departments, diseases, scenes, difficulties and purposes, and constructing a user data dictionary and a content data dictionary.
In one embodiment, in the construction module 202, the case recommendation model is specifically constructed by:
acquiring first behavior data of a user on a case, wherein the first behavior data comprises a user purchase case, a user evaluation case and a user learning case;
according to a preset rule, weights are given to a user purchase case, a user evaluation case and a user learning case;
adopting a collaborative filtering recommendation algorithm based on content and constructing a user-case interest degree model according to the given weight;
and constructing a case recommendation model based on the user-case interestingness model and the first behavior data of the user on the case.
In one embodiment, in the building module 202, the resource recommendation model is learned by:
acquiring second behavior data of the user on the case, wherein the second behavior data comprises user click, user learning and user evaluation;
counting the occurrence times of the classification labels corresponding to the second behavior data;
and constructing a learning resource recommendation model according to the occurrence times of the classification labels and the threshold value.
In one embodiment, the recommending module 203 is specifically configured to:
recommending relevant cases for the user based on the case recommendation model, and recommending a learning plan for the user based on the learning resource recommendation model.
In one embodiment, the user behavior data further comprises a user representation, and when the target user is a new user, the system further comprises a classification module for:
classifying the user portrait data according to the user identity, the academic calendar, the gender and the job title;
and recommending the learning resources corresponding to the classified categories for the target user.
In one embodiment, the case has a corresponding ward and a disease category, and the system further comprises a similarity construction module for:
combining a plurality of cases under the same disease category to construct the similarity among the cases;
and generating a recommendation result for the target user by combining the similarity between the cases and the case recommendation model.
Since the system described in the second embodiment of the present invention is a system adopted for implementing the method for personalized recommendation of online medical education resources in the first embodiment of the present invention, based on the method described in the first embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the system, and thus, details are not described herein. All systems adopted by the method of the first embodiment of the present invention are within the intended protection scope of the present invention.
EXAMPLE III
Referring to fig. 6, based on the same inventive concept as the embodiment, the embodiment provides a computer-readable storage medium 400, on which a computer program 411 is stored, which when executed implements the method of the embodiment one.
Since the computer-readable storage medium introduced in the third embodiment of the present invention is a computer-readable storage medium used for implementing the method for personalized recommendation of online medical education resources in the first embodiment of the present invention, based on the method introduced in the first embodiment of the present invention, persons skilled in the art can understand the specific structure and deformation of the computer-readable storage medium, and therefore, no further description is given here. Any computer readable storage medium used in the method of the first embodiment of the present invention falls within the intended scope of the present invention.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made in the embodiments of the present invention without departing from the spirit or scope of the embodiments of the invention. Thus, if such modifications and variations of the embodiments of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to encompass such modifications and variations.