CN114969375A - Method and system for giving artificial intelligence learning to machine based on psychological knowledge - Google Patents
Method and system for giving artificial intelligence learning to machine based on psychological knowledge Download PDFInfo
- Publication number
- CN114969375A CN114969375A CN202210652233.4A CN202210652233A CN114969375A CN 114969375 A CN114969375 A CN 114969375A CN 202210652233 A CN202210652233 A CN 202210652233A CN 114969375 A CN114969375 A CN 114969375A
- Authority
- CN
- China
- Prior art keywords
- psychological
- data
- information
- knowledge
- psychological state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Algebra (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention belongs to the technical field of artificial intelligence learning of machines, and discloses a method and a system for endowing artificial intelligence learning of machines based on psychological knowledge, wherein a large amount of psychological disease data can be effectively managed and utilized through a psychological knowledge map construction method, and a plurality of applications such as knowledge search, intelligent question answering and the like can be developed on the basis of the knowledge map; aiming at a deep learning model which lacks a large amount of labeled data training, the invention uses the ALBERT language model to pre-train the linguistic data of the psychological diseases, brings rich semantic information for the deep learning model, and can effectively improve the accuracy of entity recognition; meanwhile, the method for evaluating the psychological state of the user eliminates the influence of individual subjective factors on data collection, and is beneficial to more accurately evaluating the psychological health state.
Description
Technical Field
The invention belongs to the technical field of artificial intelligence learning of machines, and particularly relates to a method and a system for endowing machines with artificial intelligence learning based on psychological knowledge.
Background
Machine refers to a device assembled by parts and components, which can be operated to replace human labor, perform energy conversion or produce useful work. Machines are generally composed of a power section, a transmission section, an execution section, and a control section. From an energy perspective, a machine is a device that utilizes or converts mechanical energy, a prime mover such as an internal combustion engine, a steam engine, an electric motor, etc. that converts other forms of energy into mechanical energy, and a working machine such as various machine tools, cranes, compressors, etc. that utilizes mechanical energy to perform useful work. With the development of scientific technology, the concept of machines is constantly being updated and changed. However, the mental disease data labeling cost adopted by the existing method for giving artificial intelligence learning to the machine based on psychological knowledge is high, and the recognition accuracy is not high often due to the lack of a neural network trained by a large amount of labeling data; the mental disease knowledge graph belongs to a knowledge graph in the professional field, the required knowledge quality is higher, and the existing entity recognition algorithm is difficult to avoid making mistakes when extracting complex entities due to the lack of guidance of prior knowledge, so that professionals are required to carry out secondary correction, and manpower and material resources are consumed; meanwhile, the assessment of the mental health state is inaccurate.
In summary, the problems of the prior art are as follows: the traditional method for giving artificial intelligent learning to a machine based on psychological knowledge has high labeling cost of psychological disease data, and a neural network lacking a large amount of labeling data training is not high in identification precision; the mental disease knowledge graph belongs to a knowledge graph in the professional field, the required knowledge quality is higher, and the existing entity recognition algorithm is difficult to avoid making mistakes when extracting complex entities due to the lack of guidance of prior knowledge, so that professionals are required to carry out secondary correction, and manpower and material resources are consumed; meanwhile, the assessment of the mental health state is inaccurate.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for giving artificial intelligence learning to a machine based on psychological knowledge.
The invention is realized in such a way that a method for giving artificial intelligence learning to a machine based on psychological knowledge comprises the following steps:
acquiring basic information, emotion information and position information of a monitored object; wherein the basic information at least comprises the name and the head portrait picture of the monitored object;
matching corresponding scene correlation events by taking the position information as a basis; analyzing the basic information, the emotion information, the position information and the scene correlation event by using a preset psychological state analysis model to obtain the psychological state of the monitored object; establishing a psychological state document library;
performing word segmentation and intelligent abstract preprocessing on the documents in the physiological state document library to obtain keywords, performing relevance analysis on the obtained keywords, processing the values provided in the step, calculating the criticality value of the keywords aiming at the documents, and obtaining the keywords with assignments;
analyzing the user character according to the psychological knowledge map to obtain a user character tendency value, and evaluating the psychological state of the user;
matching the obtained personality tendency value with the obtained key degree value of the key words to obtain a document library with personality tendency attributes; when a user initiates an access request, the document library with the personality tendency attribute gives out the document with the personality tendency attribute.
Further, in step two, the mental state analysis model includes:
decomposing a psychological state signal in a time-frequency domain by utilizing wavelet packet transformation, and extracting a psychological state change rule of a psychological state wave;
secondly, expanding the public space mode from two types of modes to a plurality of types of modes by adopting a one-to-one strategy, and extracting feature vectors for the psychological state of the change rule of the psychological state by utilizing the one-to-one public space mode;
thirdly, selecting the dimension of the characteristic vector according to the distribution characteristics of the characteristic values;
the improved public spatial mode feature extraction method for analyzing the emotional state signals extracts the psychological state of the psychological state change rule from the original psychological state signals, and comprises the following steps: decomposing the psychological state signal in a time-frequency domain by adopting wavelet packet transformation, and performing combined reconstruction on node coefficients of a plurality of sub-bands corresponding to the psychological state change frequency band so as to extract a psychological state change rule psychological state signal consistent with the original psychological state signal form;
the improved public space mode feature extraction method for the emotional analysis of the mental state signals extracts feature vectors from mental state region data of a mental state change rule based on a public space mode, and specifically comprises the following steps: and if the category number of the emotional mental states is n, a one-to-one method is adopted to expand the two traditional public space modes aiming at the recognition problem of n categories of emotions.
The one-to-one common spatial mode algorithm comprises the following steps:
(1) with E i To represent mental state change regular emotional mental state region data, i refers to the i-th class (i ═ 1, 2.., n); matrix E i Is N x T, where N is the number of channels used to record the mental state signal, T is the number of regional points collected on each channel,the constraint condition N is less than or equal to T; respectively calculating a normalized covariance matrix, and recording as R i :
Wherein trace (X) represents the trace of the diagonal matrix X;
then, averaging the normalized covariance matrix of all the area data of each type as the average normalized spatial covariance matrix of the data of that typeThen the mixed spatial covariance matrix R of any two types of region data is:
(2) firstly, performing principal component decomposition on R:
R=UVU T ;
v is an eigenvalue diagonal matrix, and U is an eigenvector matrix formed by eigenvectors corresponding to the eigenvalues in V;
then sorting the eigenvalues in a descending order, and correspondingly adjusting the arrangement order of the eigenvectors to obtain new V and U; the whitening matrix P is defined as:
then to S 1 And S 2 Performing principal component decomposition:
to S 1 And S 2 The two eigenvector matrices obtained by principal component decomposition are equal, i.e. U 1 =U 2 B; the sum of two eigenvalue diagonal matrices is an identity matrix, i.e. V 1 +V 2 =I;
Will V 1 The eigenvalues in descending order of (1) then (V) 2 The eigenvalues in (1) are in ascending order; defining the projection matrix W as:
W=B T P;
calculating a projection matrix W for any two types of region data j (j ═ 1, 2.,. n (n-1)/2), and all the obtained projection matrixes are longitudinally spliced to construct an n-class spatial filter SF;
(4) for each area data E i Filtering using SF:
Z i =SFE i ;i=1,2,...n;
z obtained i A mode feature matrix representing a single area, wherein one row represents the feature distribution on one channel; taking the variance of each channel feature vector as the extracted psychological state signal feature, and then carrying out logarithm operation on the feature value, wherein the feature vector is shown as the following formula:
f i =log(var(Z i ));i=1,2,...n。
further, the construction method of the psychological knowledge map comprises the following steps:
(1) collecting data related to the condition of a patient's psychological disease; analyzing the collected data and establishing a mental disease corpus; determining an entity, a relation and an attribute indication word list according to the mental disease corpus;
(2) fine-tuning data in the mental disease corpus set by using a language model, constructing a mental disease named entity identification data set, extracting characteristic values of the named entity identification data set, fusing the fine-tuned data and the extracted characteristics, and training a pre-constructed deep learning model by using the fused data;
(3) and predicting the psychological disease corpus to be processed by using the trained deep learning model, converting the entity category index sequence obtained by prediction into an entity type sequence, storing each entity word into an entity word list, and respectively extracting entity relationship and attribute data according to the relationship type and the attribute type to respectively store the entity relationship and the attribute data.
Further, the specific process of acquiring existing information related to the psychological disease and establishing the psychological disease corpus includes: setting a mental disease term seed word set according to the book related to the mental disease; according to the mental disease term seed set, traversing and searching related contents in the medical website, recording related webpage url, and storing as a url set; crawling the webpage content of the url set by using a crawler technology; extracting contents of the crawled webpage contents by adopting a regular expression and an xpath analyzer, storing unstructured data into a database, directly extracting triples for storing semi-structured data, and distinguishing and storing different relation types and different attribute types; and labeling at least one part of the processed corpus.
Further, the method for evaluating the user psychological state comprises the following steps:
1) acquiring all internet surfing behaviors of the network user, and respectively setting corresponding nodes for each type of internet surfing behavior; connecting two nodes corresponding to two adjacent internet surfing behaviors triggered by a network user through edges, and setting a weight value for the edge between the two nodes according to the total number of interaction times between the two adjacent internet surfing behaviors; establishing an individual internet behavior network corresponding to a network user based on each node and edges with weighted values among the nodes, and acquiring individual network behavior characteristics;
2) establishing and training a mental state evaluation model based on the network behavior characteristics by using a machine learning method based on the network behavior characteristics and the demographic characteristics of individuals in the known area;
3) acquiring network behavior characteristics and demographic characteristics of a new individual, and obtaining the psychological condition of the new individual according to the psychological state evaluation model based on the network behavior characteristics;
wherein: the network behavior characteristics are a characteristic set reflecting the function result and the use path of the network media/service tool used by the individual; the network behavior characteristics are extracted from the network logs of the recording individuals; and the network behavior feature comprises network information and time series data of an individual, the network information of the individual comprising: time information, various instant messaging tool information, mail information, information of the category of the accessed webpage and search information; the time-series data includes: the method comprises the steps of obtaining daily internet surfing time information, daily network request number information and daily webpage information; the time information includes: average daily internet surfing time of working days and average daily internet surfing time of weekends; the mail information includes whether to send and receive mails with the client.
The invention also aims to provide a psychology knowledge-based machine artificial intelligence learning system for implementing the psychology knowledge-based machine artificial intelligence learning method.
It is a further object of the invention to provide a computer arrangement comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the method steps of imparting artificial intelligence learning to a machine based on psychological knowledge.
It is a further object of the invention to provide a computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, causes the processor to carry out the method for imparting artificial intelligence learning to a machine based on psychological knowledge.
The invention also aims to provide an information data processing terminal which is used for realizing the method for giving artificial intelligence learning to the machine based on the psychological knowledge.
The invention has the advantages and positive effects that: the invention enables massive psychological disease data to be effectively managed and utilized by a psychological knowledge map construction method, and can develop a plurality of applications such as knowledge search, intelligent question answering and the like on the basis of the knowledge map; aiming at a deep learning model which lacks a large amount of labeled data training, the invention uses the ALBERT language model to pre-train the linguistic data of the psychological diseases, brings rich semantic information for the deep learning model, and can effectively improve the accuracy of entity recognition; meanwhile, the method for evaluating the psychological state of the user eliminates the influence of individual subjective factors on data collection, and is beneficial to more accurately evaluating the psychological health state.
The mental state analysis model comprises: decomposing the psychological state signal in a time-frequency domain by utilizing wavelet packet transformation, and extracting a psychological state change rule of a psychological state wave; adopting a one-to-one strategy to expand the public space mode from two types of modes to a plurality of types of modes, and extracting feature vectors for the psychological state of the change rule of the psychological state by utilizing the one-to-one public space mode; selecting the dimension of the feature vector according to the distribution characteristics of the feature values; accurate data can be obtained.
Drawings
FIG. 1 is a flow chart of a method for imparting artificial intelligence learning to a machine based on psychological knowledge, provided by an implementation of the present invention.
FIG. 2 is a flow chart of a method for constructing a psychological knowledge-graph according to the present invention.
Fig. 3 is a flowchart of a method for evaluating a user's mental state according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The application of the principles of the present invention will now be further described with reference to the accompanying drawings.
As shown in FIG. 1, the invention provides a method for giving artificial intelligence learning to a machine based on psychological knowledge, which comprises the following steps:
s101, acquiring basic information, emotion information and position information of a monitored object; wherein the basic information at least comprises the name and the head portrait picture of the monitored object;
s102, matching corresponding scene correlation events by taking the position information as a basis; analyzing the basic information, the emotion information, the position information and the scene correlation event by using a preset psychological state analysis model to obtain the psychological state of the monitored object; establishing a psychological state document library;
s103, carrying out word segmentation and intelligent abstract preprocessing on the documents in the physiological state document library to obtain keywords, carrying out correlation analysis on the obtained keywords, processing the values provided in the steps, calculating the criticality value of the keywords aiming at the documents, and obtaining the keywords with assignment;
s104, analyzing the user character according to the psychological knowledge map to obtain a user character tendency value, and evaluating the psychological state of the user;
s105, matching the obtained character tendency value with the obtained key degree value of the keyword to obtain a document library with character tendency attributes; when a user initiates an access request, the document library with the personality tendency attribute gives out the document with the personality tendency attribute.
In step S102, the mental state analysis model includes:
decomposing a psychological state signal in a time-frequency domain by utilizing wavelet packet transformation, and extracting a psychological state change rule of a psychological state wave;
secondly, expanding the public space mode from two types of modes to a plurality of types of modes by adopting a one-to-one strategy, and extracting feature vectors for the psychological state of the change rule of the psychological state by utilizing the one-to-one public space mode;
thirdly, selecting the dimension of the characteristic vector according to the distribution characteristics of the characteristic values;
the improved public spatial mode feature extraction method for analyzing the emotional state signals extracts the psychological state of the psychological state change rule from the original psychological state signals, and comprises the following steps: decomposing the psychological state signal in a time-frequency domain by adopting wavelet packet transformation, and performing combined reconstruction on node coefficients of a plurality of sub-bands corresponding to the psychological state change frequency band so as to extract a psychological state change rule psychological state signal consistent with the original psychological state signal form;
the improved public space mode feature extraction method for the emotional analysis of the mental state signals extracts feature vectors from mental state region data of a mental state change rule based on a public space mode, and specifically comprises the following steps: and if the category number of the emotional mental states is n, a one-to-one method is adopted to expand the two traditional public space modes aiming at the recognition problem of n categories of emotions.
The one-to-one common spatial mode algorithm comprises the following steps:
(1) with E i To represent mental state change regular emotional mental state region data, i refers to the i-th class (i ═ 1, 2.., n); matrix E i The size of the channel is N x T, wherein N is the number of channels used for recording the psychological state signals, T is the number of region points collected on each channel, and the constraint condition N is less than or equal to T; respectively calculating a normalized covariance matrix, and recording as R i :
Wherein trace (X) represents the trace of the diagonal matrix X;
then, averaging the normalized covariance matrix of all the area data of each type as the average normalized spatial covariance matrix of the data of that typeThen the mixed spatial covariance matrix R of any two types of region data is:
(2) firstly, performing principal component decomposition on R:
R=UVU T ;
v is an eigenvalue diagonal matrix, and U is an eigenvector matrix formed by eigenvectors corresponding to the eigenvalues in V;
then sorting the eigenvalues in a descending order, and correspondingly adjusting the arrangement order of the eigenvectors to obtain new V and U; the whitening matrix P is defined as:
then to S 1 And S 2 Performing principal component decomposition:
to S 1 And S 2 The two eigenvector matrices obtained by principal component decomposition are equal, i.e. U 1 =U 2 B; the sum of two eigenvalue diagonal matrices is an identity matrix, i.e. V 1 +V 2 =I;
Will V 1 The eigenvalues in descending order of (1) then (V) 2 The eigenvalues in (1) are in ascending order; defining the projection matrix W as:
W=B T P;
calculating a projection matrix W for any two types of region data j (j ═ 1, 2.,. n (n-1)/2), and all the obtained projection matrixes are longitudinally spliced to construct an n-class spatial filter SF;
(4) for each area data E i Filtering using SF:
Z i =SFE i ;i=1,2,...n;
z obtained i A mode feature matrix representing a single area, wherein one row represents the feature distribution on one channel; taking the variance of each channel feature vector as the extracted psychological state signal feature, and then carrying out logarithm operation on the feature value, wherein the feature vector is shown as the following formula:
f i =log(var(Z i ));i=1,2,...n。
as shown in fig. 2, the method for constructing the psychological knowledge-graph provided by the invention comprises the following steps:
s201, collecting data related to the state of a patient' S mental disease; analyzing the acquired data and establishing a mental disease corpus; determining an entity, a relation and an attribute indication word list according to the mental disease corpus;
s202, fine tuning data in the mental disease corpus by using a language model, constructing a mental disease named entity recognition data set, extracting characteristic values of the named entity recognition data set, fusing the fine tuned data and the extracted characteristics, and training a pre-constructed deep learning model by using the fused data;
s203, predicting the psychological disease corpus to be processed by using the trained deep learning model, converting the entity category index sequence obtained by prediction into an entity type sequence, storing each entity word into an entity word list, and respectively extracting entity relationship and attribute data according to the relationship type and the attribute type for respectively storing.
The specific process for acquiring the existing information related to the psychological diseases and establishing the psychological disease corpus provided by the invention comprises the following steps: setting a mental disease term seed word set according to the book related to the mental disease; according to the mental disease term seed set, traversing and searching related contents in the medical website, recording related webpage url, and storing as a url set; crawling the webpage content of the url set by using a crawler technology; extracting contents of the crawled webpage contents by adopting a regular expression and an xpath analyzer, storing unstructured data into a database, directly extracting triples for storing semi-structured data, and distinguishing and storing different relation types and different attribute types; and labeling at least one part of the processed corpus.
As shown in fig. 3, the method for evaluating the psychological state of the user according to the present invention comprises the following steps:
s301, acquiring all internet surfing behaviors of a network user, and respectively setting corresponding nodes for each type of internet surfing behaviors; connecting two nodes corresponding to two adjacent internet surfing behaviors triggered by a network user through edges, and setting a weight value for the edge between the two nodes according to the total number of interaction times between the two adjacent internet surfing behaviors; establishing an individual internet behavior network corresponding to a network user based on each node and edges with weighted values among the nodes, and acquiring individual network behavior characteristics;
s302, establishing and training a mental state evaluation model based on network behavior characteristics based on individual network behavior characteristics and demographic characteristics in a known region by using a machine learning method;
s303, acquiring network behavior characteristics and demographic characteristics of the new individual, and obtaining the psychological condition of the new individual according to the psychological state evaluation model based on the network behavior characteristics;
wherein: the network behavior characteristics are a characteristic set reflecting the function result and the use path of the network media/service tool used by the individual; the network behavior characteristics are extracted from the network logs of the recording individuals; and the network behavior feature comprises network information and time series data of an individual, the network information of the individual comprising: time information, various instant messaging tool information, mail information, information of the category of the accessed webpage and search information; the time-series data includes: the method comprises the steps of obtaining daily internet surfing time information, daily network request number information and daily webpage information; the time information includes: average daily internet surfing time of working days and average daily internet surfing time of weekends; the mail information includes whether to send and receive mails with the client.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for endowing a machine with artificial intelligence learning based on psychological knowledge is characterized by comprising the following steps:
acquiring basic information, emotion information and position information of a monitored object; wherein the basic information at least comprises the name and the head portrait picture of the monitored object;
matching corresponding scene correlation events by taking the position information as a basis; analyzing the basic information, the emotion information, the position information and the scene correlation event by using a preset psychological state analysis model to obtain the psychological state of the monitored object; establishing a psychological state document library;
performing word segmentation and intelligent abstract preprocessing on the documents in the physiological state document library to obtain keywords, performing relevance analysis on the obtained keywords, processing the values provided in the step, calculating the criticality value of the keywords aiming at the documents, and obtaining the keywords with assignments;
analyzing the user character according to the psychological knowledge map to obtain a user character tendency value, and evaluating the psychological state of the user;
matching the obtained personality tendency value with the obtained keyword key degree value to obtain a document library with personality tendency attributes; when a user initiates an access request, the document library with the personality tendency attribute gives out the document with the personality tendency attribute.
2. The method for imparting robotic intelligence learning based on psychological knowledge according to claim 1, wherein in step two, the mental state analysis model comprises:
decomposing a psychological state signal in a time-frequency domain by utilizing wavelet packet transformation, and extracting a psychological state change rule of a psychological state wave;
secondly, expanding the public space mode from two types of modes to a plurality of types of modes by adopting a one-to-one strategy, and extracting feature vectors for the psychological state of the change rule of the psychological state by utilizing the one-to-one public space mode;
thirdly, selecting the dimension of the characteristic vector according to the distribution characteristics of the characteristic values;
the improved public spatial mode feature extraction method for analyzing the emotional state signals extracts the psychological state of the psychological state change rule from the original psychological state signals, and comprises the following steps: decomposing the psychological state signal in a time-frequency domain by adopting wavelet packet transformation, and performing combined reconstruction on node coefficients of a plurality of sub-bands corresponding to the psychological state change frequency band so as to extract a psychological state change rule psychological state signal consistent with the original psychological state signal form;
the improved public space mode feature extraction method for the emotional analysis of the mental state signals extracts feature vectors from mental state region data of a mental state change rule based on a public space mode, and specifically comprises the following steps: and if the category number of the emotional mental states is n, a one-to-one method is adopted to expand the two traditional public space modes aiming at the recognition problem of n categories of emotions.
3. The method for imparting robotic artificial intelligence learning based on psychological knowledge as claimed in claim 2, wherein the one-to-one common spatial pattern algorithm steps are:
(1) with E i To represent mental state change regular emotional mental state region data, i refers to the i-th class (i ═ 1, 2.., n); matrix E i The size of the channel is N x T, wherein N is the number of channels used for recording the psychological state signals, T is the number of region points collected on each channel, and the constraint condition N is less than or equal to T; respectively calculating a normalized covariance matrix, which is recorded as R, for each region data i :
Wherein trace (X) represents the trace of the diagonal matrix X;
then, averaging the normalized covariance matrix of all the area data of each type as the average normalized spatial covariance matrix of the data of that typeThen the mixed spatial covariance matrix R of any two types of region data is:
(2) firstly, performing principal component decomposition on R:
R=UVU T ;
v is an eigenvalue diagonal matrix, and U is an eigenvector matrix formed by eigenvectors corresponding to the eigenvalues in V;
then sorting the eigenvalues in a descending order, and correspondingly adjusting the arrangement order of the eigenvectors to obtain new V and U; the whitening matrix P is defined as:
then to S 1 And S 2 Performing principal component decomposition:
to S 1 And S 2 The two eigenvector matrices obtained by principal component decomposition are equal, i.e. U 1 =U 2 B; the sum of two eigenvalue diagonal matrices is an identity matrix, i.e. V 1 +V 2 =I;
Will V 1 The eigenvalues in descending order of (1) then (V) 2 The eigenvalues in (1) are in ascending order; defining the projection matrix W as:
W=B T P;
calculating a projection matrix W for any two types of region data j (j ═ 1, 2.,. n (n-1)/2), and all the obtained projection matrixes are longitudinally spliced to construct an n-class spatial filter SF;
(4) for each area data E i Filtering using SF:
Z i =SFE i ;i=1,2,...n;
z obtained i A mode feature matrix representing a single area, wherein one row represents the feature distribution on one channel; taking the variance of each channel feature vector as the extracted psychological state signal feature, and then carrying out logarithm operation on the feature value, wherein the feature vector is shown as the following formula:
f i =log(var(Z i ));i=1,2,...n。
4. the method for imparting artificial intelligence learning to a machine based on psychological knowledge according to claim 1, wherein in step four, the psychological knowledge map is constructed by the following method:
(1) collecting data related to the condition of a patient's psychological disease; analyzing the acquired data and establishing a mental disease corpus; determining an entity, a relation and an attribute indication word list according to the mental disease corpus;
(2) fine-tuning data in the mental disease corpus set by using a language model, constructing a mental disease named entity identification data set, extracting characteristic values of the named entity identification data set, fusing the fine-tuned data and the extracted characteristics, and training a pre-constructed deep learning model by using the fused data;
(3) and predicting the psychological disease corpus to be processed by using the trained deep learning model, converting the entity category index sequence obtained by prediction into an entity type sequence, storing each entity word into an entity word list, and respectively extracting entity relationship and attribute data according to the relationship type and the attribute type to respectively store the entity relationship and the attribute data.
5. The method for imparting machine-aided intelligent learning based on psychological knowledge according to claim 4, wherein the specific process of obtaining the existing information related to the psychological disease and establishing the corpus comprises: setting a mental disease term seed word set according to the book related to the mental disease; according to the mental disease term seed set, traversing and searching related contents in the medical website, recording related webpage url, and storing as a url set; crawling the webpage content of the url set by using a crawler technology; extracting contents of the crawled webpage contents by adopting a regular expression and an xpath analyzer, storing unstructured data into a database, directly extracting triples for storing semi-structured data, and distinguishing and storing different relation types and different attribute types; and labeling at least one part of the processed corpus.
6. The method for imparting robotic intelligence learning based on psychological knowledge according to claim 1, wherein in step four, the method for assessing the user's mental state is as follows:
1) acquiring all internet surfing behaviors of the network user, and respectively setting corresponding nodes for each type of internet surfing behavior; connecting two nodes corresponding to two adjacent internet surfing behaviors triggered by a network user through edges, and setting a weight value for the edge between the two nodes according to the total number of interaction times between the two adjacent internet surfing behaviors; establishing an individual internet behavior network corresponding to a network user based on each node and edges with weighted values among the nodes, and acquiring individual network behavior characteristics;
2) establishing and training a mental state evaluation model based on the network behavior characteristics by using a machine learning method based on the individual network behavior characteristics and the demographic characteristics in the known region;
3) acquiring network behavior characteristics and demographic characteristics of a new individual, and obtaining the psychological condition of the new individual according to the psychological state evaluation model based on the network behavior characteristics;
wherein: the network behavior characteristics are a characteristic set reflecting the function result and the use path of the network media/service tool used by the individual; the network behavior characteristics are extracted from the network logs of the recording individuals; and the network behavior feature comprises network information and time series data of an individual, the network information of the individual comprising: time information, various instant messaging tool information, mail information, information of the category of the accessed webpage and search information; the time-series data includes: the method comprises the steps of obtaining daily internet surfing time information, daily network request number information and daily webpage information; the time information includes: average daily internet surfing time of working days and average daily internet surfing time of weekends; the mail information includes whether to send and receive mails with the client.
7. A psychology knowledge imparting robotic artificial intelligence learning system implementing the psychology knowledge imparting robotic artificial intelligence learning method of any one of claims 1-6.
8. A computer arrangement, characterized in that the computer arrangement comprises a memory and a processor, the memory storing a computer program which, when executed by the processor, causes the processor to carry out the method steps of assigning a machine artificial intelligence learning based on psychological knowledge as claimed in any one of claims 1 to 6.
9. A computer-readable storage medium, storing a computer program which, when executed by a processor, causes the processor to carry out the method for imparting artificial intelligence learning to a machine based on psychological knowledge as claimed in any one of claims 1 to 6.
10. An information data processing terminal, characterized in that the information data processing terminal is used for realizing the method for giving artificial intelligence learning to a machine based on psychological knowledge as claimed in any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210652233.4A CN114969375A (en) | 2022-06-10 | 2022-06-10 | Method and system for giving artificial intelligence learning to machine based on psychological knowledge |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210652233.4A CN114969375A (en) | 2022-06-10 | 2022-06-10 | Method and system for giving artificial intelligence learning to machine based on psychological knowledge |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114969375A true CN114969375A (en) | 2022-08-30 |
Family
ID=82961634
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210652233.4A Pending CN114969375A (en) | 2022-06-10 | 2022-06-10 | Method and system for giving artificial intelligence learning to machine based on psychological knowledge |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114969375A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116821287A (en) * | 2023-08-28 | 2023-09-29 | 湖南创星科技股份有限公司 | Knowledge graph and large language model-based user psychological portrait system and method |
-
2022
- 2022-06-10 CN CN202210652233.4A patent/CN114969375A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116821287A (en) * | 2023-08-28 | 2023-09-29 | 湖南创星科技股份有限公司 | Knowledge graph and large language model-based user psychological portrait system and method |
CN116821287B (en) * | 2023-08-28 | 2023-11-17 | 湖南创星科技股份有限公司 | Knowledge graph and large language model-based user psychological portrait system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102288249B1 (en) | Information processing method, terminal, and computer storage medium | |
US8805843B2 (en) | Information mining using domain specific conceptual structures | |
CN111949758A (en) | Medical question and answer recommendation method, recommendation system and computer readable storage medium | |
CN111538894A (en) | Query feedback method and device, computer equipment and storage medium | |
KR101976081B1 (en) | Method, system and computer program for semantic image retrieval based on topic modeling | |
CN117271767B (en) | Operation and maintenance knowledge base establishing method based on multiple intelligent agents | |
KR20200145299A (en) | Intelligent recruitment support platform based on online interview video analysis and social media information analysis | |
CN112669113A (en) | Product recommendation method and device, storage medium and electronic device | |
CN113468291A (en) | Patent network representation learning-based automatic patent classification method | |
CN117668205B (en) | Smart logistics customer service processing method, system, equipment and storage medium | |
CN117520522B (en) | Intelligent dialogue method and device based on combination of RPA and AI and electronic equipment | |
CN111696656A (en) | Doctor evaluation method and device of Internet medical platform | |
CN114969375A (en) | Method and system for giving artificial intelligence learning to machine based on psychological knowledge | |
Raftopoulos et al. | Mining user queries with Markov chains: Application to online image retrieval | |
KR102096328B1 (en) | Platform for providing high value-added intelligent research information based on prescriptive analysis and a method thereof | |
CN111783473A (en) | Method and device for identifying best answer in medical question and answer and computer equipment | |
CN114003706A (en) | Keyword combination generation model training method and device | |
CN114090869A (en) | Target object processing method and device, electronic equipment and storage medium | |
Chen | Tracking latent domain structures: An integration of Pathfinder and Latent Semantic Analysis | |
Al Hasan et al. | Clustering Analysis of Bangla News Articles with TF-IDF & CV Using Mini-Batch K-Means and K-Means | |
CN110633363A (en) | Text entity recommendation method based on NLP and fuzzy multi-criterion decision | |
CN117370678B (en) | Community public opinion monitoring method and related device based on big data | |
Şentürk | Ontology for data analytics | |
CN112948544B (en) | Book retrieval method based on deep learning and quality influence | |
CN118193855B (en) | Online response method and device and computer equipment |
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 |