CN112686057A - College student psychological consultation appointment recommendation method and system - Google Patents
College student psychological consultation appointment recommendation method and system Download PDFInfo
- Publication number
- CN112686057A CN112686057A CN202110024240.5A CN202110024240A CN112686057A CN 112686057 A CN112686057 A CN 112686057A CN 202110024240 A CN202110024240 A CN 202110024240A CN 112686057 A CN112686057 A CN 112686057A
- Authority
- CN
- China
- Prior art keywords
- psychological
- student
- psychologist
- vector
- category
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a college student psychological consultation appointment recommendation method and system. The recommendation method performs problem domain mapping on psychological consultation appointment registration information of students through combination of natural language processing and big data technology; quantitatively analyzing the influence of the attributes of the psychologists on the psychological categories of the psychologists, so as to realize the mapping from the psychologists to the psychological categories; and modeling the association relation between the problem domain and the psychological category through an association rule data mining algorithm. After the psychological consultation reservation request of the student is subjected to problem mapping, a correlation model between a problem domain and a psychological category is input for recommendation reservation, and a recommended psychologist and reservation time are given through correlation operation, so that accurate reservation of psychological consultation is realized.
Description
Technical Field
The invention belongs to the technical field of psychological consultation, and particularly relates to a college student psychological consultation appointment recommendation method and system.
Background
The mental health diseases of the students in colleges and universities present multiple situations. Usually, colleges and universities have a certain number of professional psychological consultants, psychologists for short. When a student encounters psychological problems, it is necessary to solve the psychological troubles of the student by giving psychological counseling to psychologists in colleges and universities. At this time, the students are often required to make appointment registration, and can adopt the methods of site appointment, telephone appointment, QQ or WeChat appointment and the like, and the students are matched with the receptionist to fill in or inform the related information required for consultation, such as name, contact information, problems required for consultation and the like.
The reservation of students before psychological consultation is a system generally followed by the psychological consultation world at home and abroad at present. The main reasons are three: firstly, the consultation time and the consultation room can be ensured; secondly, the psychologist can make full preparation for the psychological consultation in advance so as to improve the efficiency; and thirdly, primary screening is carried out on the students. However, in the existing reservation mode, the receptionist usually recommends a suitable psychologist to the student according to the conditions provided by the student, or arranges a designated psychologist according to the requirements of the student, and finally coordinates the time of both parties to determine the appointed consultation time according to the service time arrangement of the psychologist.
At present, college students make psychological consultation appointments and often encounter the following problems: (1) students lack the professional knowledge and correct judgment on the nature, type and cause of their psychological problems, and often exaggerate or wrongly describe their psychological problems when filling in relevant information required for counseling. At this moment, the reservation receptionist cannot accurately know the psychological counseling requirements of the students, and usually allocates psychologists only by subjective feeling, so that accurate adaptation between the two is difficult to achieve. (2) Colleges and universities are usually relatively closed environments, and most students do not know the conditions of personal ability, field excellence and the like of psychologists in colleges and universities, so that the college and college department can play a role of a bridge in the reservation process and is a receptionist. However, the receptionists often have different individual abilities, and it is not easy to recommend a psychologist with strong pertinence, proper time and obvious effect to the psychological consultation reservation of each student only by the subjective efforts of the receptionists.
Disclosure of Invention
In order to solve the problems existing in the prior college student psychological consultation appointment, the inventor of the invention carries out keen research and provides a college student psychological consultation appointment recommendation method and a college student psychological consultation appointment recommendation system, wherein the problem domain mapping is carried out on the psychological consultation appointment registration information of students through the combination of natural language processing and big data technology; quantitatively analyzing the influence of the attributes of the psychologists on the psychological categories of the psychologists, and mapping the psychological categories of the psychologists; and modeling the association relation between the problem domain and the psychological category through an association rule data mining algorithm. After the psychological consultation reservation request of the student is subjected to problem mapping, a correlation model between a problem domain and a psychological category is input for recommendation reservation, and a recommended psychologist and reservation time are given through correlation operation, so that accurate reservation of psychological consultation is realized.
The technical scheme provided by the invention is as follows:
in a first aspect, a college student psychological consultation appointment recommendation method includes:
s101, recording college student XiProviding consulted psychological questions and appointment related information when performing psychological consultation appointment registration, and combining the historical consulting data of the students stored in the database to generate characteristic vectors (x) of the high-efficiency students1,x2,…,xk) Attribute information for representing each student;
s102, analyzing classification summary of student current conversation intention by natural language processingThe rate is calculated by utilizing historical psychological booking big data to calculate the mapping probability between different conversation intentions and problem domains, and the psychological problems of students to a certain problem domain A are realized by combining the characteristic vectors of the students on the basisi’Simultaneously with student XiFeature vector and corresponding problem field A ofi’The feature vectors of (a) are spliced together to form a new vector Ai’＝(Xi,Ai’) (ii) a Wherein, problem domain Ai’The feature vector of (a)1,a2,…,am) Attribute information for indicating a problem domain;
s103, recording psychologist Y engaged in psychological consultation servicejGenerating a characteristic vector (y) of a psychologist by combining self-evaluation and other evaluation according to historical consultation data statistics1,y2,…,yh) Attribute information for representing a psychologist;
s104, counting the probability of the psychologist serving different psychological categories by utilizing the big data of the psychological consulting service, mapping the psychologist feature vector to each type of psychological category, wherein the process can be formally expressed as
Wherein B ═ B1,B2,…,Bn) As a set of psychological categories, Bj’(j ═ 1,2, …, n) represents any type of mental category, which in turn forms psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bjn) Wherein B isjj’(j ═ 1,2, …, n) denotes psychologist YjIn different psychological categories Bj’A probability value of the upper service;
s105, utilizing association rule data mining algorithm, and passing through student XiWith a psychologist YjAll association rules between question domains and all psychological domains
Calculating confidence of all association rules
Form a student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculationiAnd psychologist YjVector value C of inter-reservation relationijFormally represented as Cij＝(Ai’)TMijBj', wherein Ai' and Bj' both are row vectors or column vectors, (A)i’)TIs a vector after the transposition;
s106, judging whether all psychologists Y are traversed or notjIf not, returning to the step S105 for cycle execution; otherwise, explain to obtain student XiWith all psychologists YjVector value C of inter-reservation relationijEntering the next step;
s107, taking student XiTo all psychologists YjThe reservation relation of the maximum vector value passing through the problem domain and all the psychological categories is output, and the psychologist corresponding to the reservation relation is used as the student XiAnd recommending a psychologist of the appointment.
In a second aspect, a college student psychological consultation appointment recommendation system comprises:
student characteristic module for college student X recording psychological consultation appointmentiA student set X forming a psychological consultation appointment, generating a feature vector (X) of a student in colleges and universities for the psychological consultation appointment by using the psychological question consulted by the student and the appointment-related information, and combining the historical consulting data of the student stored in the database1,x2,…,xk) Attribute information for representing students;
a problem domain module for generating a problem domain A representing the classification of psychological problems by using a historical student psychological consultation question bank based on a natural language processing technology and a data mining technologyi’Forming a set of problem domains A representing different types of psychological problems, each problem domain Ai’The feature vector of (a)1,a2,…,am) Attribute information for indicating a problem domain;
the student-question domain mapping module is used for analyzing the classification probability of the current conversation intention of the student by utilizing natural language processing, counting the mapping probability between different conversation intentions and question domains by utilizing historical psychological booking big data, and realizing that the psychological question of the student reaches a certain question domain A by combining with the characteristic vector of the student on the basisi’Simultaneously with student XiFeature vector and corresponding problem field A ofi’The feature vectors of (a) are spliced together to form a new vector Ai’＝(Xi,Ai’)；
Psychologist characteristic module for recording psychologist Y engaged in psychological consultation servicejForming a psychologist set Y engaged in psychological counseling service; generating the feature vector (y) of the psychologist by combining self-evaluation and other evaluation by using historical consultation data statistics1,y2,…,yh) Attribute information for representing a psychologist;
a psychological category module for recording different categories of psychological categories Bj’The system is responsible for managing the psychological category to form a psychological category list B corresponding to the work content of psychologists, and the psychological category is set by a psychological booking team according to the psychological professional characteristics and the psychological service condition;
the psychologist-psychological category mapping module is used for counting the probability of psychologist service in different psychological categories by utilizing the big data of psychological consultation service, mapping the psychologist feature vectors into different types of psychological categories to form psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bjn) In which B isjj’(j ═ 1,2, …, n) denotes psychologist YjIn different psychological categories Bj’A probability value of the upper service;
an association module for data mining algorithm by student X using association ruleiWith a psychologist YjAll association rules after passing through problem domain and psychological domain
Calculating confidence of all association rules
Form a student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculationiAnd psychologist YjVector value C of inter-reservation relationij，Cij＝(Ai’)TMijBj', wherein Ai' and Bj' both are row vectors or column vectors, (A)i’)TIs a vector after the transposition;
an output module for outputting the output according to the student XiTo all psychologists YjAnd outputting a psychologist corresponding to the reservation relation through the reservation relation of the maximum vector values of the problem domain and the psychological category, and using the psychologist as a psychologist recommending the reservation to students.
The college student psychological consultation appointment recommendation method and system provided by the invention have the following beneficial effects:
(1) according to the appointment recommendation method and system, the existing natural language processing and big data technology is utilized to automatically process the appointment registration information of the students, extra manual participation is not needed, the limitation of personal ability difference of receptionists is avoided, and the recommendation result objectivity and accuracy are high;
(2) according to the reservation recommendation method and system, big data statistics is carried out on historical reservation data between students and psychologists in the database, and quantitative analysis can be accurately carried out on reservation relations between the students and the psychologists by using an association rule data mining algorithm;
(3) according to the appointment recommendation method and system, the weight matrix of the appointment relationship between the student and each psychologist is established by calculating the confidence coefficient of the association rule, the vector value of the appointment relationship between the student and each psychologist is calculated quantitatively by combining the vectors after mapping of the student and each psychologist, the appointment relationship with the largest vector value can be taken as a recommendation result, and the consultation effect is improved;
(4) the reservation recommendation method and the reservation recommendation system provide reservation recommendation opinions and provide technical support for college students to use and psychology consultation receptionists to timely and efficiently process reservations.
Drawings
FIG. 1 is a flow chart of a college student psychological consultation appointment recommendation method;
fig. 2 is a block diagram of a college student psychological consultation reservation recommendation system.
Detailed Description
The features and advantages of the present invention will become more apparent and appreciated from the following detailed description of the invention.
According to a first aspect of the present invention, there is provided a college student psychological consultation appointment recommendation method, as shown in fig. 1, including:
s101, recording college student XiProviding psychological consulted questions and appointment related information such as appointment time when performing psychological consultation appointment registration, combining historical consulting data of the students stored in the database such as historical appointment times and statistical information such as evaluation of mental tendency of psychologists, and generating feature vector (x) of college students1,x2,…,xk) Attribute information for representing each student;
s102, analyzing classification probability of current conversation intention of students by using natural language processing, counting mapping probability between different conversation intentions and problem domains by using historical psychological booking big data, and realizing that the psychological problems of the students reach a certain problem domain A by combining with the characteristic vectors of the students on the basisi’Can be formally expressed as
At the same time, student XiFeature vector and corresponding problem field A ofi’The feature vectors of (a) are spliced together to form a new vector Ai’＝(Xi,Ai’) (ii) a Wherein, problem domain Ai’The feature vector of (a)1,a2,…,am) Attribute information for indicating a problem domain;
s103, recording psychologists engaged in psychological consultation serviceYjThe characteristic vector (y) of the psychologist is generated by utilizing historical consultation data statistics and adopting a mode of combining self-evaluation and other evaluation, such as self-evaluation and student grading after the psychologist participates in psychological domain services1,y2,…,yh) Attribute information for representing a psychologist;
s104, counting the probability of the psychologist serving different psychological categories by utilizing the big data of the psychological consulting service, mapping the psychologist feature vector to each type of psychological category, wherein the process can be formally expressed as
Wherein B ═ B1,B2,…,Bn) As a set of psychological categories, Bj’(j ═ 1,2, …, n) represents any type of mental category, which in turn forms psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bjn) Wherein B isjj’(j ═ 1,2, …, n) denotes psychologist YjIn different psychological categories Bj’A probability value of the upper service;
s105, utilizing association rule data mining algorithm, and passing through student XiWith a psychologist YjAll association rules between question domains and psychological categories
Calculating confidence of all association rules
Form a student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculationiAnd psychologist YjVector value C of inter-reservation relationijFormally represented as Cij＝(Ai’)TMijBj', wherein Ai' and Bj' both are row vectors or column vectors, (A)i’)TIs a vector after the transposition;
s106, judging whether all psychologists Y are traversed or notjIf j is not equal to h, returning to the step S105 for circular execution; otherwise, explain to obtain student XiWith all psychologists YjVector value C of inter-reservation relationijEntering the next step; wherein h is the number of psychologists;
s107, taking student XiTo all psychologists YjThe reservation relation between the maximum vector values passing through the problem domain and all psychological domains is formally expressed as Cij’＝max{Cij|1<＝j<H, outputting psychologist Y corresponding to the reservation relationjIt is taken as the student XiAnd recommending a psychologist of the appointment.
In the present invention S101, attributes of the student include a question to be asked, a tendency to be internal, the number of past appointments, an appointment time, and the like. Wherein the questions are the psychological questions consulted by the students; the internal tendency attribute is obtained according to the evaluation of a psychologist after the consultation of each student recorded in the database is completed, and if the internal tendency attribute is the first appointment, the value is null; the historical booking frequency attribute is obtained by counting the access frequency of each student in the database; the appointment time attribute can be extracted from the language expression of each student in appointment registration, or can be defaulted to a certain predetermined time value.
In the present invention S102, problem field Ai’Including but not limited to the purpose of the consultation, the type of problem, the primary performance, the duration, the frequency of occurrence, the severity, the degree of influence, or the individual mood, and each problem domain attribute can be extracted from the information provided by the student and from the representation of the student's consultation data stored in the database. Wherein, the consultation purposes such as 'seeking solution', 'seeking comfort' or 'understanding oneself', etc. are extracted by natural language processing technology according to the information provided by students; the types of the problems are extracted by a natural language processing technology according to information provided by students, such as 'love emotion', 'friend emotion', 'teacher and student emotion', 'learning pressure', 'family pressure', 'job hunting pressure' or 'campus violence'; mainly manifested asThe information of excitement, difficulty or no-call is extracted by natural language processing technology according to the information provided by students; the duration represents the duration of the psychological condition, such as "1 day", "2 days" or "1 month", and is extracted by natural language processing technology according to the information provided by students; the occurrence frequency represents the frequency of the psychological condition, such as 'frequent' and 'infrequent', and is judged by historical consultation information in a database by utilizing a big data technology; the severity degree represents the influence level of the psychological condition, such as 'not serious', 'slightly serious', 'serious' or 'serious', and the like, and is extracted by a natural language processing technology according to the information provided by students; the influence degree represents the influence grade of the psychological condition on the students, such as 'normal', 'light' or 'heavy', and is extracted by a natural language processing technology according to the information provided by the students; personal emotions such as "optimistic", "pessimistic" or "don't care" are extracted by natural language processing techniques based on information provided by the student.
In the present invention S102, the psychological problem to problem domain A is realized by natural language processing and big data technologyi’One-to-one problem mapping.
In the present invention S103, attributes of the psychologist include the adequacy psychological category, the participation psychological category, the student score, the psychological counseling service time, the response time, and the like. The attribute of the strong psychological category is extracted from a psychological consultation reservation service description provided by a psychologist, the attribute of the participation psychological category is obtained by subtracting the attribute of the strong psychological category from all psychological categories which are recorded in a database and are reserved and distributed by the psychologist, the student scoring attribute is obtained according to the evaluation of the effect of the student on the psychological consultation service of the reserved psychologist recorded in the database, the psychological consultation service time is extracted from the psychological consultation reservation service description provided by the psychologist, the response time attribute is obtained by mathematical operation according to the attribute of the psychological consultation service time of the psychologist and the attribute of the reservation time of the student, and the preferred response time attribute is obtained according to the Y psychological counseling service time of the psychologist and the attribute of the reservation time of the studentjPsychological counseling service time attribute of minus counseling student X1The reserved time attribute of (2) is obtained, and the initial value may be 0.
In S104 of the present invention, the psychological categories may be specifically classified into different categories, such as marital family, emotional feeling, relationship, personal growth, marital feeling, teenager psychology, emotional stress, job confusion, and the like.
In the present invention S104, one-to-many psychological mapping of psychologists to psychological categories is realized by big data technology.
In the present invention S105, student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsijThe formalized representation is:
wherein, a'ij∈A′i，1<＝j<＝d，d＝|A′i|；Bjj’(j ═ 1,2, …, n) denotes psychologist YjIn mapping to psychological domain Bj’The latter vector value.
In the present invention S105, student X calculated by the matrix multiplication methodiAnd psychologist YjVector value of reservation relation is Cij＝(Ai’)TMijBj’，CijThe matrix multiplication form of (a) is:
wherein, (A'i)T＝(a′i1…a′id)，
Wherein, problem domain Ai' and psychological category Bj' converting the attribute vector value to the same dimension, typically mapping the data to [0,1]Or [ -1,1 [)]Within the interval, the standard deviation standardization, the range standardization, the logarithmic function conversion and the arc tangent can be adoptedFunctions, normalization, etc.
According to a second aspect of the present invention, there is provided a college student psychological consultation reservation recommending system, as shown in fig. 2, comprising:
student characteristic module for college student X recording psychological consultation appointmentiA student set X forming a psychological consultation appointment, generating a feature vector (X) of a student in colleges and universities for the psychological consultation appointment by using the psychological question consulted by the student and the appointment-related information, and combining the historical consulting data of the student stored in the database1,x2,…,xk) Attribute information for representing students;
a question domain module for generating a question domain A representing a category of psychological questionsiForming a set of problem domains A representing different types of psychological problems, each problem domain Ai’The feature vector of (a)1,a2,…,am) Attribute information for representing a problem domain, techniques for dividing the problem domain including, but not limited to, natural language processing techniques and data mining techniques, and information employed including, but not limited to, a whole set or a partial set of historical student psychological counseling questions;
the student-question domain mapping module analyzes the classification probability of the current conversation intention of the student by using natural language processing, counts the mapping probability between different conversation intentions and question domains by using historical psychological booking big data, and realizes that the psychological question of the student reaches a certain question domain A by combining with the characteristic vector of the student on the basisi’Can be formally expressed as
At the same time, student XiFeature vector and corresponding problem field A ofi’The feature vectors of (a) are spliced together to form a new vector Ai’＝(Xi,Ai’)；
Psychologist characteristic module for recording psychologist Y engaged in psychological consultation servicejForming a psychologist set Y engaged in psychological counseling service; taking self-evaluation and other evaluation by using historical consultation data statisticsIn combination, a psychologist's feature vector (y) is generated1,y2,…,yh) Attribute information for representing a psychologist;
a psychological category module for recording different categories of psychological categories Bj’The system is responsible for managing the psychological category to form a psychological category list B corresponding to the work content of the psychologist, and the psychological category list can be represented by B ═ B1,B2,…,Bn) Is shown in the specification, wherein Bj’(j ═ 1,2, …, n) represents each psychological category; the psychological category is set by a psychological booking team according to the psychological professional characteristics and the psychological service condition;
the psychologist-psychological category mapping module is used for counting the probability of psychologist service in different psychological categories by utilizing the big data of psychological consultation service, mapping the psychologist feature vectors into different types of psychological categories to form psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bjn) In which B isjj’(j ═ 1,2, …, n) denotes psychologist YjIn different psychological categories Bj’A probability value of the upper service;
an association module for data mining algorithm by student X using association ruleiWith a psychologist YjAll association rules after passing through problem domain and psychological domain
Calculating confidence of all association rules
Form a student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculationiAnd psychologist YjVector value C of inter-reservation relationij，Cij＝(Ai’)TMijBj', wherein Ai' and Bj' both are row vectors or column vectors, (A)i’)TIs a vector after the transposition;
an output module for outputting the output according to the student XiTo all psychologists YjThe reservation relation between the maximum vector values passing through the problem domain and the psychological domain is formally expressed as Cij’＝max{Cij|1<＝j<H, the psychologist corresponding to the reservation relation is output as the psychologist to the student XiAnd recommending a psychologist of the appointment.
In the present invention, the attributes of each student are as described in the first aspect, and will not be described in detail here.
In the present invention, the attribute of each question field is as described in the first aspect, and is not described herein again.
In the present invention, the attributes of the psychologist are as described in the first aspect, and are not described in detail herein.
In the present invention, the psychological category classification is as described in the first aspect, and is not described herein again.
In the invention, the student-problem domain mapping module realizes one-to-one problem mapping from the student characteristic module to the problem domain module through natural language processing and big data technology.
In the invention, the psychologist-psychological category mapping module realizes one-to-many psychological mapping from the psychologist characteristic module to the psychological category module through a big data technology.
In the invention, a one-to-many association relationship can exist between the problem domain module and the psychological category module. That is to say, each problem domain and each psychological category may have an association relationship, each association relationship may calculate a weight, and the weight of each association relationship may be obtained by calculating the confidence of the item group in the association relationship according to an association rule data mining algorithm, so as to form the weight matrix of all association relationships.
Student X constructed by association moduleiAnd psychologist YjWeight matrix M of inter-subscription relationshipsijThe formalized representation is:
wherein, a'ij∈A′i，1<＝j<＝d，d＝|A′i|。
In the invention, the problem domain module and the psychological category module realize reservation recommendation based on the incidence relation. By using the weight matrix and the matrix multiplication method, vector values of all incidence relations between the students and the psychologists, formed by the problem domains subjected to problem mapping and the psychological categories subjected to psychological mapping can be calculated, and finally the incidence relation with the maximum vector value is reserved and recommended to the students.
Student X calculated by correlation module by using matrix multiplication methodiAnd psychologist YjVector value of reservation relation is Cij＝(Ai’)TMijBj', the matrix multiplication form:
wherein, (A'i)T＝(a′i1…a′id)，
Wherein A isi' and Bj' converting the attribute vector value to the same dimension, typically mapping the data to [0,1]Or [ -1,1 [)]Within the interval, standard deviation normalization, range normalization, logarithmic function conversion, arctangent function, normalization, and the like can be used.
Examples
Example 1
A recommendation system for college student psychological consultation appointment assumes a student X1The psychological consultation appointment registration is provided, and the problem is that the mind is difficult to suffer when the I just shares hands with the I/O friends for one weekCan not be discharged;
student characteristic module, college student X recording psychological consultation reservation1The method comprises forming student X by using the psychological questions and appointment time provided by students, and combining the historical appointment times of the students and the evaluation of psychologists on their internal tendency stored in the database1Feature vector (x) of1,x2,x3,x4) (ii) a Attribute x1Corresponding to the problems, the method is that the mind cannot be released after I just hands with I women for one week; attribute x2Corresponding to the tendency of inner core, it is "the character is inward; attribute x3The corresponding historical reservation times are '6'; attribute x4Corresponding to the reserved time, it is "wednesday".
And the problem domain module is used for recording problem domains representing different types of psychological problems, and assuming that a problem domain set A is { academic problems, love emotions and physical barriers }.
Student-problem domain mapping module, according to student X1Proposed psychological counseling question x1The expression, the reservation related problems and the counseling data of the students stored in the database, and the psychological counseling problems of the students are classified into a problem domain A of a love emotion type by utilizing natural language processing and big data technology2Extracting problem domain A2Each attribute of (1), including consulting purpose a1Is "find solution", type a of problem2Is "love emotion" and shows the main expression of a3Is "refractory" for a duration of time a4Is one week, the frequency of occurrence a5Is "not often", severity a6Is "somewhat severe", affecting the degree a7Is "general", personal emotion a8Is pessimistic, and further will student X1And corresponding problem field A2Are spliced together to form a new vector A1’＝(X1,A2)＝(x1,x2,x3,x4,a1,a2,a3,a4,a5,a6,a7,a8)。
A mental category module for assuming the mental category setThe co-formalization is represented by B ═ B1,B2,…,B8In which B is1Representing "marriage family", B2Representing "emotional feeling", B3Indicates "parent-child relationship", B4Meaning "personal growth", B5Representing "marital emotion", B6Representing "juvenile psychology", B7Indicating "emotional stress", B8Representing 8 different categories such as "job confusion".
Psychologist characteristics module, assuming that there are currently 3 psychologists, i.e. h is 3, the psychologist set is formalized as Y { Y ═ 31,Y2,Y3}. According to each psychologist YjProviding the description of psychological consultation reservation service and big data statistical information, and knowing the adept psychological category y of each psychologist1And participate in the psychological category y2Scoring y for students3Time of psychological counseling service y4Response time y5The 5 attributes are shown in table 1. Wherein, the students score y3The method is characterized in that a score list is obtained after the psychological consultation effect of a reservation psychologist is evaluated after students finish psychological consultation every time in history, and the evaluation standard can be a percentage system; response time attribute y5The initial value may be 0, then according to psychologist YjPsychological counseling service time attribute y4And consult student X1Reserved time attribute x4Obtained by mathematical operations, e.g. y5＝|y4-x4|。
TABLE 1
| Yj | y1 | y2 | y3 | y4 | y5 |
| Y1 | B1,B2,B3 | B4,B7 | 80,70,90,85,92 | Wednesday and thursday | 0,1 |
| Y2 | B3,B5,B6 | B4,B8 | 85,80,95,76,87 | Tuesday and Friday | 1,2 |
| Y3 | B4,B7,B8 | B1,B5 | 80,75,90,90,96 | Monday | 2 |
Psychologist-psychological category mapping module: 3-bit psychologist Y, using big data technology, according to the assumptions abovejExcellence in the psychological category y1And participate in the psychological category y2To map psychologists to 8In different psychological categories, thereby forming psychologists YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bj8)。
An association module for data mining algorithm by using association rule through student X1With a psychologist YjInter-transit problem domain a2And all association rules of psychological category B
Computing problem Domain A2Confidence of all association rules in the psychological domain B
Form a student X1And psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculation1And psychologist YjVector value of inter-reservation relation formally expressed as Cij＝(Ai’)TMijBj', wherein Ai' and Bj' are column vectors, (A)i’)TIs a transposed row vector;
an output module for outputting the output according to the student X1To all psychologists YjThe reservation relation between the maximum vector values passing through the problem domain and the psychological domain is formally expressed as Cij’＝max{Cij|1<＝j<H, outputting psychologist Y corresponding to the reservation relation1Will psychologist Y1As to student X1And recommending a psychologist for reservation, wherein the wednesday is the reservation time.
Because the problem domain and the psychological category have one-to-many correlation, the student feature vector X1Mapped problem domain A2And psychologist feature vector YjThere may be one association in each of the 8 different psychological categories of the mapping, and all such associations may be formally expressed as
If it is notEach student attribute, each question domain attribute and each psychological category attribute are regarded as one item, and the association relationship between the attributes is a dependency relationship between the items, which can be called as an association rule. According to the association rule data mining algorithm, the confidence of the item group on each association relationship, namely the confidence between the attributes can be calculated. Since the confidence is actually a conditional concept, the confidence value can be regarded as a weight on each association relationship, and thus a weight matrix of all the association relationships is formed. When obtaining student X1Attribute, corresponding problem Domain A2Attribute, post-mapping psychological category Bj' weight matrix M of all associations on an attributeijThen, by using a matrix multiplication method, the student X can be obtained by calculation respectively1To 3 psychologists Y1,Y2,Y3And vector values of all incidence relations formed by the problem domain of the problem mapping and the psychological category of the psychological mapping. And finally, making reservation recommendation to the student by the psychologist with the maximum vector value.
Example 2
A recommendation method for college student psychological consultation appointment assumes a student X1The method proposes psychological consultation reservation registration, and solves the problems that the mind is difficult to keep down when I just divides hands of I and I/O friends for one week, and the flow of the recommendation method is as follows:
s101, college student X1When the psychological consultation appointment is registered, the counselor is matched to provide the psychological questions consulted and the appointment time, and the characteristic vector X of the student is formed by combining the historical appointment times of the student in the database and the evaluation information of the psychologist on the internal tendency of the student1＝(x1,x2,x3,x4) For representing attribute information of each student, question x1Is that "I just and I women's friend divide hands for one week, the mind is hard to be put down", the internal tendency is x2Is "inwardly oriented character", the number of historical appointments x3Is "6", the reservation time x4Is "Wednesday";
s102, student X1The provided information and the historical consulting data of the student stored in the database are mapped to the problem domain A2In (1), this process can be formally expressed as
Wherein the problem domain A2The feature vector of (a)1,a2,…,a8) Consultation purpose a1Is "find solution", type a of problem2Is "love emotion" and shows the main expression of a3Is "refractory" for a duration of time a4Is one week, the frequency of occurrence a5Is "not often", severity a6Is "somewhat severe", affecting the degree a7Is "general", personal emotion a8Is "pessimistic" and will be student X at the same timeiSplicing with the vector of the corresponding problem domain to form a new vector A1’＝(X1,A2)＝(x1,x2,x3,x4,a1,a2,a3,a4,a5,a6,a7,a8)；
S103, assume that there are 3 psychologists { Y }1,Y2,Y3According to each psychologist YjThe information of the psychological consultation reservation service description and the big data statistics is provided, so that each psychologist can know the adept psychological category y1And participate in the psychological category y2Scoring y for students3Time of psychological counseling service y4Response time y55 attributes, see Table 1 for details, form psychologist YjFeature vector (y) of1,y2,y3,y4,y5)；
S104, according to psychologist YjAttribute information, general psychologist YjMapping into 8 different types of mental domains, this process can be formalized as
Form psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bj8) In which B isjj’(j ═ 1,2, …,8) denotes psychologist YjIn mapping to psychological domain Bj’The latter vector value;
Bjj’the vector value calculation formula can be expressed as follows:
wherein the content of the first and second substances,
y5＝y4-x4，|y3i then means student's score y3The total number of the middle scores, and alpha, beta and theta are parameters, and can be obtained by experience values or training by a large amount of data. The theta parameter is preceded by a negative sign and can be considered as a decay factor, because in general psychologists with shorter response times are more likely to be selected and have a greater probability for the student's appointment time.
S205, using association rule data mining algorithm, through student X1With a psychologist YjInter-transit problem domain a2And all association rules of psychological category B
Computing problem Domain A2Confidence of all association rules in the psychological domain B
Form a student X1And psychologist YjWeight matrix M of inter-subscription relationships1jFormalized as:
wherein, a'1j∈A′1，1<＝j<＝d，d＝|A′112. Further, student X is calculated by using a matrix multiplication method1And psychologist YjVector value C of inter-reservation relation1j＝(A1’)TM1jBj', can be expressed in matrix multiplication form:
wherein, (A'1)T＝(a′11…a′1d)，
To facilitate vector calculation, A isi' vector sum Bj' the attribute values of the vector are mapped to [0,1 ] using a standard deviation normalization method]Within the interval.
S206, judging whether all 3 psychologists Y are traversed or notjIf j is not equal to h and h is 3, returning to S205 for loop execution; otherwise, calculating to obtain the student X1With all psychologists YjVector value of inter-reservation relation { C11,C12,C13Fifthly, entering the next step;
s207, taking student X1To all 3 psychologists YjThe reservation relation between the maximum vector values passing through the problem domain and the psychological domain is formally expressed as C1j’＝max{C11,C12,C13}，1<＝j<H is h, h is 3, and the psychologist Y corresponding to the reservation relation is output1As to student X1And recommending a psychologist for reservation, wherein the wednesday is the reservation time.
The invention has been described in detail with reference to specific embodiments and illustrative examples, but the description is not intended to be construed in a limiting sense. Those skilled in the art will appreciate that various equivalent substitutions, modifications or improvements may be made to the technical solution of the present invention and its embodiments without departing from the spirit and scope of the present invention, which fall within the scope of the present invention. The scope of the invention is defined by the appended claims.
Those skilled in the art will appreciate that those matters not described in detail in the present specification are well known in the art.
Claims (10)
1. A college student psychological consultation appointment recommendation method is characterized by comprising the following steps:
s101, recording college student XiThe consulted psychological question and appointment-related information provided when performing psychological consultation appointment registration are combined with the historical consulting data of the student stored in the database to generate a feature vector (x) of the student in colleges and universities1,x2,…,xk) Attribute information for representing each student;
s102, analyzing classification probability of current conversation intention of students by using natural language processing, counting mapping probability between different conversation intentions and problem domains by using historical psychological booking big data, and realizing that the psychological problems of the students reach a certain problem domain A by combining with the characteristic vectors of the students on the basisi’Simultaneously with student XiFeature vector and corresponding problem field A ofi’The feature vectors of (a) are spliced together to form a new vector Ai’＝(Xi,Ai’) (ii) a Wherein, problem domain Ai’The feature vector of (a)1,a2,…,am) Attribute information for indicating a problem domain;
s103, recording psychologist Y engaged in psychological consultation servicejGenerating a characteristic vector (y) of a psychologist by combining self-evaluation and other evaluation according to historical consultation data statistics1,y2,…,yh) Attribute information for representing a psychologist;
s104, counting the probability of the psychologist serving different psychological categories by utilizing the big data of the psychological consulting service, mapping the psychologist feature vector to each type of psychological category, wherein the process can be formally expressed as
Wherein B ═ B1,B2,…,Bn) As a set of psychological categories, Bj’(j ═ 1,2, …, n) represents any type of mental category, which in turn forms psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bjn) Wherein B isjj’(j ═ 1,2, …, n) denotes psychologist YjIn different psychological categories Bj’A probability value of the upper service;
s105, utilizing association rule data mining algorithm, and passing through student XiWith a psychologist YjAll association rules between question domains and all psychological domains
Calculating confidence of all association rules
Form a student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculationiAnd psychologist YjVector value C of inter-reservation relationijFormally represented as Cij＝(Ai’)T MijBj', wherein Ai' and Bj' both are row vectors or column vectors, (A)i’)TIs a vector after the transposition;
s106, judging whether all psychologists Y are traversed or notjIf not, returning to the step S105 for cycle execution; otherwise, explain to obtain student XiWith all psychologists YjVector value C of inter-reservation relationijEntering the next step;
s107, taking student XiTo all psychologists YjThe reservation relation of the maximum vector value passing through the problem domain and all the psychological categories is output, and the psychologist corresponding to the reservation relation is used as the student XiAnd recommending a psychologist of the appointment.
2. The recommendation method according to claim 1, wherein in S102, a one-to-one problem mapping from a psychological problem to a problem domain is implemented by natural language processing and big data technology.
3. The recommendation method according to claim 1, wherein in S104, one-to-many psychomapping of psychologists to psychological categories is implemented by big data technology.
4. The recommendation method according to claim 1, wherein in S105, student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsijComprises the following steps:
wherein, a'ij∈A′i，1<＝j<＝d，d＝|A′i|；Bjj’(j ═ 1,2, …, n) denotes psychologist YjIn mapping to psychological domain Bj’The latter vector value.
5. The recommendation method according to claim 1, wherein in S105, the student X calculated by using a matrix multiplication methodiAnd psychologist YjVector value C of inter-reservation relationij＝(Ai’)T MijBj’，CijThe matrix multiplication form of (a) is:
wherein, (A'i)T＝(a′i1 … a′id)，
6. The recommendation method according to claim 5, wherein in S105, student X is calculatediAnd psychologist YjVector value C of inter-reservation relationijTime, problemDomain Ai'and psychological category B'jThe attribute vector values of (1) are converted to the same dimension.
7. A college student psychological consultation appointment recommendation system, comprising:
student characteristic module for college student X recording psychological consultation appointmentiA student set X forming a psychological consultation appointment, generating a feature vector (X) of a student in colleges and universities for the psychological consultation appointment by using the psychological question consulted by the student and the appointment-related information, and combining the historical consulting data of the student stored in the database1,x2,…,xk) Attribute information for representing students;
a problem domain module for generating a problem domain A representing the classification of psychological problems by using a historical student psychological consultation question bank based on a natural language processing technology and a data mining technologyi’Forming a set of problem domains A representing different types of psychological problems, each problem domain Ai’The feature vector of (a)1,a2,…,am) Attribute information for indicating a problem domain;
the student-question domain mapping module is used for analyzing the classification probability of the current conversation intention of the student by utilizing natural language processing, counting the mapping probability between different conversation intentions and question domains by utilizing historical psychological booking big data, and realizing that the psychological question of the student reaches a certain question domain A by combining with the characteristic vector of the student on the basisi’Simultaneously with student XiFeature vector and corresponding problem field A ofi’The feature vectors of (a) are spliced together to form a new vector Ai’＝(Xi,Ai’)；
Psychologist characteristic module for recording psychologist Y engaged in psychological consultation servicejForming a psychologist set Y engaged in psychological counseling service; generating a characteristic vector (y) of a psychologist by combining self-evaluation and other evaluation by utilizing historical consultation data statistics1,y2,…,yh) Attribute information for representing a psychologist;
psychological category modelBlocks for recording different categories of psychological categories Bj’The system is responsible for managing the psychological category to form a psychological category list B corresponding to the work content of psychologists, and the psychological category is set by a psychological booking team according to the psychological professional characteristics and the psychological service condition;
the psychologist-psychological category mapping module is used for counting the probability of psychologist service in different psychological categories by utilizing the big data of psychological consultation service, mapping the psychologist feature vectors into different types of psychological categories to form psychologist YjAssociated psychological category list vector Bj’＝(Bj1,Bj2,…,Bjn) In which B isjj’(j ═ 1,2, …, n) denotes psychologist YjIn different psychological categories Bj’A probability value of the upper service;
an association module for data mining algorithm by student X using association ruleiWith a psychologist YjAll association rules after passing through problem domain and psychological domain
Calculating confidence of all association rules
Form a student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsij(ii) a Then, by using a matrix multiplication method, the student X is obtained by calculationiAnd psychologist YjVector value C of inter-reservation relationij，Cij＝(Ai’)TMijBj', wherein Ai' and Bj' both are row vectors or column vectors, (A)i’)TIs a vector after the transposition;
an output module for outputting the output according to the student XiTo all psychologists YjAnd outputting a psychologist corresponding to the reservation relation through the reservation relation of the maximum vector values of the problem domain and the psychological category, and using the psychologist as a psychologist recommending the reservation to students.
8. The recommendation system according to claim 7, wherein the attributes of the students in the student characteristics module include questions asked, tendency to be internal, historical booking times and booking time, wherein the questions asked are psychological questions consulted by the students; the internal tendency attribute is obtained according to the evaluation of psychologists after the consultation of each student recorded in the database is completed, and if the internal tendency attribute is the first appointment, the value is null; the historical booking frequency attribute is obtained according to the access frequency statistics of each student in the database; the appointment time attribute is extracted from language expression of each student in appointment registration or defaults to a predetermined time value; and/or
The attributes of different question domains in the question domain module comprise a plurality of consultation purposes, types of questions, main expressions, duration, occurrence frequency, severity, influence degrees or individual moods;
the attributes of psychologists in the psychologist characteristics module include a plurality of categories of excellence psychology, participation psychology, student rating, psychological counseling service time or response time, wherein the attribute of the strong psychological category is extracted from a psychological consultation reservation service description provided by a psychologist, the participation psychological category attribute is obtained by subtracting the adept psychological category from all psychological categories in which the psychologist who is recorded in the database is reserved and allocated and participates, the student rating attribute is obtained based on evaluation of the effect of the psychological counseling service of the student to the psychologist who makes the appointment recorded in the database, the psychological counseling service time is extracted from a psychological counseling reservation service description provided by a psychologist, the response time attribute is obtained by mathematical operation according to the psychological consultation service time attribute of a psychologist and the reservation time attribute of a student;
the psychological category in the psychological category module can be divided into a plurality of categories including marital family, emotional emotion, relationship, personal growth, marital emotion, teenager psychology, emotional stress or job confusion.
9. The recommendation system according to claim 7, wherein the student-question domain mapping module implements one-to-one question mapping from student feature modules to question domain modules through natural language processing and big data technology;
the psychologist-psychological category mapping module realizes one-to-many psychological mapping from the psychologist feature module to the psychological category module through a big data technology.
10. The recommendation system according to claim 7, wherein the association module calculates student XiAnd psychologist YjWeight matrix M of inter-subscription relationshipsijThe formalized representation is:
wherein, a'ij∈A′i，1<＝j<＝d，d＝|A′i|；Bjj’(j ═ 1,2, …, n) denotes psychologist YjIn mapping to psychological domain Bj’The latter vector value;
student X calculated by association moduleiAnd psychologist YjVector value C of inter-reservation relationijThe matrix multiplication form of (a) is:
wherein, (A'i)T＝(a′i1 … a′id)，
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110024240.5A CN112686057B (en) | 2021-01-08 | 2021-01-08 | College student psychological consultation appointment recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110024240.5A CN112686057B (en) | 2021-01-08 | 2021-01-08 | College student psychological consultation appointment recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686057A true CN112686057A (en) | 2021-04-20 |
| CN112686057B CN112686057B (en) | 2022-12-06 |
Family
ID=75456475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110024240.5A Active CN112686057B (en) | 2021-01-08 | 2021-01-08 | College student psychological consultation appointment recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686057B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682447A (en) * | 2017-02-16 | 2017-05-17 | 上海心得乐网络科技有限公司 | Computer-assisted psychological consultation system and method |
| CN106971062A (en) * | 2017-03-09 | 2017-07-21 | 安徽创易心理科技有限公司 | A kind of mental health services method and system |
| CN107562906A (en) * | 2017-09-08 | 2018-01-09 | 北京辅仁淑凡软件科技有限公司 | A kind of Counseling relationship automatic matching method for psychological consultation reservation |
| CN109637627A (en) * | 2018-12-05 | 2019-04-16 | 贵阳高新数通信息有限公司 | Psychological consultation management system |
-
2021
- 2021-01-08 CN CN202110024240.5A patent/CN112686057B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682447A (en) * | 2017-02-16 | 2017-05-17 | 上海心得乐网络科技有限公司 | Computer-assisted psychological consultation system and method |
| CN106971062A (en) * | 2017-03-09 | 2017-07-21 | 安徽创易心理科技有限公司 | A kind of mental health services method and system |
| CN107562906A (en) * | 2017-09-08 | 2018-01-09 | 北京辅仁淑凡软件科技有限公司 | A kind of Counseling relationship automatic matching method for psychological consultation reservation |
| CN109637627A (en) * | 2018-12-05 | 2019-04-16 | 贵阳高新数通信息有限公司 | Psychological consultation management system |
Non-Patent Citations (2)
| Title |
|---|
| 张俊杰等: "数据挖掘在学生心理管理系统中的应用", 《科技信息》 * |
| 曾璇: "可定制化的心理服务系统的研究与设计", 《电脑编程技巧与维护》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686057B (en) | 2022-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chihara et al. | Mathematical statistics with resampling and R | |
| Zaremohzzabieh et al. | Predicting social entrepreneurial intention: A meta-analytic path analysis based on the theory of planned behavior | |
| Peiris | Effect of financial literacy on individual savings behavior; the mediation role of intention to saving | |
| Radcliffe | A study of alumni engagement and its relationship to giving behaviors | |
| Sweeney | A predictive model of student satisfaction | |
| Bergman | An examination of factors that impact persistence among adult students in a degree completion program at a four-year university | |
| Bakker | Identifying the ‘subnormal’child in an age of expansion of special education and child science in the Netherlands (c. 1945–1965) | |
| CN112686057B (en) | College student psychological consultation appointment recommendation method and system | |
| Batool et al. | Women empowerment in the perspective of socioeconomics dynamics: A case study of Northern Punjab, Pakistan | |
| Abrams | Commitment to diversity, equity, and inclusion in higher education: Exploring DEI elements across institutions | |
| Krug | In-work benefits for low-wage jobs: Can additional income reduce employment stability? | |
| Manik | Trials, tribulations and triumphs of transnational teachers: teacher migration between South Africa and United Kingdom. | |
| Petroff | A national transition follow-up study of youth identified as deafblind:" Parent perspectives" | |
| Amish et al. | The Importance of Life Satisfaction: Role of Demographic Variables and Quality of Work Life of College Teachers | |
| Welch | Exploring the Graduation Gap Between Oregon Virtual and Traditional High Schools | |
| Alam | The Effect of Woman Leadership Style and Organizational Culture on Locus of Control, Work Achievement, and Work Satisfaction of Employee | |
| Settle | The effect of socioeconomic status on year-to-year persistence of first-generation and continuing-generation college students at two-year and four-year institutions: Developing a conceptual model | |
| Styles | Breaking the glass ceiling: South Carolina female superintendents' perceptions of career paths, critical skills and barriers to advancement | |
| Levkin | EVALUATION OF THE EFFECTIVENESS OF THE IMPLEMENTATION OF THE MASTER'S PROGRAM" ADMINISTRATIVE LAW AND PROCESS" AT PETROZAVODSK STATE UNIVERSITY ON THE BASIS OF SELF-EXAMINATION | |
| Harmon | The relationship between the funding models of Catholic high schools and seminary enrollment | |
| Mhlongo | The role of pervasive skills in the academic and professional preparation of Accounting students in the University of KwaZulu-Natal. Iqhaza lokwandiswa kwamakhono emfundo ephakeme kanye nokulungiselelwa ngobungcweti kwabafundi abafunda isifundo esibhekene nezezimali eNyuvesi yaKwaZulu-Natali. | |
| Marlina et al. | Financial Literacy of SME's In Medan City: A Descriptive Analysis | |
| Koppernaes | EVALUATING AN ONLINE, SELF-ADMINISTERED STUDENT WELL-BEING AND RESILIENCE PROGRAM | |
| Afua | Value Added Methodology-An Alternative Approach to Quality Measurement in Higher Education | |
| Malalantang | The Role of Leadership and Motivation on Employee Performance: PT. Multi Media Kabar Case Study |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |