CN114676390B - Searching method, system, device and storage medium for persons with similar psychological characteristics - Google Patents
Searching method, system, device and storage medium for persons with similar psychological characteristics Download PDFInfo
- Publication number
- CN114676390B CN114676390B CN202210584383.6A CN202210584383A CN114676390B CN 114676390 B CN114676390 B CN 114676390B CN 202210584383 A CN202210584383 A CN 202210584383A CN 114676390 B CN114676390 B CN 114676390B
- Authority
- CN
- China
- Prior art keywords
- psychological
- trait
- person
- traits
- current
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 50
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 239000013598 vector Substances 0.000 claims description 55
- 238000010606 normalization Methods 0.000 claims description 27
- 238000012360 testing method Methods 0.000 claims description 27
- 238000012545 processing Methods 0.000 claims description 12
- 239000000203 mixture Substances 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 description 9
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006996 mental state Effects 0.000 description 4
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 239000005018 casein Substances 0.000 description 1
- BECPQYXYKAMYBN-UHFFFAOYSA-N casein, tech. Chemical compound NCCCCC(C(O)=O)N=C(O)C(CC(O)=O)N=C(O)C(CCC(O)=N)N=C(O)C(CC(C)C)N=C(O)C(CCC(O)=O)N=C(O)C(CC(O)=O)N=C(O)C(CCC(O)=O)N=C(O)C(C(C)O)N=C(O)C(CCC(O)=N)N=C(O)C(CCC(O)=N)N=C(O)C(CCC(O)=N)N=C(O)C(CCC(O)=O)N=C(O)C(CCC(O)=O)N=C(O)C(COP(O)(O)=O)N=C(O)C(CCC(O)=N)N=C(O)C(N)CC1=CC=CC=C1 BECPQYXYKAMYBN-UHFFFAOYSA-N 0.000 description 1
- 235000021240 caseins Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009532 heart rate measurement Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000001671 psychotherapy Methods 0.000 description 1
- 230000000506 psychotropic effect Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Child & Adolescent Psychology (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Artificial Intelligence (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system, a device and a storage medium for searching people with similar psychological traits, the method can be applied to the field of psychology, the corresponding mean value and variance are obtained by firstly calculating the information belonging to the same psychological traits in the information of the personnel in the database, normalizing the psychological characteristics according to the mean value and the variance, constructing a trait matrix according to the normalized psychological traits, then standardizing the psychological characteristics of the current tested person according to the mean value and the variance obtained by calculation to obtain the standard psychological characteristics of the current tested person, and then calculating the standard psychological traits of the current tested person and the trait distance of each in-library person identifier corresponding to the psychological traits in the trait matrix, and determining the target person close to the psychological traits of the current tested person in the information of the in-library persons according to the trait distances, thereby effectively improving the accuracy of searching results of the persons close to the psychological traits.
Description
Technical Field
The invention relates to the field of psychology, in particular to a method, a system, a device and a storage medium for searching people with similar psychological characteristics.
Background
Psychological traits refer to the level of psychological stress one person experiences when faced with different emergencies. In the psychotherapy process, the psychotherapist is matched with the prior patients with similar characteristics, and effective treatment reference data can be provided for doctors. In the related technology, when searching for similar people, a psychological consultant searches for a previous patient similar to the current patient according to own experience, and the accuracy of the search result is reduced by the searching mode.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a searching method, a system, a device and a storage medium for people with similar psychological characteristics, which can effectively improve the accuracy of the searching result.
On one hand, the embodiment of the invention provides a method for searching people with similar psychological characteristics, which comprises the following steps:
the method comprises the steps of obtaining information of people in the warehouse, wherein the information of the people in the warehouse comprises a plurality of identifications of the people in the warehouse, and each identification of the people in the warehouse is associated with a plurality of different psychological traits;
extracting all psychological traits which belong to the same type in the library personnel identification to form a trait library;
respectively calculating the mean value and the variance of the psychological traits in each trait library, and carrying out normalization processing on the psychological traits in the trait libraries according to the mean value and the variance;
constructing a trait matrix according to the normalized psychological traits;
standardizing the psychological traits of the current tested person according to the mean value and the variance to obtain the standard psychological traits of the current tested person;
calculating the standard psychological trait of the current tested person and a trait distance of each in-library person identifier corresponding to the psychological trait in the trait matrix, wherein the trait distance is determined by a cosine distance and an Euclidean distance;
and determining the target person with the psychological characteristics similar to the current tested person in the in-bank person information according to the characteristic distance.
In some embodiments, each of the psychoacoustic traits corresponds to a real number within the trait matrix.
In some embodiments, the calculating the mean and variance of the psychological traits separately within each trait library comprises:
the mean value of the psychological traits in each trait library is calculated by the following formula:
wherein,
means representing a psychological trait in a jth trait library;
a psychology feature vector representing psychology feature composition in the jth feature library; n represents the total number of psychological traits in the jth trait library;
the variance of the psychological trait in each trait library is calculated separately using the following formula:
wherein,
representing the variance of psychological traits in the jth trait library;
representing the psychological trait of the kth within the jth trait library.
In some embodiments, the normalizing the psychological trait in the trait library according to the mean and the variance includes:
the psychological traits in the trait library are normalized by adopting the following formula:
wherein,
representing the characteristic psychology characteristic vector after the j th psychology characteristic vector is normalized.
In some embodiments, the normalizing the psychological characteristic of the current human subject according to the mean and the variance comprises:
the psychological characteristics of the current human subject were normalized using the following formula:
wherein,
representing the current person under test after standardisationA psychometric trait vector;
representing a psychometric trait vector of a current human subject prior to normalization;
、
and
respectively, represent individual trait values within the psychometric trait vector of the current human subject prior to normalization.
In some embodiments, said calculating a trait distance between the standard psychological trait of the current human subject and each in-pool person identification corresponding psychological trait within the trait matrix comprises:
calculating the cosine distance between the standard psychological trait of the current tested person and the psychological trait corresponding to each in-bank person identifier in the trait matrix:
calculating the standard psychological traits of the current tested person and the Euclidean distance of each in-store person identifier corresponding to the psychological traits in the trait matrix;
and calculating the characteristic distance according to the cosine distance, the Euclidean distance and the weight harmonic coefficient.
In some embodiments, the determining, according to the characteristic distance, the target person whose psychological characteristic is similar to that of the current human subject in the in-bank person information includes:
when the characteristic distance meets the following formula, determining that target persons close to the psychological characteristics of the current tested person exist in the database person information:
wherein,
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a);
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a);
representing a hyper-parameter.
On the other hand, the embodiment of the invention provides a system for searching people with similar psychological traits, which comprises:
the system comprises an acquisition module, a storage management module and a storage management module, wherein the acquisition module is used for acquiring the information of the people in the storage, the information of the people in the storage comprises a plurality of identification of the people in the storage, and each identification of the people in the storage is associated with a plurality of different psychological traits;
the extraction module is used for extracting all psychological traits belonging to the same type from the library personnel identification to form a trait library;
the first calculation module is used for calculating the mean value and the variance of the psychological traits in each trait library respectively and carrying out normalization processing on the psychological traits in the trait library according to the mean value and the variance;
the construction module is used for constructing a trait matrix according to the normalized psychological traits;
the standardization processing module is used for standardizing the psychological traits of the current tested person according to the mean value and the variance to obtain the standard psychological traits of the current tested person;
the second calculation module is used for calculating a standard psychological trait of the current tested person and a trait distance of each in-library person identifier corresponding to the psychological trait in the trait matrix, wherein the trait distance is determined by a cosine distance and an Euclidean distance;
and the determining module is used for determining the target person with the psychological characteristics similar to the current tested person in the in-library person information according to the characteristic distance.
On the other hand, an embodiment of the present invention provides a device for searching people with similar psychological traits, including:
at least one memory for storing a program;
at least one processor for loading the program to execute the searching method of the person with similar psychological characteristics.
In another aspect, an embodiment of the present invention provides a storage medium, in which a computer-executable program is stored, and the computer-executable program is executed by a processor to implement the method for searching people with similar psychological characteristics.
The searching method for the people with similar psychological characteristics provided by the embodiment of the invention has the following beneficial effects:
the embodiment calculates the information belonging to the same psychological traits in the information of the persons in the library to obtain the corresponding mean value and variance, normalizing the psychological traits according to the mean value and the variance, constructing a traits matrix according to the normalized psychological traits, then standardizing the psychological traits of the current tested person according to the mean value and the variance obtained by calculation to obtain the standard psychological traits of the current tested person, and then calculating the standard psychological traits of the current human subject and the trait distance of each in-library person identifier corresponding to the psychological traits in the trait matrix, and determining target persons close to the psychological traits of the current human subject in the library person information according to the trait distances.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The invention is further described with reference to the following figures and examples, in which:
FIG. 1 is a flowchart of a method for searching people with similar psychological characteristics according to an embodiment of the present invention;
FIG. 2 is a flow chart of a first computing mode according to an embodiment of the present invention;
FIG. 3 is a flow chart of a second calculation mode according to the embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality is one or more, the meaning of a plurality is two or more, and the above, below, exceeding, etc. are understood as excluding the present numbers, and the above, below, within, etc. are understood as including the present numbers. If it is stated that the first and second are only for the purpose of distinguishing technical peculiarities, it is not to be understood as indicating or implying a relative importance or implying a number of indicated technical peculiarities or implying a precedence relationship between indicated technical peculiarities.
In the description of the present invention, unless otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
In the description of the present invention, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples," etc., means that a particular feature or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Referring to fig. 1, an embodiment of the present invention provides a method for searching people with similar psychological traits. The method can be applied to a server, a cloud end or a processor of a psychological test platform.
Taking the method of the present embodiment applied to the server as an example, the method of the present embodiment includes, but is not limited to, the following steps:
step 130, respectively calculating the mean value and the variance of the psychological traits in each trait library, and carrying out normalization processing on the psychological traits in the trait library according to the mean value and the variance;
step 150, standardizing the psychological traits of the current human subject according to the mean value and the variance to obtain the standard psychological traits of the current human subject;
step 160, calculating a trait distance between the standard psychological trait of the current tested person and each in-library person identifier corresponding to the psychological trait in the trait matrix, wherein the trait distance is determined by a cosine distance and an Euclidean distance;
and 170, determining the target person with the psychological characteristics similar to the current tested person in the in-store person information according to the characteristic distance.
In the present embodiment, it is assumed that in the library staff informationIf the database comprises N in-store personnel, N in-store personnel identifiers exist, and the N in-store personnel identifiers can be represented as
，
Representing one of the in-store personnel identifications. K psychological states constitute a psychological trait vector
. Wherein,
is a scalar quantity, representing the mental state value of the jth scene. The mental state value can be a physiological index such as heart rate in a specific scene, and can also be a metering value obtained through other ways. Use of
Representing a person to be tested
The psychometric trait vector of (1). Use of
And j-th mental state values representing all tested persons, namely j-th mental state values representing all the persons in the database in the information of the persons in the database. And, assume that M represents a psychological trait matrix of all the test persons, the matrix M being as shown in formula (1):
formula (1)
In the embodiment of the present application, each psychological trait corresponds to a real number in the trait matrix, and it can be known from practical situations that the numerical difference between different traits is large, and if the psychological trait is directly operated, some psychological traits with large numerical values will generate large offset to the distance. Based on this, the present embodiment processes psychological traits through a normalization method. Specifically, by respectively normalizing the psychological characteristics of the same type. For the feature matrix M, the column vectors are normalized separately. Specifically, for the jth psychometric feature vector
The psychometric trait vector exists in the jth column in the matrix M and corresponds to the jth trait library, and the present embodiment calculates the mean value of the psychometric trait vector of the jth column by formula (2)
Calculating the variance of the psychometric feature vector of the j-th column by formula (3):
Wherein,
means representing a psychological trait in a jth trait library;
a psychology feature vector representing psychology feature composition in the jth feature library; n represents the total number of psychological traits in the jth trait library;
Wherein,
representing the variance of psychological traits in the jth trait library;
representing the psychological trait of the kth within the jth trait library.
After obtaining the mean and the variance of the psychological traits of the jth column, the psychological traits of the jth column can be calculated by the formula (4)
Normalization is carried out to obtain the normalized psychological traits
：
Formula (4)
For other column vectors in the feature matrix M, the corresponding mean and variance can be calculated by using the formula (2) and the formula (3). Specifically, after the calculation of all the column vectors of the trait matrix M is completed, the mean X of all the psychological traits shown in equation (5) and the variance shown in equation (6) can be obtained
：
After the mean values and the variance of all the columns of the trait matrix M are obtained, all the psychological traits of the trait matrix M may be normalized according to the formula (7), so as to obtain a normalized trait matrix
：
Formula (7)
In the embodiment of the application, after the normalization processing of the psychological traits of the persons in the library is completed. When the current tested person needs to be searched whether the person close to the current tested person exists in the library person, the current tested person is assumed to be
The psychological trait vector corresponding to the tested person is
Wherein
、
. In the embodiment, the psychological traits of the current human subject are normalized by the mean and variance of the psychological traits of the human subject in the library, and the processing procedure is shown in formula (8):
formula (8)
Wherein,
representing a normalized psychometric trait vector of a current human subject;
representing a psychometric trait vector of a current human subject prior to normalization;
、
and
respectively, represent individual trait values within the psychometric trait vector of the current human subject prior to normalization.
After the standardization processing of the psychological traits of the current human subject is completed, the trait distance between the current human subject and each person in the database in the information of the person in the database is calculated. Specifically, the trait distance is calculated by calculating the distance between the psychological trait vector of the current human subject and the psychological trait vector of each person in the pool. The present embodiment determines the final trait distance by the cosine distance and the euclidean distance. The cosine distance between the current tested person and each person in the warehouse can be calculated by the formula (9):
formula (9)
Wherein,
indicating the current person under test
With any one person in stock
The cosine of the distance of (a) is,
indicating the current person under test
The psychometric trait scalar at line k after normalization,
indicating any one person in the warehouse
Psychographic trait scalar at line k, i.e. on-Bank personnel
In a feature matrix
The psychometric trait scalar of line k.
The euclidean distance between the current test person and each of the persons in the warehouse can be calculated by the formula (10):
Wherein,
indicating the current person under test
With any one person in the warehouse
The euclidean distance of (c).
Obtaining the current person to be tested
And the person in the warehouse
After the euclidean distance and the cosine distance, the present embodiment obtains the current human subject through calculation of formula (11)
And the person in the warehouse
Characteristic distance of
：
Wherein,
in order to weight the harmonic coefficients, the coefficients are,
。
after the characteristic distances between the current tested person and all the persons in the warehouse are obtained through calculation, the current tested person shown in the formula (12) can be obtained
Idiosyncratic distances to all in-bank personnel:
Obtaining the current person to be tested
After the characteristic distances from all the in-store personnel, judging whether the in-store personnel exist in the current tested personnel or not according to a formula (13)
The close target person:
Wherein,
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a);
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a);
represents a hyper-parameter, theHyper-parameters represent the maximum distance that satisfies similar characteristics of psychological traits.
In the formula (13), when
Greater than a hyperparameter
Then do not consider
And with
The relation of (2) can directly determine that target persons with psychological characteristics close to that of the current tested person do not exist in the information of the library persons; when in use
Is greater than
Then do not consider
And hyper-parameter
The relation of (2) can directly determine that target persons with psychological characteristics close to that of the current tested person do not exist in the information of the library persons; when in use
Less than or equal to the hyperparameter
And is
Is less than or equal to
Determining the person in the library in the information of the person in the library
The characteristic information of the database is similar to the characteristic information of the current tested person, and the person in the database is about to be in the database
As the target person.
When the embodiment of the application is applied to an actual psychological test process, historical case information of a psychological consultant during developing psychological consultation is stored in a tested person set of a computer system, each option of psychological trait assessment of tested participation is used as one trait of the psychological trait, all options of psychological assessment of each case are used as F, and the options are updated into a trait matrix M. And when the psychological consultant finishes each psychological consultation, updating the in-bank personnel identifier U and the characteristic matrix M, namely updating the information of the in-bank personnel.
When the personnel identifier U and the characteristic matrix M in the library are updated, the mean value and the variance of all column vectors of the characteristic matrix M are synchronously updated, and the normalized characteristic matrix is updated through the updated mean value and variance
。
When newly receiving a psychological consultation case
In time, psychological consultants develop tests of psychological traits through the system of the invention. Specifically, two different psychological trait acquisition modes can be simultaneously supported: the first mode is obtained by means of psychological evaluation mode, wherein each evaluated question is used as a measure of psychological traits, and each option value of the answer to be tested is used as a psychological trait; the second mode is that different scenes are displayed through the system, and the physiological signal change under the scenes is obtained through the wearable device as psychological traits. Obtaining all of the cases by any one of the two waysVector formed by evaluation options
. Psychology attribute vector of individual case using mean and variance of column vector in attribute matrix M
Preprocessing is carried out to obtain normalized psychology trait vectors
。
Use of
From
According to a distance calculation formula
Neutralization of
Nearest vector if the distance is less than the fusing distance
Then the history case represented by the vector is
The psychological characteristics of (1) approximate the case. The return case is
The consulting scheme of the similar personal case of psychological traits is used for the psychological consultant to refer to, otherwise, a new personal case type is prompted.
In the embodiment of the present application, in the calculation process of the psychotropic vector, the embodiment includes two calculation modes:
as shown in fig. 2, the first calculation mode is to search for a target person close to the current human subject through steps 160 and 170 after the current human subject completes all psychological trait measures and generates a complete psychological trait vector. The first calculation mode is suitable for a human subject who has the capability to perform a full-scale mental trait measurement.
As shown in FIG. 3, the second calculation mode is an iterative measurement, that is, when the current human subject completes the psychological trait measurement of one scene, the psychological trait vector with the newest psychological trait is formed by all the psychological traits that have been currently measured
Where the length K of the vector is the current value, e.g. K is 1 when the current human subject has only completed psychometric trait measurement of the first scene, K is 2 when the psychometric trait measurement of the second scene has been completed, and so on. Using the current eigenvector vector
Calculating the vector after the characteristic normalization
. Calculations of close persons are performed according to step 160 and step 170. In this calculation mode, due to the normalized in-bank membership matrix
The rows of (a) represent different persons under test and the columns represent different traits. Thus, use of non-full-weight traits
When performing matching calculation, only need to be based on
Characteristic length K pairs of
Is mapped to obtain the column vector
The sub-matrix of (a). The second calculation mode is suitable for use in a scene under test that does not have the capability to perform a full measure of psychological traits.
In the embodiment, two calculation modes are set, so that the searching of similar persons can be performed on the option set of one psychological questionnaire, the searching of similar persons can be performed on the option sets of a plurality of psychological questionnaires, and meanwhile, the searching of persons with similar psychological characteristics can be performed based on heart rate measurement information in a specific scene.
In summary, the present embodiment has the following advantages:
first, in the present embodiment, by introducing a single column vector normalization, normalization is performed according to the distribution of different column vectors, rather than global normalization, compared with the existing normalization method, so that normalization can be performed according to the severity of psychological reaction in a scene, and thus the problem of insignificant traits caused by global normalization is avoided.
The second point, the embodiment introduces the weighted harmonic distance of the euclidean distance and the cosine for measuring the distance between the two vectors, and compared with the existing method that a single distance measurement function is adopted for the distance between the two vectors, the embodiment introduces the weighted harmonic coefficient, and the embodiment blends the two distances to measure the distribution directions of the two measured psychological traits on the one hand, and to measure the reaction degree difference of the two measured psychological stimuli on the other hand, thereby more accurately measuring the similarity degree of the two measured psychological traits.
Third, the present embodiment fuses by introducing the maximum distance
. Because the existing vector similarity finding method always has a vector with the minimum distance according to the distance sorting, even if the distance between the vectors with the minimum distance is still large, in the psychological trait similarity measurement, when the distance between two psychological trait vectors with the minimum distance is still large, the method cannot be used for judging that two persons tested to be similar traits are not used, and the method cannot be used for judging that the two persons tested to be similar traits are not usedCan be applied to similar treatment regimens. Thus, the present embodiment introduces a maximum distance fusing factor
The problem is solved.
The fourth advantage of the dynamic measurement introduced in this embodiment is that it can support any length of psychology feature vector to perform matching of psychology features, so that it is not necessary to perform feature alignment on the vector, or it is not necessary to perform all psychology feature measurements in a trial to perform similarity search.
The embodiment of the invention provides a system for searching people with similar psychological characteristics, which comprises:
the system comprises an acquisition module, a storage management module and a storage management module, wherein the acquisition module is used for acquiring the information of the people in the storage, the information of the people in the storage comprises a plurality of identification of the people in the storage, and each identification of the people in the storage is associated with a plurality of different psychological traits;
the extraction module is used for extracting all psychological traits belonging to the same type from the library personnel identification to form a trait library;
the first calculation module is used for calculating the mean value and the variance of the psychological traits in each trait library respectively and carrying out normalization processing on the psychological traits in the trait library according to the mean value and the variance;
the construction module is used for constructing a trait matrix according to the normalized psychological traits;
the standardization processing module is used for standardizing the psychological traits of the current tested person according to the mean value and the variance to obtain the standard psychological traits of the current tested person;
the second calculation module is used for calculating the standard psychological traits of the current tested person and the trait distance of each in-library person identifier corresponding to the psychological traits in the trait matrix, and the trait distance is determined by cosine distance and Euclidean distance;
and the determining module is used for determining the target person with the psychological characteristics similar to the current tested person in the in-library person information according to the characteristic distance.
The content of the embodiment of the method of the invention is all applicable to the embodiment of the system, the function of the embodiment of the system is the same as the embodiment of the method, and the beneficial effect achieved by the embodiment of the system is the same as the beneficial effect achieved by the method.
The embodiment of the invention provides a device for searching people with similar psychological characteristics, which comprises:
at least one memory for storing a program;
at least one processor for loading the program to perform the method of searching for people with similar psychological traits as shown in FIG. 1.
The content of the method embodiment of the invention is all applicable to the device embodiment, the functions specifically realized by the device embodiment are the same as those of the method embodiment, and the beneficial effects achieved by the device embodiment are also the same as those achieved by the method.
An embodiment of the present invention provides a storage medium in which a computer-executable program is stored, and the computer-executable program is executed by a processor to implement the method for searching for people with similar psychological traits as shown in fig. 1.
Embodiments of the present invention also provide a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions can be read by a processor of a computer device from a computer-readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the searching method of the psychologically close persons as shown in fig. 1.
The embodiments of the present invention have been described in detail with reference to the drawings, but the present invention is not limited to the embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention. Furthermore, the embodiments of the present invention and the features of the embodiments may be combined with each other without conflict.
Claims (8)
1. A method for searching people with similar psychological characteristics is characterized by comprising the following steps:
acquiring in-store personnel information, wherein the in-store personnel information comprises a plurality of in-store personnel identifiers, and each in-store personnel identifier is associated with a plurality of different psychological traits;
extracting all psychological traits belonging to the same type in the library personnel identification to form a trait library;
respectively calculating the mean value and the variance of the psychological traits in each trait library, and carrying out normalization processing on the psychological traits in the trait libraries according to the mean value and the variance;
constructing a trait matrix according to the normalized psychological traits
；
Standardizing the psychological traits of the current tested person according to the mean value and the variance to obtain the standard psychological traits of the current tested person;
calculating the standard psychological trait of the current tested person and a trait distance of each in-library person identifier corresponding to the psychological trait in the trait matrix, wherein the trait distance is determined by a cosine distance and an Euclidean distance;
determining target persons with similar psychological characteristics to the current tested persons in the in-store person information according to the characteristic distance;
after the target person of the current tested person is determined, updating the mean value and the variance of the psychological traits in each trait library according to the psychological traits of the current tested person;
the calculating the characteristic distance between the standard psychological characteristic of the current tested person and each in-library person identifier corresponding to the psychological characteristic in the characteristic matrix comprises the following steps:
calculating the cosine distance between the standard psychological trait of the current tested person and each in-library person identifier corresponding to the psychological trait in the trait matrix by the following formula, wherein the cosine distance is used for measuring the distribution directions of the two tested psychological traits:
wherein,
indicating the current person under test
With any one person in stock
The cosine of the distance of (a) is,
indicating the current person under test
The psychometric trait scalar at line k after normalization,
indicating any one person in the warehouse
Psychographic trait scalar at line k, i.e. on-Bank personnel
In a feature matrix
The psychometric trait scalar of the k-th row of (a),
indicating the current person under test
The psycho-attribute vector after normalization is performed,
indicating any one person in the warehouse
The normalized psychometric trait vector of (1);
calculating the Euclidean distance between the standard psychological traits of the current tested person and the psychological traits corresponding to each person identifier in the database in the trait matrix by the following formula, wherein the Euclidean distance is used for measuring the reaction degree difference of the psychological stimuli of the two tested persons:
wherein,
indicating the current person under test
With any one person in stock
K represents the total number of psychological traits;
according to the cosine distance, the Euclidean distance and the weight harmonic coefficient, the idiosyncrasy distance is calculated through the following formula:
wherein,
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a) is,
in order to weight the harmonic coefficients, the coefficients are,
；
the step of determining the target person with the psychological characteristics similar to the current tested person in the in-bank person information according to the characteristic distance comprises the following steps:
when the characteristic distance meets the following formula, determining that target persons close to the psychological characteristics of the current tested person exist in the database person information:
wherein,
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a);
the representation of the hyper-parameter is,
a matrix representing the psychological trait composition of all human subjects.
2. The method of claim 1, wherein each of the psychological traits corresponds to a real number in the trait matrix.
3. The method according to claim 1, wherein the calculating the mean and variance of the psychological traits in each trait library respectively comprises:
the mean value of the psychological traits in each trait library is calculated by the following formula:
wherein,
means representing a psychological trait within a jth trait library;
a psychology feature vector representing psychology feature composition in the jth feature library; n represents the total number of psychological traits in the jth trait library;
the variance of the psychological trait in each trait library is calculated separately using the following formula:
wherein,
representing the variance of psychological traits in the jth trait library;
representing the psychological trait of the kth within the jth trait library.
4. The method according to claim 3, wherein the normalizing the psychological traits in the trait library according to the mean and the variance comprises:
the psychological traits in the trait library are normalized by adopting the following formula:
wherein,
representing the characteristic psychology characteristic vector after the j th psychology characteristic vector is normalized.
5. The method for searching people with similar psychological characteristics according to claim 1, wherein the normalizing the psychological characteristics of the current human subject according to the mean and the variance comprises:
the psychological characteristics of the current human subject were normalized using the following formula:
wherein,
indicating signStandardized psychology trait vectors of the current tested person;
representing a psychometric trait vector of a current human subject prior to normalization;
、
and
respectively, represent individual trait values within the psychometric trait vector of the current human subject prior to normalization.
6. A system for searching persons with similar psychological characteristics, comprising:
the system comprises an acquisition module, a storage management module and a storage management module, wherein the acquisition module is used for acquiring the information of the people in the storage, the information of the people in the storage comprises a plurality of identification of the people in the storage, and each identification of the people in the storage is associated with a plurality of different psychological traits;
the extraction module is used for extracting all psychological traits belonging to the same type from the library personnel identification to form a trait library;
the first calculation module is used for calculating the mean value and the variance of the psychological traits in each trait library respectively and carrying out normalization processing on the psychological traits in the trait library according to the mean value and the variance;
a construction module for constructing a trait matrix according to the normalized psychological traits
；
The standardization processing module is used for standardizing the psychological traits of the current tested person according to the mean value and the variance to obtain the standard psychological traits of the current tested person;
the second calculation module is used for calculating the standard psychological traits of the current tested person and the trait distance of each in-library person identifier corresponding to the psychological traits in the trait matrix, and the trait distance is determined by cosine distance and Euclidean distance;
the determining module is used for determining the target person with the psychological characteristics similar to the current tested person in the in-store person information according to the characteristic distance;
after the target person of the current human subject is determined, updating the mean value and the variance of the psychological traits in each trait library according to the psychological traits of the current human subject;
the calculating the characteristic distance between the standard psychological characteristic of the current tested person and each in-library person identifier corresponding to the psychological characteristic in the characteristic matrix comprises the following steps:
calculating the cosine distance between the standard psychological trait of the current tested person and each in-library person identifier corresponding to the psychological trait in the trait matrix by the following formula, wherein the cosine distance is used for measuring the distribution directions of the two tested psychological traits:
wherein,
indicating the current person under test
With any one person in stock
The cosine of the distance of (a) is,
indicating the current person under test
The psychometric trait scalar at line k after normalization,
indicating any one person in the library
Psychographic trait scalar at line k, i.e. on-Bank personnel
In a feature matrix
The psychometric trait scalar of the k-th row of (a),
indicating the current person under test
The psychometric trait vector after normalization is performed,
indicating any one person in the warehouse
The normalized psychometric trait vector of (1);
calculating the Euclidean distance between the standard psychological traits of the current tested person and the psychological traits corresponding to each person identifier in the database in the trait matrix by the following formula, wherein the Euclidean distance is used for measuring the reaction degree difference of the psychological stimuli of the two tested persons:
wherein,
indicating the current person under test
With any one person in stock
K represents the total number of psychological traits;
according to the cosine distance, the Euclidean distance and the weight harmonic coefficient, the idiosyncrasy distance is calculated through the following formula:
wherein,
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a) is,
in order to weight the harmonic coefficients, the coefficients are,
；
the step of determining the target person with the psychological characteristics similar to the current tested person in the in-bank person information according to the characteristic distance comprises the following steps:
when the characteristic distance meets the following formula, determining that target persons close to the psychological characteristics of the current tested person exist in the database person information:
wherein,
indicating the current person under test
And the person in the warehouse in the information of the person in the warehouse
The characteristic distance of (a);
the representation of the hyper-parameter is,
a matrix representing the psychological trait composition of all the human subjects.
7. A device for searching people with similar psychological characteristics is characterized by comprising:
at least one memory for storing a program;
at least one processor configured to load the program to perform the method of searching for psychologically close persons according to any of claims 1-5.
8. A storage medium having stored therein a computer-executable program for implementing a method for searching for psychologically close persons according to any one of claims 1-5 when the computer-executable program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210584383.6A CN114676390B (en) | 2022-05-27 | 2022-05-27 | Searching method, system, device and storage medium for persons with similar psychological characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210584383.6A CN114676390B (en) | 2022-05-27 | 2022-05-27 | Searching method, system, device and storage medium for persons with similar psychological characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114676390A CN114676390A (en) | 2022-06-28 |
| CN114676390B true CN114676390B (en) | 2022-08-16 |
Family
ID=82079913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210584383.6A Active CN114676390B (en) | 2022-05-27 | 2022-05-27 | Searching method, system, device and storage medium for persons with similar psychological characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114676390B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915561A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Intelligent disease attribute matching method |
| WO2018030906A2 (en) * | 2016-08-08 | 2018-02-15 | Общество С Ограниченной Ответственностью Эксперно Аналитическое Объединение "Проф-Диалог" | Method for the computer psychodiagnosis of individual personality traits |
| CN108549873A (en) * | 2018-04-19 | 2018-09-18 | 北京华捷艾米科技有限公司 | Three-dimensional face identification method and three-dimensional face recognition system |
| CN109214273A (en) * | 2018-07-18 | 2019-01-15 | 平安科技（深圳）有限公司 | Facial image comparison method, device, computer equipment and storage medium |
| CN113661497A (en) * | 2020-04-09 | 2021-11-16 | 商汤国际私人有限公司 | Matching method, matching device, electronic equipment and computer-readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070087313A1 (en) * | 2003-12-15 | 2007-04-19 | Vest Herb D | Method for improving relationship compatibility analysis based on the measure of psychological traits |
| US9589107B2 (en) * | 2014-11-17 | 2017-03-07 | Elwha Llc | Monitoring treatment compliance using speech patterns passively captured from a patient environment |
| CN106682445B (en) * | 2017-01-21 | 2019-03-05 | 浙江连信科技有限公司 | A kind of psychological test system |
| CN109998570A (en) * | 2019-03-11 | 2019-07-12 | 山东大学 | Inmate's psychological condition appraisal procedure, terminal, equipment and system |
| CN111897967A (en) * | 2020-07-06 | 2020-11-06 | 北京大学 | Medical inquiry recommendation method based on knowledge graph and social media |
| CN114359930A (en) * | 2021-12-17 | 2022-04-15 | 华南理工大学 | Depth cross-modal hashing method based on fusion similarity |
-
2022
- 2022-05-27 CN CN202210584383.6A patent/CN114676390B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915561A (en) * | 2015-06-11 | 2015-09-16 | 万达信息股份有限公司 | Intelligent disease attribute matching method |
| WO2018030906A2 (en) * | 2016-08-08 | 2018-02-15 | Общество С Ограниченной Ответственностью Эксперно Аналитическое Объединение "Проф-Диалог" | Method for the computer psychodiagnosis of individual personality traits |
| CN108549873A (en) * | 2018-04-19 | 2018-09-18 | 北京华捷艾米科技有限公司 | Three-dimensional face identification method and three-dimensional face recognition system |
| CN109214273A (en) * | 2018-07-18 | 2019-01-15 | 平安科技（深圳）有限公司 | Facial image comparison method, device, computer equipment and storage medium |
| CN113661497A (en) * | 2020-04-09 | 2021-11-16 | 商汤国际私人有限公司 | Matching method, matching device, electronic equipment and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114676390A (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Roebianto et al. | Content validity: Definition and procedure of content validation in psychological research | |
| CN111341446B (en) | Personalized physical examination package recommendation method | |
| Guilleux et al. | RespOnse Shift ALgorithm in Item response theory (ROSALI) for response shift detection with missing data in longitudinal patient-reported outcome studies | |
| Wang et al. | An automatic assessment system of diabetic foot ulcers based on wound area determination, color segmentation, and healing score evaluation | |
| CN109934723B (en) | Medical insurance fraud behavior identification method, device and equipment | |
| Kong et al. | Combining principal component analysis and the evidential reasoning approach for healthcare quality assessment | |
| CN109119137A (en) | A kind of method for detecting abnormality, device, server and storage medium | |
| CN116705300A (en) | Medical decision assistance method, system and storage medium based on sign data analysis | |
| Wickham et al. | Accuracy and bias in perceptions of conflict style among same-sex and heterosexual couples | |
| Fitra et al. | Effect of Workload, Compensation and Employee Commitment To the Employees Performance of Public Works and Spatial Arrangements Office of Karimun District | |
| Zalewska-Puchała et al. | Attitudes of polish nurses toward selected national groups | |
| Nagadeepa et al. | Artificial intelligence based cervical cancer risk prediction using m1 algorithms | |
| CN114676390B (en) | Searching method, system, device and storage medium for persons with similar psychological characteristics | |
| CN116350203B (en) | Physical testing data processing method and system | |
| Kubiatko et al. | Comparison of the effects of gender variable on attitudes towards the teaching profession by random and fixed effects model: Meta-Analysis | |
| US20230060794A1 (en) | Diagnostic Tool | |
| US20240134886A1 (en) | Classification system | |
| CN113140315B (en) | Health self-testing system, server and health detection system | |
| Thomas | Mental tests as instruments of science. | |
| Adalian | General considerations about data and selection of statistical approaches | |
| Harrison et al. | Modern psychometric measurement and computerized adaptive testing | |
| Harren et al. | Sex roles and cognitive styles as predictors of Holland typologies | |
| CN111370095A (en) | IC card based traditional Chinese medicine constitution distinguishing and conditioning test system and test method | |
| Duffy et al. | Deep Learning Discovery of Demographic Biomarkers in Echocardiography | |
| CN111261264A (en) | Intelligent physique testing device and method and storage medium |
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 |