CN113571184A - Dialogue interaction design method and system for mental health assessment - Google Patents
Dialogue interaction design method and system for mental health assessment Download PDFInfo
- Publication number
- CN113571184A CN113571184A CN202110818801.9A CN202110818801A CN113571184A CN 113571184 A CN113571184 A CN 113571184A CN 202110818801 A CN202110818801 A CN 202110818801A CN 113571184 A CN113571184 A CN 113571184A
- Authority
- CN
- China
- Prior art keywords
- user
- mental
- health
- mental health
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004630 mental health Effects 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000013461 design Methods 0.000 title claims abstract description 29
- 230000003993 interaction Effects 0.000 title claims abstract description 28
- 230000003340 mental effect Effects 0.000 claims abstract description 54
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000012216 screening Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 13
- 201000010099 disease Diseases 0.000 claims description 33
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 33
- 238000001514 detection method Methods 0.000 claims description 27
- 230000008451 emotion Effects 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 23
- 208000024891 symptom Diseases 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 12
- 238000004140 cleaning Methods 0.000 claims description 7
- 230000014509 gene expression Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 229940079593 drug Drugs 0.000 claims description 6
- 239000003814 drug Substances 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000006996 mental state Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000006872 improvement Effects 0.000 description 11
- 238000011156 evaluation Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 230000036541 health Effects 0.000 description 6
- 230000002787 reinforcement Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 206010003805 Autism Diseases 0.000 description 2
- 208000020706 Autistic disease Diseases 0.000 description 2
- 206010026749 Mania Diseases 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- 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
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- 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
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Child & Adolescent Psychology (AREA)
- Social Psychology (AREA)
- Developmental Disabilities (AREA)
- Psychology (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Hospice & Palliative Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a dialogue interaction design method and a dialogue interaction design system for mental health assessment, wherein the method comprises the following steps of: s1, collecting the user conversation by using the terminal part of the smart phone, screening the user information, and uploading the screened user information to a cloud platform; s2, receiving information data of the user on the cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map; and S3, processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user. Has the advantages that: a knowledge extraction model combining a conditional random field model and rule extraction is designed, and extracted key information is subjected to entity unification and then is put into a warehouse together with diagnostic standard data, so that the mental health assessment map is constructed in a map database, and an auxiliary diagnostic result and a visual assessment map are given.
Description
Technical Field
The invention relates to the technical field of mental health assessment dialogue interaction systems of knowledge graphs, in particular to a dialogue interaction design method and system for mental health assessment.
Background
With the acceleration of urban life rhythm, the physical health of people is gradually not guaranteed, wherein the mental sub-health of people is more and more, partial sub-health people are not willing to receive evaluation due to the privacy of patients, the number of professional medical staff is limited, and the evaluation of all sub-health people cannot be met if evaluation is carried out only by manpower, so that comprehensive work is difficult to be carried out on the mental health evaluation face of the sub-health people, and the work faces huge challenges.
However, with the development of computer technology and artificial intelligence technology, some text analysis algorithms are used for disease assessment, and currently, the algorithms have achieved results in some disease assessment directions;
1. the automatic disease coding method based on text analysis comprises the following steps: the disease is coded, namely, the disease evaluation is converted into standard ICD (international disease classification) codes, the codes are an automatic disease coding method, the ICD codes most relevant to the disease evaluation name to be coded can be obtained by means of text relevant measurement, and the method has the advantages of high accuracy, excellent efficiency and flexible classification level conversion, and can be widely used in various data analysis scenes;
2. clinical assessment based on textual electronic medical records: in addition, according to the image technology, a natural language processing technology is utilized to carry out clinical intelligent assessment technology based on a text type electronic medical record, the technology can be equivalent to a primary health care pediatrician in terms of accuracy, and the artificial intelligent program can accurately detect test results, health records or even handwritten notes like the doctor, so that the children disease is assessed, a large number of mental and sub-health cases need to be collected, and the collection scheme is difficult to realize due to privacy problems;
3. text and deep learning based depression recognition scheme: the method constructs a depression field dictionary base, comprehensively analyzes common characteristics of depression microwave feelings and behaviors, synthesizes a knowledge base and a corpus, constructs the depression field dictionary base by adopting two semantic similarity algorithms, comprehensively analyzes common characteristics of depression feelings and behaviors, and compensates dictionary vacancy in the field, and aims at microblog characteristics, so that the accuracy is not high;
in addition, traditional mental health solutions rely primarily on active hospitalization of sub-mental health, but do not wish to expose identity information for the majority of patients, and resist direct contact with the physician, therefore, there is a need for a dialogue system that can provide evaluation services to patients in an anonymous situation, and knowledge-graph technology has achieved great theoretical results through research and study in recent years, and has practical application in many fields such as search engine and intelligent question-answering system, but at present, the Chinese knowledge atlas database in the vertical industry is still lacked, particularly, more refined division is performed in various industries, such as mental health knowledge maps in the medical field, most of related researches of two-map construction focus on extraction and representation of English knowledge, and the large difference of Chinese and English grammar causes that theoretical results are difficult to migrate to the field of Chinese knowledge maps.
An effective solution to the problems in the related art has not been proposed yet.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a dialogue interaction design method and system for mental health assessment, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
according to an aspect of the present invention, there is provided a dialogue interaction design method for mental health assessment, the method comprising the steps of:
s1, collecting the user conversation by using the terminal part of the smart phone, screening the user information, and uploading the screened user information to a cloud platform;
s2, receiving information data of the user on the cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map;
and S3, processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user.
Further, the method for collecting the user conversation by using the terminal part of the smart phone, screening the user information, and uploading the screened user information to the cloud platform further comprises the following steps:
s11, receiving information data of a user of the smart phone terminal by using the smart phone terminal, and transmitting the information data of the user to an emotion detection platform of the cloud platform;
s12, analyzing the user data and judging the mental health condition of the user;
and S13, transmitting the detection result of the mental state of the user to the smart phone terminal.
Furthermore, the intelligent mobile phone terminal comprises a user conversation stage, an information collection stage and an information preliminary screening stage.
Further, the analyzing the user data and determining the mental health status of the user further comprises the following steps:
s121, if no sensitive vocabulary appears in the user conversation, the mental health of the user is proved, and the mental health result is directly fed back to the user;
and S122, if the sensitive words appear in the user conversation, uploading the user information to an emotion detection platform, and processing the user information on the emotion detection platform.
Further, the step of receiving the information data of the user at the cloud platform and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge graph further comprises the following steps:
s21, obtaining a probability chart of various symptoms of the user through a section of self description of the user and a disease judgment function based on text analysis, and judging whether the user has mental sub-health problems or not according to the probability chart;
s22, providing disease analysis and guidance suggestions for the mental sub-health users from the prepared conversation set through a section of self description of the mental sub-health users, text similarity matching and answer selection based on the question and answer conversation set;
s23, a question-answer dialogue platform is provided for mental sub-health users by constructing knowledge maps of diseases, symptoms and medicines.
Further, the construction of the knowledge graph further comprises the following steps:
collecting spoken text expressions of a large number of mental sub-health people by using a web crawler, and completing data cleaning to obtain a constructed dictionary;
completing data annotation by utilizing a dictionary Chinese word segmentation and keyword extraction technology;
adopting machine data marking to match with manual screening to obtain training data marking;
selecting an appropriate sequence data annotation, training named entity recognition for depression assessment;
combining named entity recognition with dictionary-based extraction to obtain complete knowledge extraction;
and (4) unifying the entities to construct a knowledge graph for mental health assessment.
Further, the processing the mental health condition of the mental sub-health user on the cloud computing platform and transmitting the analysis result to the mental sub-health user further comprises the following steps:
s31, receiving user information collected by the smart phone terminal, and transmitting the information to the data analysis and calculation module;
s32, storing the knowledge graph constructed by the emotion detection platform in a cache library;
and S33, analyzing the mental health condition of the user at the emotion detection platform, and transmitting the analysis result to the user.
According to another aspect of the present invention, there is provided a dialogue interaction design system for mental health assessment, the system comprising:
terminal part of the smart phone: collecting user conversations by using a terminal part of the smart phone, screening user information, and uploading the screened user information to a cloud platform;
the emotion detection platform part: receiving information data of a user at a cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map;
the cloud computing platform part: and processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user.
Further, the step of receiving the information data of the user at the cloud platform and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge graph further comprises the following steps:
obtaining a probability chart of various symptoms suffered by the user through a section of self description of the user and a disease judgment function based on text analysis, and judging whether the user has a mental sub-health problem according to the probability chart;
providing disease analysis and guidance suggestions for the mental sub-health users from the prepared conversation set through a section of self description of the mental sub-health users, text similarity matching and answer selection based on a question and answer conversation set;
by constructing knowledge maps of diseases, symptoms and medicines, a question-answer dialogue platform is provided for mental sub-health users.
Further, the construction of the knowledge graph further comprises the following steps:
collecting spoken text expressions of a large number of mental sub-health people by using a web crawler, and completing data cleaning to obtain a constructed dictionary;
completing data annotation by utilizing a dictionary Chinese word segmentation and keyword extraction technology;
adopting machine data marking to match with manual screening to obtain training data marking;
selecting an appropriate sequence data annotation, training named entity recognition for depression assessment;
combining named entity recognition with dictionary-based extraction to obtain complete knowledge extraction;
and (4) unifying the entities to construct a knowledge graph for mental health assessment.
The invention has the beneficial effects that:
1. the invention provides a method for constructing and utilizing mental health knowledge maps to carry out conversation, and designs a knowledge extraction model which combines a conditional random field model with rule extraction, and puts extracted key information into storage together with diagnostic standard data after entity unification, thereby completing the construction of the mental health assessment maps in a map database, and giving auxiliary diagnostic results and visual assessment maps.
2. The knowledge graph is a Chinese knowledge graph in the professional field, has mobility in the intelligent medical field, has certain universality, is only suitable for mental health assessment at present, but can be used for designing an auxiliary assessment scheme suitable for autism, mania and other mental health diseases subsequently by referring to the system construction scheme.
3. The mental health improvement scheme combining deep reinforcement learning and the knowledge graph can be updated and optimized at any time according to the condition of the user.
4. The invention can make the user converse on the network in an anonymous form, namely, the user describes himself to obtain the self description of the user through the user's self description, and then the collected information is used as the input of text analysis, thus solving the problem that the user does not want to contact doctors and expose personal information.
5. The emotion detection platform can be placed in the cache library by the cloud computing platform part, so that the energy consumption of the smart phone terminal is reduced, meanwhile, the delay caused by computing can be reduced by the strong computing capacity of the cloud platform, and the user experience degree is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow diagram of a dialog interaction design method for mental health assessment, according to an embodiment of the present invention;
FIG. 2 is a functional block diagram of a conversational interaction design system for mental health assessment, according to an embodiment of the invention;
FIG. 3 is a block diagram of a dialog interaction system for mental health assessment in a dialog interaction design system for mental health assessment, according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating the establishment of mental health assessment knowledge graph in a dialogue interaction design method for mental health assessment according to an embodiment of the invention;
fig. 5 is a training improvement scheme framework based on deep reinforcement learning and knowledge maps in a dialogue interaction design method for mental health assessment according to an embodiment of the invention.
In the figure:
1. a terminal part of the smart phone; 2. an emotion detection platform part; 3. and a cloud computing platform part.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to an embodiment of the present invention, a dialog interaction design method for mental health assessment is provided.
Referring now to the drawings and the detailed description, the present invention will be further explained, as shown in fig. 1, in accordance with an embodiment of the present invention, a dialogue interaction design method for mental health assessment, the method comprising the steps of:
s1, collecting the user conversation by using the terminal part of the smart phone, screening the user information, and uploading the screened user information to a cloud platform;
in one embodiment, the collecting the user's conversation by using the terminal portion of the smart phone, screening the user's information, and uploading the screened user's information to the cloud platform further includes the following steps:
s11, receiving information data of a user of the smart phone terminal by using the smart phone terminal, and transmitting the information data of the user to an emotion detection platform of the cloud platform;
s12, analyzing the user data and judging the mental health condition of the user;
and S13, transmitting the detection result of the mental state of the user to the smart phone terminal.
In one embodiment, the smartphone terminal includes user dialog, information gathering and information prescreening stages;
in one embodiment, the analyzing the user data and determining the mental health condition of the user further comprises:
s121, if no sensitive vocabulary appears in the user conversation, the mental health of the user is proved, and the mental health result is directly fed back to the user;
and S122, if the sensitive words appear in the user conversation, uploading the user information to an emotion detection platform, and processing the user information on the emotion detection platform.
S2, receiving information data of the user on the cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map;
s21, obtaining a probability chart of various symptoms of the user through a section of self description of the user and a disease judgment function based on text analysis, and judging whether the user has mental sub-health problems or not according to the probability chart;
s22, providing disease analysis and guidance suggestions for the mental sub-health users from the prepared conversation set through a section of self description of the mental sub-health users, text similarity matching and answer selection based on the question and answer conversation set;
s23, a question-answer dialogue platform is provided for mental sub-health users by constructing knowledge maps of diseases, symptoms and medicines.
In one embodiment, the construction of the knowledge-graph further comprises the steps of:
collecting spoken text expressions of a large number of mental sub-health people by using a web crawler, and completing data cleaning to obtain a constructed dictionary;
completing data annotation by utilizing a dictionary Chinese word segmentation and keyword extraction technology;
adopting machine data marking to match with manual screening to obtain training data marking;
selecting an appropriate sequence data annotation, training named entity recognition for depression assessment;
combining named entity recognition with dictionary-based extraction to obtain complete knowledge extraction;
and (4) unifying the entities to construct a knowledge graph for mental health assessment.
In a specific application, as shown in fig. 4, this framework first processes the spoken descriptive text 201. Collecting spoken text expressions of a large number of mental sub-health persons through a web crawler, completing data cleaning 203, obtaining a constructed dictionary 204, completing data annotation 205 by utilizing the technologies of Chinese word segmentation, keyword extraction and the like by utilizing data, assisting manual screening by machine annotation data to obtain annotation data for training, selecting a proper sequence annotation model, training a named entity identification model 206 aiming at depression assessment, combining the named entity identification model 208 with an extraction model 207 based on a dictionary to obtain a complete knowledge extraction model, unifying 209 entities to complete the establishment of a mental health assessment knowledge map, establishing an assessment information map 211 according to the guidance and correction of a professional mental health diagnosis scale and professional doctors of Wuhan people hospital, utilizing key information in spoken description texts extracted by the knowledge extraction model as input data, and (5) referring to mental health diagnosis standards, and completing the design of a mental health evaluation module.
And S3, processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user.
In one embodiment, the processing mental health conditions of the mental sub-health users on the cloud computing platform and transmitting the analysis results to the mental sub-health users further comprises the following steps:
s31, receiving user information collected by the smart phone terminal, and transmitting the information to the data analysis and calculation module;
s32, storing the knowledge graph constructed by the emotion detection platform in a cache library;
and S33, analyzing the mental health condition of the user at the emotion detection platform, and transmitting the analysis result to the user.
In specific application, as shown in fig. 5, fig. 5 is a training improvement scheme framework based on deep reinforcement learning and knowledge graph, which is to collect the state 301 of user feedback, construct a training improvement scheme knowledge graph 302 by a similar mental health assessment knowledge graph construction method, then establish a related symptom dictionary 303, a related condition dictionary 304 of the user, a training improvement scheme dictionary 305 and the like according to the knowledge graph, use the related symptom dictionary and the related condition dictionary as state spaces, input a deep reinforcement learning model as action spaces for training 307 by using the training improvement scheme dictionary 305 as action spaces, and obtain the improvement scheme 306 required by the user in the time period.
According to another embodiment of the present invention, as shown in fig. 2, there is also provided a dialogue interaction design system for mental health assessment, the system including:
terminal part of the smart phone: collecting user conversations by using a terminal part of the smart phone, screening user information, and uploading the screened user information to a cloud platform;
the emotion detection platform part: receiving information data of a user at a cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map;
in a specific application, as shown in fig. 3, the smartphone terminal part 1 comprises a user dialog module 101, which allows the user to answer questions posed by the terminal and to upload his own symptoms. The information collection module 102 collects the information uploaded by the user and classifies the information of the user into symptom-type information, drug-type information, environment-type information, and the like. The information preliminary screening stage 103 is used for preliminarily screening the information of the user and detecting whether the symptom information of the user contains sensitive words related to mental sub-health. If no sensitive words exist, the result is directly fed back to the user. Otherwise, transmitting the information data of the user to the cloud platform; the cloud computing platform comprises a data receiving module 301, and the data receiving module receives information data of a smart phone terminal user and transmits the data to the emotion detection platform. The emotion detection platform is arranged in a data caching module 302 of the cloud computing platform, wherein the data analysis computing module 303 is arranged in the data caching module. And analyzing the user data in the data cache module to obtain the mental health condition of the user. And then transmitting the obtained mental health condition result of the user to a data transmission module 304 of the cloud computing platform. The data transmission platform transmits the data to the terminal, and the user obtains a mental health evaluation result; at the emotion detection platform, information data of a user is received at a data collection module 201. The mental health status of the user is judged 202 according to the data of the user and the constructed mental health knowledge graph, whether the mental health status of the user is normal or not is judged, and if the mental health status is normal, the mental health status is transmitted to the user. Otherwise, the health level is evaluated 203 based on the user question-answer dialog set, and the health level of the user is fed back to the terminal. The user then receives his or her mental health level and may proceed with a medical encyclopedia session 204, again based on the knowledge graph. In the medical encyclopedia dialogue system based on the knowledge graph, the user describes the symptoms of the user again in detail, and the system obtains corresponding measures for assisting in improving the mental health level. And is fed back to the user through the data transmission module 304. In addition, the user selectively uploads the disease condition according to the self disease condition according to the time node, selects the mental health improvement scheme and uses the disease condition after the training scheme of the improved disease condition. The next mental health improvement scheme is selected through a training selection model 501 module based on deep learning and knowledge map combination, and then is fed back to the user through a training and result feedback module 502.
The cloud computing platform part: and processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user.
In one embodiment, the receiving, at the cloud platform, the information data of the user and determining the mental health condition of the user according to the data of the user and the constructed mental health knowledge graph further includes the following steps:
obtaining a probability chart of various symptoms suffered by the user through a section of self description of the user and a disease judgment function based on text analysis, and judging whether the user has a mental sub-health problem according to the probability chart;
providing disease analysis and guidance suggestions for the mental sub-health users from the prepared conversation set through a section of self description of the mental sub-health users, text similarity matching and answer selection based on a question and answer conversation set;
by constructing knowledge maps of diseases, symptoms and medicines, a question-answer dialogue platform is provided for mental sub-health users.
In one embodiment, the construction of the knowledge-graph further comprises the steps of:
collecting spoken text expressions of a large number of mental sub-health people by using a web crawler, and completing data cleaning to obtain a constructed dictionary;
completing data annotation by utilizing a dictionary Chinese word segmentation and keyword extraction technology;
adopting machine data marking to match with manual screening to obtain training data marking;
selecting an appropriate sequence data annotation, training named entity recognition for depression assessment;
combining named entity recognition with dictionary-based extraction to obtain complete knowledge extraction;
and (4) unifying the entities to construct a knowledge graph for mental health assessment.
In summary, with the aid of the technical scheme, the invention provides a method for constructing and utilizing a mental health knowledge map for carrying out dialogue, designs a knowledge extraction model combining a conditional random field model and rule extraction, and stores extracted key information together with diagnostic standard data after entity unification, so that construction of the mental health assessment map is completed in a map database, and an auxiliary diagnostic result and a visual assessment map are given; the knowledge graph is a Chinese knowledge graph in the professional field, has mobility in the intelligent medical field, has certain universality, is only suitable for mental health assessment at present, but can be used for designing an auxiliary assessment scheme suitable for autism, mania and other mental health diseases by referring to the system construction scheme; the mental health improvement scheme combining deep reinforcement learning and the knowledge graph can be updated and optimized at any time according to the condition of the user; the invention can make the user converse on the network in an anonymous form, namely, the user describes himself to obtain the self description of the user through the user, and then the collected information is used as the input of text analysis, thus solving the problem that the user does not want to contact the doctor and expose personal information; the emotion detection platform can be placed in the cache library by the cloud computing platform part, so that the energy consumption of the smart phone terminal is reduced, meanwhile, the delay caused by computing can be reduced by the strong computing capacity of the cloud platform, and the user experience degree is improved.
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, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A conversational interaction design method for mental health assessment, the method comprising the steps of:
s1, collecting the user conversation by using the terminal part of the smart phone, screening the user information, and uploading the screened user information to a cloud platform;
s2, receiving information data of the user on the cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map;
and S3, processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user.
2. The dialogue interaction design method for mental health assessment as recited in claim 1, wherein the step of collecting dialogues of the user by using the terminal part of the smart phone, screening information of the user, and uploading the information of the screened user to the cloud platform further comprises the steps of:
s11, receiving information data of a user of the smart phone terminal by using the smart phone terminal, and transmitting the information data of the user to an emotion detection platform of the cloud platform;
s12, analyzing the user data and judging the mental health condition of the user;
and S13, transmitting the detection result of the mental state of the user to the smart phone terminal.
3. The dialog interaction design method for mental health assessment according to claim 2, characterized in that the smartphone terminal comprises user dialog, information gathering and information prescreening stages.
4. The dialog interaction design method for mental health assessment according to claim 2, wherein the analyzing the user data and determining the mental health status of the user further comprises the following steps:
s121, if no sensitive vocabulary appears in the user conversation, the mental health of the user is proved, and the mental health result is directly fed back to the user;
and S122, if the sensitive words appear in the user conversation, uploading the user information to an emotion detection platform, and processing the user information on the emotion detection platform.
5. The dialogue interaction design method for mental health assessment according to claim 1, wherein the step of receiving the information data of the user at the cloud platform and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge graph further comprises the following steps:
s21, obtaining a probability chart of various symptoms of the user through a section of self description of the user and a disease judgment function based on text analysis, and judging whether the user has mental sub-health problems or not according to the probability chart;
s22, providing disease analysis and guidance suggestions for the mental sub-health users from the prepared conversation set through a section of self description of the mental sub-health users, text similarity matching and answer selection based on the question and answer conversation set;
s23, a question-answer dialogue platform is provided for mental sub-health users by constructing knowledge maps of diseases, symptoms and medicines.
6. The dialogue interaction design method for mental health assessment according to claim 5, wherein the construction of the knowledge graph further comprises the following steps:
collecting spoken text expressions of a large number of mental sub-health people by using a web crawler, and completing data cleaning to obtain a constructed dictionary;
completing data annotation by utilizing a dictionary Chinese word segmentation and keyword extraction technology;
adopting machine data marking to match with manual screening to obtain training data marking;
selecting an appropriate sequence data annotation, training named entity recognition for depression assessment;
combining named entity recognition with dictionary-based extraction to obtain complete knowledge extraction;
and (4) unifying the entities to construct a knowledge graph for mental health assessment.
7. The dialogue interaction design method for mental health assessment according to claim 1, wherein the processing the mental health status of the mental sub-health user on the cloud computing platform and transmitting the analysis result to the mental sub-health user further comprises the following steps:
s31, receiving user information collected by the smart phone terminal, and transmitting the information to the data analysis and calculation module;
s32, storing the knowledge graph constructed by the emotion detection platform in a cache library;
and S33, analyzing the mental health condition of the user at the emotion detection platform, and transmitting the analysis result to the user.
8. A dialogue interaction design system for mental health assessment for implementing the steps of the dialogue interaction design method for mental health assessment according to any one of claims 1 to 7, the system comprising:
terminal part of the smart phone: collecting user conversations by using a terminal part of the smart phone, screening user information, and uploading the screened user information to a cloud platform;
the emotion detection platform part: receiving information data of a user at a cloud platform, and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge map;
the cloud computing platform part: and processing the mental health condition of the mental sub-health user on the cloud computing platform, and transmitting the analysis result to the mental sub-health user.
9. The dialogue interaction design system for mental health assessment according to claim 8, wherein the step of receiving the information data of the user at the cloud platform and judging the mental health condition of the user according to the data of the user and the constructed mental health knowledge graph further comprises the following steps:
obtaining a probability chart of various symptoms suffered by the user through a section of self description of the user and a disease judgment function based on text analysis, and judging whether the user has a mental sub-health problem according to the probability chart;
providing disease analysis and guidance suggestions for the mental sub-health users from the prepared conversation set through a section of self description of the mental sub-health users, text similarity matching and answer selection based on a question and answer conversation set;
by constructing knowledge maps of diseases, symptoms and medicines, a question-answer dialogue platform is provided for mental sub-health users.
10. The system of claim 9, wherein the construction of the knowledge-graph further comprises the steps of:
collecting spoken text expressions of a large number of mental sub-health people by using a web crawler, and completing data cleaning to obtain a constructed dictionary;
completing data annotation by utilizing a dictionary Chinese word segmentation and keyword extraction technology;
adopting machine data marking to match with manual screening to obtain training data marking;
selecting an appropriate sequence data annotation, training named entity recognition for depression assessment;
combining named entity recognition with dictionary-based extraction to obtain complete knowledge extraction;
and (4) unifying the entities to construct a knowledge graph for mental health assessment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110818801.9A CN113571184B (en) | 2021-07-20 | 2021-07-20 | Dialogue interactive design method and system for mental health evaluation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110818801.9A CN113571184B (en) | 2021-07-20 | 2021-07-20 | Dialogue interactive design method and system for mental health evaluation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113571184A true CN113571184A (en) | 2021-10-29 |
CN113571184B CN113571184B (en) | 2023-10-31 |
Family
ID=78165761
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110818801.9A Active CN113571184B (en) | 2021-07-20 | 2021-07-20 | Dialogue interactive design method and system for mental health evaluation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113571184B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115083602A (en) * | 2022-08-16 | 2022-09-20 | 阿里巴巴(中国)有限公司 | Mental disease auxiliary diagnosis method, device, equipment, storage medium and system |
CN116469532A (en) * | 2023-04-20 | 2023-07-21 | 荣科科技股份有限公司 | Intelligent hospital management method, system, computer equipment and storage medium |
CN117056536A (en) * | 2023-10-10 | 2023-11-14 | 湖南创星科技股份有限公司 | Knowledge graph driving-based virtual doctor system and operation method thereof |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1995019604A2 (en) * | 1994-01-10 | 1995-07-20 | Informed Access Systems, Inc. | Medical network management system and process |
US20020198707A1 (en) * | 2001-06-20 | 2002-12-26 | Guojun Zhou | Psycho-physical state sensitive voice dialogue system |
KR20120098368A (en) * | 2011-02-25 | 2012-09-05 | 성균관대학교산학협력단 | Apparatus and method for sentiment diagnosis of user |
US20160239573A1 (en) * | 2015-02-18 | 2016-08-18 | Xerox Corporation | Methods and systems for predicting psychological types |
CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
WO2018006470A1 (en) * | 2016-07-07 | 2018-01-11 | 深圳狗尾草智能科技有限公司 | Artificial intelligence processing method and device |
CN109243582A (en) * | 2018-09-19 | 2019-01-18 | 江苏金惠甫山软件科技有限公司 | The human-computer interaction motion management method and system of knowledge based graphical spectrum technology |
CN109241257A (en) * | 2018-08-20 | 2019-01-18 | 重庆柚瓣家科技有限公司 | A kind of the wisdom question answering system and its method of knowledge based map |
CN110598000A (en) * | 2019-08-01 | 2019-12-20 | 达而观信息科技(上海)有限公司 | Relationship extraction and knowledge graph construction method based on deep learning model |
CN111651609A (en) * | 2020-04-24 | 2020-09-11 | 中国电力科学研究院有限公司 | Multi-turn dialogue method and system integrating knowledge graph and emotion supervision |
CN112309520A (en) * | 2020-10-29 | 2021-02-02 | 重庆巴奥科技有限公司 | Paperless application system based on big data health management service |
CN112768070A (en) * | 2021-01-06 | 2021-05-07 | 万佳安智慧生活技术(深圳)有限公司 | Mental health evaluation method and system based on dialogue communication |
CN112908481A (en) * | 2021-03-18 | 2021-06-04 | 马尚斌 | Automatic personal health assessment and management method and system |
CN113053416A (en) * | 2021-02-26 | 2021-06-29 | 上海声通信息科技股份有限公司 | Speech emotion recognition system based on knowledge graph |
-
2021
- 2021-07-20 CN CN202110818801.9A patent/CN113571184B/en active Active
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1995019604A2 (en) * | 1994-01-10 | 1995-07-20 | Informed Access Systems, Inc. | Medical network management system and process |
US20020198707A1 (en) * | 2001-06-20 | 2002-12-26 | Guojun Zhou | Psycho-physical state sensitive voice dialogue system |
KR20120098368A (en) * | 2011-02-25 | 2012-09-05 | 성균관대학교산학협력단 | Apparatus and method for sentiment diagnosis of user |
US20160239573A1 (en) * | 2015-02-18 | 2016-08-18 | Xerox Corporation | Methods and systems for predicting psychological types |
US9805128B2 (en) * | 2015-02-18 | 2017-10-31 | Xerox Corporation | Methods and systems for predicting psychological types |
WO2018006470A1 (en) * | 2016-07-07 | 2018-01-11 | 深圳狗尾草智能科技有限公司 | Artificial intelligence processing method and device |
CN107590120A (en) * | 2016-07-07 | 2018-01-16 | 深圳狗尾草智能科技有限公司 | Artificial intelligence process method and device |
CN107145744A (en) * | 2017-05-08 | 2017-09-08 | 合肥工业大学 | Construction method, device and the aided diagnosis method of medical knowledge collection of illustrative plates |
CN109241257A (en) * | 2018-08-20 | 2019-01-18 | 重庆柚瓣家科技有限公司 | A kind of the wisdom question answering system and its method of knowledge based map |
CN109243582A (en) * | 2018-09-19 | 2019-01-18 | 江苏金惠甫山软件科技有限公司 | The human-computer interaction motion management method and system of knowledge based graphical spectrum technology |
CN110598000A (en) * | 2019-08-01 | 2019-12-20 | 达而观信息科技(上海)有限公司 | Relationship extraction and knowledge graph construction method based on deep learning model |
CN111651609A (en) * | 2020-04-24 | 2020-09-11 | 中国电力科学研究院有限公司 | Multi-turn dialogue method and system integrating knowledge graph and emotion supervision |
CN112309520A (en) * | 2020-10-29 | 2021-02-02 | 重庆巴奥科技有限公司 | Paperless application system based on big data health management service |
CN112768070A (en) * | 2021-01-06 | 2021-05-07 | 万佳安智慧生活技术(深圳)有限公司 | Mental health evaluation method and system based on dialogue communication |
CN113053416A (en) * | 2021-02-26 | 2021-06-29 | 上海声通信息科技股份有限公司 | Speech emotion recognition system based on knowledge graph |
CN112908481A (en) * | 2021-03-18 | 2021-06-04 | 马尚斌 | Automatic personal health assessment and management method and system |
Non-Patent Citations (1)
Title |
---|
田迎;单娅辉;王时绘;: "基于知识图谱的抑郁症自动问答***研究", 湖北大学学报(自然科学版), no. 05, pages 81 - 82 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115083602A (en) * | 2022-08-16 | 2022-09-20 | 阿里巴巴(中国)有限公司 | Mental disease auxiliary diagnosis method, device, equipment, storage medium and system |
CN116469532A (en) * | 2023-04-20 | 2023-07-21 | 荣科科技股份有限公司 | Intelligent hospital management method, system, computer equipment and storage medium |
CN116469532B (en) * | 2023-04-20 | 2023-11-03 | 荣科科技股份有限公司 | Intelligent hospital management method, system, computer equipment and storage medium |
CN117056536A (en) * | 2023-10-10 | 2023-11-14 | 湖南创星科技股份有限公司 | Knowledge graph driving-based virtual doctor system and operation method thereof |
CN117056536B (en) * | 2023-10-10 | 2023-12-26 | 湖南创星科技股份有限公司 | Knowledge graph driving-based virtual doctor system and operation method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN113571184B (en) | 2023-10-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110516161B (en) | Recommendation method and device | |
CN111316281B (en) | Semantic classification method and system for numerical data in natural language context based on machine learning | |
CN113571184B (en) | Dialogue interactive design method and system for mental health evaluation | |
CN112786194A (en) | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence | |
CN111666477B (en) | Data processing method, device, intelligent equipment and medium | |
CN110675944A (en) | Triage method and device, computer equipment and medium | |
CN110337645A (en) | The processing component that can be adapted to | |
WO2023029502A1 (en) | Method and apparatus for constructing user portrait on the basis of inquiry session, device, and medium | |
CN112100406B (en) | Data processing method, device, equipment and medium | |
CN110277167A (en) | The Chronic Non-Communicable Diseases Risk Forecast System of knowledge based map | |
WO2023029506A1 (en) | Illness state analysis method and apparatus, electronic device, and storage medium | |
CN112241457A (en) | Event detection method for event of affair knowledge graph fused with extension features | |
EP4068113A1 (en) | Method for determining text similarity, method for obtaining semantic answer text, and question answering method | |
WO2022227203A1 (en) | Triage method, apparatus and device based on dialogue representation, and storage medium | |
WO2023029501A1 (en) | Smart interrogation method and apparatus, electronic device, and storage medium | |
CN113569023A (en) | Chinese medicine question-answering system and method based on knowledge graph | |
CN111916216A (en) | Medicine knowledge graph construction method and system based on deep learning | |
CN112164459A (en) | Information evaluation method for depression symptoms | |
CN112541066A (en) | Text-structured-based medical and technical report detection method and related equipment | |
CN116313120A (en) | Model pre-training method, medical application task processing method and related devices thereof | |
CN117149998B (en) | Intelligent diagnosis recommendation method and system based on multi-objective optimization | |
CN113658690A (en) | Intelligent medical guide method and device, storage medium and electronic equipment | |
CN113688205A (en) | Disease detection method based on deep learning | |
CN110377698B (en) | Reading understanding-based task processing method and device, equipment and readable medium | |
CN116702743A (en) | Text similarity detection method and device, electronic equipment 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 |