CN115994271A - Recommendation method of psychological assessment - Google Patents

Recommendation method of psychological assessment Download PDF

Info

Publication number
CN115994271A
CN115994271A CN202310065461.6A CN202310065461A CN115994271A CN 115994271 A CN115994271 A CN 115994271A CN 202310065461 A CN202310065461 A CN 202310065461A CN 115994271 A CN115994271 A CN 115994271A
Authority
CN
China
Prior art keywords
user
scale
cluster
users
similarity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310065461.6A
Other languages
Chinese (zh)
Inventor
李石君
刘梓轩
余伟
余放
杨济海
杨俊成
李宇轩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan University WHU
Original Assignee
Wuhan University WHU
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan University WHU filed Critical Wuhan University WHU
Priority to CN202310065461.6A priority Critical patent/CN115994271A/en
Publication of CN115994271A publication Critical patent/CN115994271A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a recommendation method of a psychological assessment scale, which comprises the following steps: step 1, acquiring psychological assessment historical data and preprocessing the data; step 2, constructing a user-scale evaluation score matrix according to the data preprocessed in the step 1; step 3, constructing a user cluster by adopting a K-means algorithm according to the user-scale evaluation score matrix in the step 2; and 4, calculating the similarity between the target user and each clustering center point obtained in the step 3 when the target user recommending scale is obtained, taking the user cluster with the center point with the highest similarity as the clustering cluster to which the target user belongs, and generating a recommending scale set based on the partitioned clustering clusters. The invention can automatically recommend the proper psychological assessment scale for the target user, protects the personal information of the user, improves the accuracy, diversity and novelty of recommendation, reduces the problem scale by adopting the particle swarm optimization K-means algorithm, improves the recommendation speed and saves the calculation resources.

Description

Recommendation method of psychological assessment
Technical Field
The invention belongs to the technical field of psychological assessment, and particularly relates to a recommendation method of a psychological assessment.
Background
Psychological assessment system: with the continuous attention of society to psychological health problems, organizations such as enterprises, schools and the like have urgent demands for grasping psychological health conditions of personnel, and if the psychological health problems of the personnel cannot be found in time, hidden dangers in life health safety and property safety of the personnel can be caused. Traditional psychological assessment depends on professional psychological analyzers, the psychological analyzers communicate with consultants, the psychological health condition of the consultants is analyzed according to the experience of the analyzers, the performances of the consultants, the psychological assessment questions and the like, and an online psychological assessment system requires users to select scales from a large number of psychological assessment scales for assessment. The method has the advantages that the method is used for recommending a proper psychological assessment scale for a target user, so that the psychological assessment efficiency can be greatly improved, time and labor are saved, and psychological health condition information is timely acquired.
Psychological assessment scale: the psychological assessment is a set of questions summarized by psychologists, comprehensively analyzed based on diagnostic data and aimed at specific psychological questions, and is a measuring tool for assessing the psychological health condition of individuals. Since psychological assessment is generally built based on statistics, in most cases there is universality to the user. The psychological assessment tables are divided into a single-dimensional table and a multi-dimensional measurement table, namely, the psychological health condition of the user is assessed based on a single assessment score and a plurality of assessment scores respectively. The psychological assessment scale for early warning the psychological health problem of the user is higher in assessment score, and the possibility that the user has the psychological health problem is higher.
Psychological assessment history: in an on-line psychological assessment system, historical psychological assessment records of all users of the system are stored, wherein the records comprise the contents of assessment time length, assessment scale, assessment results and the like, and the structured data form a data base for recommending the psychological assessment scale.
Psychological assessment scale recommendation: the psychological assessment scales are various and distributed in different psychological fields, the traditional method is highly dependent on psychological analysts, when an online psychological assessment system is used, a user is difficult to select a psychological assessment scale suitable for the self condition from a large number of psychological assessment scales, and if the validity of the psychological assessment scale to the user cannot be ensured, the accuracy of screening the psychological health condition of the user is difficult to ensure, so that unnecessary resource waste is caused. Therefore, it is necessary to make psychological assessment scale recommendation for the user.
The existing psychological assessment recommendation method at the present stage is to recommend a batch of psychological assessment which is possibly applicable based on demographic information such as occupation, age and gender of a user, the psychological assessment recommendation method does not consider the influence of subjective factors on psychological health conditions, meanwhile, a single data source causes one side in recommendation, and the recommendation accuracy is difficult to guarantee. In addition, this approach requires acquisition of demographic information of the user without utilizing protection of the user's privacy. Therefore, there is an urgent need to develop new psychological assessment scale recommendation methods to solve the above-mentioned problems.
Disclosure of Invention
The invention aims to provide a recommendation method of a psychological assessment scale aiming at the defects of the prior art, the method provides a recommendation method of the psychological assessment scale based on collaborative filtering, and a K-means algorithm optimized by particle swarm is used for clustering to reduce the problem scale, so that the problem of data sparsity in the collaborative filtering is improved, and finally the recommendation of the psychological assessment scale is completed.
In order to solve the technical problems, the invention adopts the following technical scheme:
a recommendation method of a psychological scale, comprising the steps of:
step 1, acquiring psychological assessment historical data and preprocessing the data;
step 2, constructing a user-scale evaluation score matrix according to the data preprocessed in the step 1;
step 3, constructing a user cluster by adopting a K-means algorithm according to the user-scale evaluation score matrix in the step 2;
and 4, calculating the similarity between the target user and each clustering center point obtained in the step 3 when the target user recommending scale is obtained, taking the user cluster with the center point with the highest similarity as the clustering cluster to which the target user belongs, and generating a recommending scale set based on the partitioned clustering clusters.
Further, the data obtained in step 1 are:
reading and cleaning psychological assessment histories stored in a database based on Python, wherein one history is the assessment score of a user on one psychological assessment scale:
R i ={U t ,S j ,P i }
wherein R is i Represents the ith evaluation history, U t Representing user ID, S j Representing the scale ID, P i Indicating the evaluation score.
Further, the pretreatment method comprises the following steps:
for a multi-dimension scale with a plurality of evaluation scores, splitting each dimension of the multi-dimension scale into a single-dimension scale to serve as a single history record; and normalizing the scale evaluation scores in the history record, and converting the equal ratio into a percentage system.
Further, the step 3 specifically includes:
step 3.1, randomly selecting K users as initial center points, and calculating the user U t Similarity to each center point and to the user U t Dividing the clustering information into clusters where the center points with highest similarity are located;
step 3.2, continuing iterative computation, and repeating the steps of recalculating the center point of each cluster and dividing the user into clusters where the center points with the highest similarity are located before the maximum iteration number M is reached;
step 3.3, finishing iteration when the maximum iteration number M is reached, and generating and outputting K cluster clusters including a center point and a user set;
and 3.4, carrying out iterative computation on the K clustering clusters divided in the step 3.3 by adopting a particle swarm algorithm, and outputting a group of clustering center points serving as initial center points of the K-means algorithm.
Further, in step 3.1, the cosine similarity is used to calculate the similarity of the two users:
Figure BDA0004073774460000031
wherein U is i 、U j Is two users needing to calculate similarity, S is a scale, Q is U i Psychological assessment and U j Intersection of evaluated psychological assessment, P U,S The score of the user U on the psychology evaluation scale S corresponds to one of the score matrixes of the user-scale evaluation;
the range of cosine similarity is [ -1,1], and the closer the value of cosine similarity is to 1, the higher the similarity of the two users is.
Further, the method for dividing new families by iterative computation in the step 3.2 comprises the following steps:
calculating a center point of each cluster, and calculating a similarity mean value of each user and other users for each cluster:
Figure BDA0004073774460000041
wherein W is the average value of the similarity between the user U and other users in the cluster, and m is the number of users in the cluster;
and (3) taking the user with the smallest mean value as a new center point, and dividing the rest users according to the step 3.1 to form a new cluster.
Further, the method for iteratively calculating the initial center point of the K-means algorithm by adopting the particle swarm algorithm POS in the step 3.4 is as follows:
the fitness function of the particle swarm algorithm POS is defined as finding K cluster centers, so that the fitness of all users to the cluster center point of the cluster is highest:
Figure BDA0004073774460000042
wherein D is k Is a data set, the original data is divided into K clusters to obtain a new data set, mu= { mu% 12 ,...,μ K Is the cluster center, n is the number of data stripes in the kth cluster,
Figure BDA0004073774460000043
is the ith data in the kth cluster;
PSO initializes a group of random clustering center points, and regards the random clustering center points as random particles, calculates the fitness of initial random solutions, and initializes the optimal position of individuals, the optimal fitness of individuals, the optimal position of groups and the optimal fitness of groups;
finding an optimal solution through iteration, and in each iteration, the particle updates own speed and position through tracking;
checking and updating the individual optimal position, the individual optimal fitness, the group optimal position and the group optimal fitness until the maximum iteration number is reached, and outputting a group of clustering center points serving as initial center points of a K-means algorithm.
Further, step 4 further comprises the following sub-steps:
step 4.1, constructing a user-scale evaluation score matrix in the cluster, calculating the similarity between the target user and other users in the cluster, and selecting L users with the highest similarity as nearest neighbor users of the target user;
step 4.2, predicting the score of each psychological assessment scale used by the target user;
and 4.3, after obtaining the predictive scores of each psychological assessment scale by the target user, merging the multi-item single-dimensional scales split by one multi-dimensional scale in the step 1, taking the highest predictive score of the multi-item single-dimensional scales as the predictive score of the multi-dimensional scale, sorting each psychological assessment scale according to the descending order of the predictive score of the target user, and taking the first N item scales as the recommended scales of the target user for output.
Further, the calculation formula of the evaluation score of the prediction scale is as follows:
Figure BDA0004073774460000051
wherein F is U,S Is the predicted score of the user U for the table S,
Figure BDA0004073774460000052
is the average of the user's score of the table, C is the nearest neighbor set of users for the target user U, sim (U, U j ) Is a target user U and a nearest neighbor user U j Cosine similarity of P U,S Is the score of the user U to the scale S, i.e. the user-scale evaluates one of the score matrices.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a method for recommending a psychological assessment based on collaborative filtering, and a K-means algorithm optimized by particle swarm is used for clustering to reduce the problem scale, so that the problem of data sparsity in collaborative filtering is improved, and finally the recommendation of the psychological assessment is completed;
the invention can automatically recommend the proper psychological assessment scale for the target user, uses the behavior data of the user, does not depend on the personal information of the user, protects the personal information of the user, improves the accuracy, diversity and novelty of recommendation, improves the possibility of finding psychological health problems of the user, reduces the problem scale by adopting a particle swarm optimization K-means algorithm, improves the recommendation speed and saves the calculation resources.
Drawings
Fig. 1 is a flowchart of a recommendation method of a psychological assessment scale according to an embodiment of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described in the following in conjunction with the embodiments of the present invention, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other.
The invention will be further illustrated, but is not limited, by the following examples.
As shown in fig. 1, the present invention provides a recommendation method for a psychological assessment, comprising the following steps:
step 1, acquiring psychological assessment historical data and preprocessing the data;
in this embodiment, psychological assessment histories stored in the database are read and cleaned based on Python, and one history is an assessment score of a user on one psychological assessment scale:
R i ={U t ,S j ,P i }
wherein R is i Represents the ith evaluation history, U t Representing user ID, S j Representing the scale ID, P i Indicating the evaluation score.
For a multi-dimensional scale with multiple evaluation scores, each dimension of the multi-dimensional scale is split into a single-dimensional scale, the single-dimensional scale is used as a separate history record, the evaluation scores of the scales in the history record are normalized, and the equal ratio is converted into a percentage system.
Step 2, constructing a user-scale evaluation score matrix according to the data preprocessed in the step 1;
constructing a user-scale evaluation score matrix according to the data preprocessed in the step 1, wherein the constructed user-scale evaluation score matrix is shown in a table 1;
TABLE 1.1 user-scale evaluation score matrix
Figure BDA0004073774460000061
Figure BDA0004073774460000071
In Table 1, U is the user, S is the scale, P U,S The score of the table S for the user U. In the psychology evaluation system, a user often has a plurality of history evaluation records for one item of scale, and a score average calculation matrix is obtained for the history evaluation records.
Step 3, constructing a user cluster by adopting a K-means algorithm according to the user-scale evaluation score matrix in the step 2;
step 3.1, constructing an initial cluster;
randomly selecting K users as initial center points, and calculating user U t Similarity with each center point, similarity of two users is calculated by cosine similarity:
Figure BDA0004073774460000072
wherein U is i 、U j Is two users needing to calculate similarity, S is a scale, Q is U i Psychological assessment and U j Intersection of evaluated psychological assessment, P U,S The score of the user U on the psychology evaluation scale S corresponds to one of the score matrixes of the user-scale evaluation;
user U t Dividing the clustering information into clusters where the center points with highest similarity are located;
step 3.2, continuing iteration, and repeating the steps of recalculating the center point of each cluster and dividing the user into clusters where the center points with the highest similarity are located before the maximum iteration number M is reached;
calculating a center point of each cluster, and calculating a similarity mean value of each user and other users for each cluster:
Figure BDA0004073774460000073
wherein W is the average value of the similarity between the user U and other users in the cluster, and m is the number of users in the cluster;
the user with the smallest mean value is taken as a new center point, and the rest users are divided according to the step 3.1 to form a new cluster;
step 3.3, generating a final cluster, ending iteration when the maximum iteration number M is reached, and outputting K clusters including a center point and a user set;
step 3.4, carrying out iterative computation on the K clustering clusters divided in the step 3.3 by adopting a particle swarm algorithm, and outputting a group of clustering center points serving as initial center points of a K-means algorithm;
particle swarm algorithm (Particle Swarm Optimization, PSO) simulates birds in a shoal by designing a mass-free particle that has only two properties: velocity v i And the current position x i The speed represents the speed of movement and the position represents the direction of movement. Each particle has an adaptation value (fit value) determined by the objective function and knows the best position pbest found by itself so far and the best position gbest found by the population so far.
The fitness function of the PSO is defined as finding K cluster centers, so that the fitness of all users to the center point of the cluster to which the user belongs is highest:
Figure BDA0004073774460000081
wherein D is k Is a data set, the original data is divided into K clusters to obtain a new data set, mu= { mu% 12 ,...,μ K Is the cluster center, n is the number of data stripes in the kth cluster,
Figure BDA0004073774460000082
is the ith data in the kth cluster.
PSO initializes a group of random clustering center points, regards the random clustering center points as random particles, calculates the fitness (fitness) of an initial random solution, and initializes the individual optimal position, the individual optimal fitness, the group optimal position and the group optimal fitness.
The optimal solution is found by iteration, in each iteration the particle is tracked by tracking (p best ,g best ) The speed and the position of the user are updated, and the calculation formula is as follows:
v i (t+1)=v i (t)+c 1 ×rand()×(pbest i (t)-x i (t))+c 2 ×rand()
×(gbest(t)-x i (t))
x i (t+1)=x i (t)+v i (t+1)
where i=1, 2,..n, N is the total number of particles in the population, rand () is a random number between (0, 1), c 1 And c 2 Is a learning factor, set c 1 =c 2 =2,v i Has a maximum value of V max (set to the range width of the particles), if v i Greater than V max V is then i =V max
Inertial weight factors are introduced to give consideration to the effects of local search and global search, and convergence speed is optimized, so that the formulas of particle update speed and position are as follows:
v i (t+1)=w×v i (t)+c 1 ×rand()×(pbest i (t)-x i (t))+c 2 ×rand()
×(gbest(t)-x i (t))
x i (t+1)=x i (t)+v i (t+1)
wherein w is an inertia factor, the value of which is non-negative, and w is set by using a linear decreasing weight strategy:
Figure BDA0004073774460000091
wherein G is max Is the maximum iteration number, w int Is an initialization weight, which is 0.9, w end The weight value is iterated to the maximum value, and 0.4 is taken.
Checking and updating the individual optimal position, the individual optimal fitness, the group optimal position and the group optimal fitness until the maximum iteration number is reached, and outputting a group of clustering center points serving as initial center points of a K-means algorithm.
Step 4, calculating the similarity between the target user and each clustering center point obtained in the step 3 when recommending the scale for the target user, taking the user cluster with the center point with the highest similarity as the cluster to which the target user belongs, and generating a recommending scale set based on the divided cluster; in this embodiment, the steps specifically include:
step 4.1, calculating user similarity and selecting nearest neighbor users; in the cluster, a user-scale evaluation score matrix is constructed, the similarity between a target user and other users in the cluster is calculated based on cosine similarity, and L users with the highest similarity are selected as nearest neighbor users of the target user;
step 4.2, predicting the scale evaluation score; predicting the score of each psychological assessment by the target user, wherein the formula for calculating the score of the predictive assessment is as follows:
Figure BDA0004073774460000092
wherein F is U,S Is the predicted score of the user U for the table S,
Figure BDA0004073774460000093
is the average of the user's score of the table, C is the nearest neighbor set of users for the target user U, sim (U, U j ) Is a target user U and a nearest neighbor user U j Cosine similarity of P U,S The score of the user U on the scale S, namely one of the score matrices is measured by the user-scale;
step 4.3, recommending the scale; and (3) after the predicted scores of the target user on each psychological assessment scale are obtained, merging the multi-item single-dimensional scales split by one multi-item scale in the step (1), and taking the highest predicted score of the multi-item single-dimensional scales as the predicted score of the multi-item single-dimensional scale. And ordering all psychological assessment scales according to the target user prediction score descending order, taking the first N item scales as recommendation scales of the target user, and outputting.
The foregoing is merely illustrative of the preferred embodiments of the present invention and is not intended to limit the embodiments and scope of the present invention, and it should be appreciated by those skilled in the art that equivalent substitutions and obvious variations may be made using the teachings of the present invention, which are intended to be included within the scope of the present invention.

Claims (9)

1. A recommendation method of a psychological scale, comprising the steps of:
step 1, acquiring psychological assessment historical data and preprocessing the data;
step 2, constructing a user-scale evaluation score matrix according to the data preprocessed in the step 1;
step 3, constructing a user cluster by adopting a K-means algorithm according to the user-scale evaluation score matrix in the step 2;
and 4, calculating the similarity between the target user and each clustering center point obtained in the step 3 when the target user recommending scale is obtained, taking the user cluster with the center point with the highest similarity as the clustering cluster to which the target user belongs, and generating a recommending scale set based on the partitioned clustering clusters.
2. The recommendation method of a psychological assessment according to claim 1 wherein the data obtained in step 1 are:
reading and cleaning psychological assessment histories stored in a database based on Python, wherein one history is the assessment score of a user on one psychological assessment scale:
R i ={U t ,S j ,P i }
wherein R is i Represents the ith evaluation history, U t Representing user ID, S j Representing the scale ID, P i Indicating the evaluation score.
3. The recommendation method of a psychological assessment according to claim 2 wherein the preprocessing method is:
for a multi-dimension scale with a plurality of evaluation scores, splitting each dimension of the multi-dimension scale into a single-dimension scale to serve as a single history record; and normalizing the scale evaluation scores in the history record, and converting the equal ratio into a percentage system.
4. The recommendation method of a psychological assessment according to claim 1, wherein step 3 specifically comprises:
step 3.1, randomly selecting K users as initial center points, and calculating the user U t Similarity to each center point and to the user U t Dividing the clustering information into clusters where the center points with highest similarity are located;
step 3.2, continuing iterative computation, and repeating the steps of recalculating the center point of each cluster and dividing the user into clusters where the center points with the highest similarity are located before the maximum iteration number M is reached;
step 3.3, finishing iteration when the maximum iteration number M is reached, and generating and outputting K cluster clusters including a center point and a user set;
and 3.4, carrying out iterative computation on the K clustering clusters divided in the step 3.3 by adopting a particle swarm algorithm, and outputting a group of clustering center points serving as initial center points of the K-means algorithm.
5. The recommendation method of a psychological assessment according to claim 4 wherein in step 3.1, cosine similarity is used to calculate the similarity of two users:
Figure FDA0004073774450000021
wherein U is i 、U j Is two users needing to calculate similarity, S is a scale, Q is I i Psychological assessment and U j Intersection of evaluated psychological assessment, P U,S Is that user U is atThe score on the psychological scale S corresponds to one of the user-scale scoring matrices;
the range of cosine similarity is [ -1,1], and the closer the value of cosine similarity is to 1, the higher the similarity of the two users is.
6. The recommendation method of a psychological assessment according to claim 4 wherein the iterative calculation in step 3.2 is a method of dividing new families:
calculating a center point of each cluster, and calculating a similarity mean value of each user and other users for each cluster:
Figure FDA0004073774450000022
wherein W is the average value of the similarity between the user U and other users in the cluster, and m is the number of users in the cluster;
and (3) taking the user with the smallest mean value as a new center point, and dividing the rest users according to the step 3.1 to form a new cluster.
7. The recommendation method of a psychological assessment according to claim 4 wherein the method of iterative computation of the initial center point of the K-means algorithm using the particle swarm algorithm POS in step 3.4 is:
the fitness function of the particle swarm algorithm POS is defined as finding K cluster centers, so that the fitness of all users to the cluster center point of the cluster is highest:
Figure FDA0004073774450000031
wherein D is k Is a data set, the original data is divided into K clusters to obtain a new data set, mu= { mu% 12 ,...,μ K Is the cluster center, n is the number of data stripes in the kth cluster,
Figure FDA0004073774450000032
is the ith data in the kth cluster;
PSO initializes a group of random clustering center points, and regards the random clustering center points as random particles, calculates the fitness of initial random solutions, and initializes the optimal position of individuals, the optimal fitness of individuals, the optimal position of groups and the optimal fitness of groups;
finding an optimal solution through iteration, and in each iteration, the particle updates own speed and position through tracking;
checking and updating the individual optimal position, the individual optimal fitness, the group optimal position and the group optimal fitness until the maximum iteration number is reached, and outputting a group of clustering center points serving as initial center points of a K-means algorithm.
8. The recommendation method of a psychological assessment according to claim 1 wherein step 4 further comprises the sub-steps of:
step 4.1, constructing a user-scale evaluation score matrix in the cluster, calculating the similarity between the target user and other users in the cluster, and selecting L users with the highest similarity as nearest neighbor users of the target user;
step 4.2, predicting the score of each psychological assessment scale used by the target user;
and 4.3, after the predicted scores of the target users for each psychological assessment are obtained, taking the highest predicted score of the multi-item single-dimensional scale as the predicted score of the multi-dimensional scale, sorting each psychological assessment according to the descending order of the predicted scores of the target users, and taking the first N item scales as the recommended scales of the target users to output.
9. The recommendation method of a psychological assessment according to claim 8, wherein the calculation formula of the predictive assessment score is as follows:
Figure FDA0004073774450000041
wherein F is U,S Is the predicted score of the user U for the table S,
Figure FDA0004073774450000042
is the average of the user's score of the table, C is the nearest neighbor set of users for the target user U, sim (U, U j ) Is a target user U and a nearest neighbor user U j Cosine similarity of P U,S Is the score of the user U to the scale S, i.e. the user-scale evaluates one of the score matrices. />
CN202310065461.6A 2023-01-12 2023-01-12 Recommendation method of psychological assessment Pending CN115994271A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310065461.6A CN115994271A (en) 2023-01-12 2023-01-12 Recommendation method of psychological assessment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310065461.6A CN115994271A (en) 2023-01-12 2023-01-12 Recommendation method of psychological assessment

Publications (1)

Publication Number Publication Date
CN115994271A true CN115994271A (en) 2023-04-21

Family

ID=85993359

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310065461.6A Pending CN115994271A (en) 2023-01-12 2023-01-12 Recommendation method of psychological assessment

Country Status (1)

Country Link
CN (1) CN115994271A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116364261A (en) * 2023-06-02 2023-06-30 北京小懂科技有限公司 Intelligent recommendation method, system, equipment and storage medium
CN116596640A (en) * 2023-07-19 2023-08-15 国网山东省电力公司营销服务中心(计量中心) Recommendation method, system, equipment and storage medium for electric power retail electric charge package
CN117352114A (en) * 2023-10-16 2024-01-05 北京心企领航科技有限公司 Recommendation method and system of psychological assessment scale based on clustering algorithm
CN117851464A (en) * 2024-03-07 2024-04-09 济南道图信息科技有限公司 Auxiliary analysis method for user behavior pattern for psychological assessment

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116364261A (en) * 2023-06-02 2023-06-30 北京小懂科技有限公司 Intelligent recommendation method, system, equipment and storage medium
CN116596640A (en) * 2023-07-19 2023-08-15 国网山东省电力公司营销服务中心(计量中心) Recommendation method, system, equipment and storage medium for electric power retail electric charge package
CN117352114A (en) * 2023-10-16 2024-01-05 北京心企领航科技有限公司 Recommendation method and system of psychological assessment scale based on clustering algorithm
CN117352114B (en) * 2023-10-16 2024-04-09 北京心企领航科技有限公司 Recommendation method and system of psychological assessment scale based on clustering algorithm
CN117851464A (en) * 2024-03-07 2024-04-09 济南道图信息科技有限公司 Auxiliary analysis method for user behavior pattern for psychological assessment
CN117851464B (en) * 2024-03-07 2024-05-14 济南道图信息科技有限公司 Auxiliary analysis method for user behavior pattern for psychological assessment

Similar Documents

Publication Publication Date Title
CN115994271A (en) Recommendation method of psychological assessment
US8583571B2 (en) Facility for reconciliation of business records using genetic algorithms
CN112667899A (en) Cold start recommendation method and device based on user interest migration and storage equipment
WO2006004131A1 (en) Company evaluation device, company evaluation program, and company evaluation method
CN113051291A (en) Work order information processing method, device, equipment and storage medium
CN115309998B (en) Employment recommendation method and system based on big data
CN112562863A (en) Epidemic disease monitoring and early warning method and device and electronic equipment
CN112613953A (en) Commodity selection method, system and computer readable storage medium
CN115829683A (en) Power integration commodity recommendation method and system based on inverse reward learning optimization
CN115983622A (en) Risk early warning method of internal control cooperative management system
Atanasov et al. Talent spotting in crowd prediction
CN118485444A (en) Intelligent customer relationship management system based on big data
Ragapriya et al. Machine Learning Based House Price Prediction Using Modified Extreme Boosting
CN117807452A (en) Ordering method, device, equipment and storage medium based on target matching
CN111221915B (en) Online learning resource quality analysis method based on CWK-means
CN116385151A (en) Method and computing device for risk rating prediction based on big data
CN112506930B (en) Data insight system based on machine learning technology
CN116127194A (en) Enterprise recommendation method
CN115115414A (en) Second-hand car valuation method based on machine learning
WO2022047011A1 (en) Synthetic comparable market analysis systems and methods
CN114048977A (en) Engineer classification method and device and terminal equipment
CN113590673A (en) Data heat degree statistical method based on block chain deep learning
CN112818215A (en) Product data processing method, device, equipment and storage medium
Malara et al. Modelling the determinants of winning in public tendering procedures based on the activity of a selected company
CN112215385B (en) Student difficulty degree prediction method based on greedy selection strategy

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