CN112951429A - Information processing method and device for screening psychological crisis of primary and secondary school students - Google Patents
Information processing method and device for screening psychological crisis of primary and secondary school students Download PDFInfo
- Publication number
- CN112951429A CN112951429A CN202110321958.0A CN202110321958A CN112951429A CN 112951429 A CN112951429 A CN 112951429A CN 202110321958 A CN202110321958 A CN 202110321958A CN 112951429 A CN112951429 A CN 112951429A
- Authority
- CN
- China
- Prior art keywords
- corpus
- text
- target
- determining
- target user
- 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
- 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
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the disclosure discloses an information processing method and an information processing device for screening psychological crisis of primary and secondary school students, wherein firstly, after the identity information of a target user is judged to be the identity of the primary and secondary school students, a dialogue corpus text sent by the target user through a user terminal is received; determining a corpus text matched with the dialogue corpus text, and sending the matched corpus text to the user side so as to enable the user side and a target user to establish multi-round dialogue interaction; after multi-turn dialogue interaction, acquiring all corpus texts determined in the multi-turn dialogue interaction process; determining data under a plurality of preset indexes based on all the corpus texts; and finally, determining the psychological crisis level of the target user based on the data and a preset strategy. The data source is obtained in an interactive mode, and the efficiency and the accuracy of screening the psychological crisis of the primary and secondary school students can be improved by determining the psychological crisis level based on the data source.
Description
Technical Field
The disclosure relates to the technical field of psychological data processing, in particular to an information processing method and device for screening psychological crisis of primary and secondary school students.
Background
The screening and intervention work of the psychological crisis of the middle and primary schools is an important component of the safety work of the schools, and is brought into the routine system construction of the schools to establish a long-acting mechanism. The prevention and early warning are important. The construction of the psychological crisis screening and intervention working system of primary and secondary school students is gradually promoted in China from 2014, the psychological crisis early warning report of the primary and secondary school students is periodically issued, the critical crisis early warning information of key regions, key time periods, key objects and the like of the psychological crisis early warning of the primary and secondary school students in the whole province is issued by combining the conditions of the psychological general survey result, the psychological crisis investigation and the like, and the prevention screening and intervention working of the psychological crisis are guided to be done in advance.
The mental health education of middle and primary schools is the demand of the current school education, avoids various emergencies, maintains stable social associations, enables the schools to operate normally, ensures the normal health and the comprehensive development of students and meets the demand of the social change period. Correspondingly, the domestic middle and primary school students have no systematic and structured psychological crisis intervention informatization system on the aspect of psychological health, most of the psychological data acquisition and management of the middle and primary school students are finished manually, the psychological data acquisition and management is not standardized, great working intensity is brought to the school, and meanwhile, the psychological data is difficult to form so as to improve the intervention quality.
The psychological crisis grade can be used for representing the degree of mental unhealthy of primary and secondary school students, and the higher the grade is, the higher the probability of the extreme psychological event is.
Disclosure of Invention
The main purpose of the present disclosure is to provide an information processing method and apparatus for screening the psychological crisis of primary and secondary school students, so as to solve the problem that the manual screening method for screening the psychological crisis of primary and secondary school students is inefficient.
In order to achieve the above object, according to a first aspect of the present disclosure, there is provided an information processing method for screening psychological crisis of primary and secondary school students, including: after the identity information of the target user is judged to be the identity of the primary and secondary school students, receiving a dialogue corpus text sent by the target user through a user side; determining a corpus text matched with the dialogue corpus text, and sending the matched corpus text to a user side so as to enable the user side and the target user to establish multiple rounds of dialogue interaction; after multi-turn dialogue interaction, acquiring all corpus texts determined in the multi-turn dialogue interaction process; determining data under a plurality of preset indexes based on all the corpus texts; and determining the psychological crisis level of the target user based on the data and a preset strategy.
Optionally, the method further comprises: determining intervention strategy information corresponding to the psychological crisis grade; acquiring feedback information which is sent by the user side and corresponds to the intervention strategy information; and determining the current crisis level of the target user based on the feedback information.
Optionally, the determining data under a plurality of preset indexes based on the all corpus texts includes: determining whether the emotion categories corresponding to all the corpus texts contain target emotion categories or not based on all the corpus texts; and if the target emotion category is contained, determining the data of all the corpus texts under the multiple preset indexes.
Optionally, the determining data under a plurality of preset indexes based on the all corpus texts includes: extracting a first target characteristic text of all the corpus texts to determine the current emotion category of the target user based on the first target characteristic text; extracting a second target characteristic text of all the corpus texts to determine the emotion intensity of the target user based on the second target characteristic text; extracting a second target feature text of the all corpus texts to determine whether the all corpus texts contain a target event based on the second target feature text; and extracting a third target characteristic text of all the corpus texts to determine cognitive deviation information based on the third target characteristic text.
As an optional implementation manner of this embodiment, before determining a corpus text adapted to the dialog corpus text and sending the adapted corpus text to the user side to enable the user side to establish multiple dialog interactions with the target user, the method further includes: and establishing a conversation content pool, so that each corpus text fed back to the target user by the user side in the content pool corresponds to a plurality of corpus texts capable of expressing the same semantics.
Optionally, determining a corpus text adapted to the dialog corpus text, and sending the adapted corpus text to the user side, so that the user side and the target user establish multiple rounds of dialog interactions, including: converting the dialogue corpus text sent by the target user through the user side into a vector; performing semantic analysis on the dialogue corpus text to obtain semantic information; and determining the corpus text fed back to the target user in a content pool based on the vector and the semantic information.
According to a second aspect of the present disclosure, there is provided an information processing apparatus for screening psychological crisis of primary and secondary school students, comprising: the receiving unit is configured to receive the dialogue corpus text sent by the target user through the user terminal after the identity information of the target user is judged to be the identity of the primary and secondary school students; the first determining unit is configured to determine a corpus text matched with the dialogue corpus text and send the matched corpus text to the user side so that the user side and the target user can establish multiple rounds of dialogue interaction; the obtaining unit is configured to obtain all corpus texts determined in the multi-round conversation interaction process after the multi-round conversation interaction; a second determination unit configured to determine data under a plurality of preset indexes based on the entire corpus text; a third determination unit configured to determine a psychological crisis level of the target user based on the data and a preset calculation strategy.
Optionally, the apparatus further comprises: a fourth determination unit configured to determine intervention strategy information corresponding to the psychological crisis level; an obtaining unit configured to obtain feedback information corresponding to the intervention policy information sent by the user side; a fifth determination unit configured to determine a current crisis level of the target user based on the feedback information.
According to a third aspect of the present disclosure, there is provided an electronic device comprising storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to carry out the method as in any one of the embodiments of the first aspect
According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium, comprising computer instructions stored thereon, the computer instructions being configured to cause the computer to execute the information processing method for screening psychological crisis of primary and secondary school students according to any one of the embodiments of the first aspect.
In the embodiment of the disclosure, after the identity information of the target user is judged to be the identity of the primary and secondary school students, a dialogue corpus text sent by the target user through a user terminal is received; determining a corpus text matched with the dialogue corpus text, and sending the matched corpus text to the user side so as to enable the user side and a target user to establish multi-round dialogue interaction; after multi-turn dialogue interaction, acquiring all corpus texts determined in the multi-turn dialogue interaction process; determining data under a plurality of preset indexes based on all the corpus texts; and finally, determining the psychological crisis level of the target user based on the data and a preset strategy. The data source is obtained in an interactive mode, and the efficiency and the accuracy of screening the psychological crisis of the primary and secondary school students can be improved by determining the psychological crisis level based on the data source.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of an information processing method for primary and secondary school student psychological crisis screening according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an information processing apparatus for screening psychological crisis of primary and secondary school students according to an embodiment of the present disclosure;
FIG. 3 is a schematic block diagram of an electronic device suitable for use in implementing embodiments of the present disclosure.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those skilled in the art, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only some embodiments of the present disclosure, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the present disclosure may be described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an embodiment of the present disclosure, there is provided an information processing method for screening psychological crisis of primary and secondary school students, as shown in fig. 1, the method including steps 101 to 105 as follows.
Step 101: and after the identity information of the target user is judged to be the identity of the primary and secondary school students, receiving a dialogue corpus text sent by the target user through a user side.
In this embodiment, the main body performing emotion recognition model training may be a server or any terminal with data processing capability, the execution main body may first receive an authentication request sent by a user terminal, and then perform authentication on a target user triggering the user terminal authentication request in response to the request to determine whether the target user is a primary and secondary school student, and if the target user is the primary and secondary school student, the server may receive dialogue corpora locally received by the user terminal sent by the user terminal.
The students in middle and primary schools can send conversation corpora to the user terminal, the conversation corpora do not have any limitation and belong to daily conversations, such as problems in life or learning, such as 'how to relieve anxiety and emotion in high-speed college entrance examination', 'how much stress is felt by students nearby', and the like. In the embodiment, the psychological information of the primary and secondary school students is collected in a daily conversation mode, and the psychological crisis level determined based on the psychological information can very accurately represent the psychological conditions of the primary and secondary school students. If the assessment is directly carried out by a manual assessment mode, firstly, for primary and secondary school students, a newspaper hiding behavior appears in the assessment process, and meanwhile, the situation that the students are unwilling to reveal their real psychological ideas exists; secondly, through the manual evaluation mode, the collected information is only limited to the information collected in the evaluation process, and not to the large amount of daily data accumulated daily. All the situations can cause unreal psychological data sources and limitation of acquisition means, so that the screening result is not accurate.
It can be understood that the method screens the psychological crisis of primary and secondary school students (minors), and due to the particularity of the identity, the acquired psychological information, the determination of the psychological crisis level, the intervention strategy and the like in the subsequent dialogue interaction process are determined uniquely by the identity.
Step 102: and determining a corpus text matched with the dialogue corpus text, and sending the matched corpus text to the user side so as to enable the user side to establish multiple rounds of dialogue interaction with the target user.
In this embodiment, after receiving the dialog corpus text, the server needs to determine the corpus text adapted to the corpus. The adapted corpus text can be firstly subject to dialogue corpus text to ensure that no question is asked, and secondly, the adapted corpus text can be the corpus text which aims at determining psychological crisis and inducing a target user. After the server determines the adapted corpus text, the adapted corpus text can be sent to the user side, so that the user side broadcasts the corpus, and multiple rounds of dialogue interaction are established. The corpus text for determining adaptation may be determined from a pre-established content pool, or may be determined by other means, which is not limited herein.
As an optional implementation manner of this embodiment, before determining a corpus text adapted to a dialog corpus text and sending the adapted corpus text to a user side to enable the user side to establish multiple dialog interactions with the target user, the method further includes: and establishing a conversation content pool, so that each corpus text fed back to the target user by the user side in the content pool corresponds to a plurality of corpus texts capable of expressing the same semantics.
In this embodiment, the FAQ model may be used to determine the adapted corpus text, and the process of training the FAQ model may include: training data can be obtained based on a preset scale, and the captured data is question-answer pairs; cleaning and denoising the data, reducing unnecessary symbols, removing spaces, converting case and case, and the like; labeling the data; and then processing the question and answer pairs, and finally enabling each corpus text fed back to the target user by the user end to correspond to a plurality of corpus texts capable of representing the same semantic meaning. For example, the semantic recognition result that the dialog corpus of the target user is "the schoolmates are too much and the pressure is felt to be good" is "the learning pressure is large", and 1 feedbackable corpus text can be corresponded to the learning pressure. However, because the semantic meaning of "learning with high pressure" may have different representation methods, for example, "a person is about to go up before sleeping badly", and the like, the content pool in this embodiment may represent at least 5 corpus texts with the same semantic meaning, where the 5 corpus texts all correspond to the same corpus text that can be fed back. After the content pool is built, all corpora need to be converted into vectors in an offline environment, so that the time consumed by online service processing is shortened, and a user request can be responded in time. Data magnitude is greatly improved by processing and storing data through an Elastic Search (ES) framework.
As an optional implementation manner of this embodiment, determining a corpus text adapted to the dialog corpus text, and sending the adapted corpus text to the user side, so that the user side and the target user establish multiple rounds of dialog interactions includes: converting the dialogue corpus text sent by the target user through the user side into a vector; performing semantic analysis on the dialogue corpus text to obtain semantic information; and determining the corpus text fed back to the target user in a content pool based on the vector and the semantic information.
In this embodiment, after receiving the dialog corpus of the target user, the server needs to recall the adapted corpus text, and may convert the dialog corpus into a vector, and may perform matching based on the text on the literal hierarchy, that is, matching between the query of the user and the word hierarchy in the content pool; the same semantic meaning can then be expressed based on matching at the semantic understanding level, i.e. through the semantic information of the external pre-training word vector, although the words are seemingly different. The specific implementation strategy recall characteristics comprise TFIDF, BM25, information entropy, Word2Vec _ Max and Word2Vec _ Mean. Wherein TFIDF, BM25, entropy of information are matching literally, and Word2Vec _ Max and Word2Vec _ Mean are matching based on semantic information. Each recall feature policy may recall 5 corpus texts from the content pool that are similar to the dialog corpus. And then, the recalled corpus texts similar to the dialogue corpus can be fused and sequenced, the corpus text with the highest score is determined as the most similar corpus, and the corresponding corpus text which can be fed back is used as the adaptive corpus text and sent to the user side. The fine ranking layer is used for fusing and fine ranking candidate similar questions matched by different recall strategies of the recall layer and then returning the recorded answer with the highest ranking score to the user. The fine ranking layer extracts effective semantic feature information from the query of the user and the candidate similar problem sequence by using a neural network XLNET, considers the feature influence of mutual interaction between the query and the candidate similar problem, and gives the best answer reply to return to the user side after synthesizing all information.
Step 103: and after multi-turn dialogue interaction, acquiring all corpus texts determined in the multi-turn dialogue interaction process.
Step 104: and determining data under a plurality of preset indexes based on all the corpus texts.
In the present embodiment, the plurality of preset indicators may include an emotion indicator (no emotion, unknown emotion, music, anger, sadness, fear, dislike, fright), an emotion intensity indicator (the emotion intensity may include 5 levels of intensity, 1,3,5,7,9 may be represented by numbers), an indicator of whether or not a target event is included (whether or not a crisis event is included, for example, parent divorce, family violence, and the like, and may be represented by 3 kinds of labels, such as occurred, not occurred, and not recognized), and a cognitive deviation indicator (including absolute and not absolute, for example, the psychology that a parent divorce is extreme belongs to absolute cognitive deviation). The data under multiple indexes, namely, the information under each index obtained by identifying each model, can be used for determining the psychological crisis level. The model may include: and the emotion recognition model is used for recognizing emotion classification. Training is carried out through data with emotion class labels, and when a user inputs dialogue linguistic data, which emotion belongs to can be judged. In the training process, the data labeling step can include data grabbing through an internet open channel and self-owned data set integration, and through manual labeling, 8 kinds of labels are in total: no emotion, unknown emotion, joy, anger, sadness, fear, aversion and fright. And a characteristic extraction step, namely inputting data with emotion labels, simultaneously calculating content characteristics and context characteristics through a neural network model XLNET, extracting word emotion weight, calculating emotion weight of a sentence, and judging which emotion classification belongs to. And an emotion classification step, wherein when the user inputs content, the emotion classification step can judge which emotion category the user belongs to.
And the degree model is used for identifying the emotional intensity, training is carried out through data with the emotional intensity labels, and when a user inputs a problem, the emotional intensity grade of the user can be judged. The data labeling step comprises data grabbing through an internet open channel and self-owned data set integration, and through manual labeling, 5 degree grade labels are in total: 1. 3,5,7 and 9. And (3) training a model, namely inputting data with emotion intensity levels, performing a level classification task through a neural network XLNET, and outputting the probability of each emotion intensity. Degree classification: when the user inputs contents, it is possible to judge which emotional intensity level belongs.
An event recognition model that identifies whether an event has occurred, has not occurred, and is otherwise (events that have no tendency or are described are not actionable). Data annotation: data snatchs and has data set integration oneself through internet open channel, through artifical mark, totally 3 kinds of event tense labels: occurred, not identified. Model training: inputting data with event temporal labels, training through a neural network XLNET, and judging whether an event occurs or not by an output end.
The cognitive deviation model divides the thought cognitive deviation into an absolute type and a non-absolute type. The model mainly determines to which kind of cognition the user input belongs. And (3) data labeling, wherein data are captured and integrated with a self-owned data set through an internet open channel, and through manual labeling, 2 kinds of idea cognitive deviation labels are provided: absolute, not absolute. Model training: data with cognitive deviation labels are input, training is carried out through a neural network XLNET, and the output end judges whether the idea is absolute or not.
As an optional implementation manner of this embodiment, determining, based on the all corpus texts, data under a plurality of preset indexes includes: determining whether the emotion categories corresponding to all the corpus texts contain target emotion categories or not based on all the corpus texts; and if the target emotion category is contained, determining the data of all the corpus texts under a plurality of preset indexes.
In this embodiment, when determining the psychological crisis level, since only the user whose psychological crisis level belongs to the severe level needs to be screened out, when determining the psychological crisis level, the emotion classification can be determined first, and the emotion classification recognition model can be used for recognition, so as to obtain which of the moods, unknown emotions, music, anger, grief, fear, nausea and fright the target user belongs to, and then the further screening can be performed for the user whose emotion classification is anger, grief, fear, nausea and fright. By adopting the mode, the screening efficiency can be accelerated.
As an optional implementation manner of this embodiment, determining the psychological crisis level of the target user based on the data and a preset calculation strategy includes extracting a first target feature text of all the corpus texts, so as to determine a current emotion category of the target user based on the first target feature text; and extracting a second target characteristic text of the all corpus texts to determine the emotional intensity of the target user based on the second target characteristic text. Extracting a second target feature text of the all corpus texts to determine whether the all corpus texts contain a target event based on the second target feature text; and/or extracting a third target characteristic text of all the corpus texts to determine cognitive deviation information based on the third target characteristic text.
In this embodiment, after the data are obtained, a preset strategy can be used to determine a psychological crisis grade, which can be embodied in a score manner; it can also be embodied in different grades, such as high, medium, low. For example, a weighted sum algorithm may be used to determine the score for the psychological crisis level.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present disclosure, there is also provided an apparatus for implementing the above information processing method for screening psychological crisis of primary and secondary school students, as shown in fig. 2, the apparatus including:
the receiving unit 201 is configured to receive a dialog corpus text sent by a target user through a user terminal after determining that the identity information of the target user is the identity of a primary and secondary school student; a first determining unit 202, configured to determine a corpus text adapted to the dialog corpus text, and send the adapted corpus text to the user side, so that the user side and the target user establish multiple rounds of dialog interactions; the obtaining unit 203 is configured to obtain all corpus texts determined in the multi-round conversation interaction process after the multi-round conversation interaction; a second determining unit 204 configured to determine data under a plurality of preset indexes based on the whole corpus text; a third determining unit 205 configured to determine a psychological crisis level of the target user based on the data and a preset calculation strategy.
As an optional implementation manner of this embodiment, the apparatus further includes: a fourth determination unit configured to determine intervention strategy information corresponding to the psychological crisis level; an obtaining unit configured to obtain feedback information corresponding to the intervention policy information sent by the user side; a fifth determination unit configured to determine a current crisis level of the target user based on the feedback information.
The embodiment of the present disclosure provides an electronic device, as shown in fig. 3, the electronic device includes one or more processors 31 and a memory 32, where one processor 31 is taken as an example in fig. 3.
The controller may further include: an input device 33 and an output device 33.
The processor 31, the memory 32, the input device 33 and the output device 33 may be connected by a bus or other means, and fig. 3 illustrates the connection by a bus as an example.
The processor 31 may be a Central Processing Unit (CPU). The processor 31 may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 32, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules, such as program instructions/modules corresponding to the control methods in the embodiments of the present disclosure. The processor 31 executes various functional applications of the server and data processing by running non-transitory software programs, instructions and modules stored in the memory 32, namely, implements the information processing method for screening psychological crisis of primary and secondary school students of the above method embodiment.
The memory 32 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a processing device operated by the server, and the like. Further, the memory 32 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 32 may optionally include memory located remotely from the processor 31, which may be connected to a network connection device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 33 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the processing device of the server. The output device 34 may include a display device such as a display screen.
One or more modules are stored in the memory 32, which when executed by the one or more processors 31 perform the method as shown in fig. 1.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program to instruct related hardware, and the program can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the motor control methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-only memory (ROM), a Random Access Memory (RAM), a flash memory (FlashMemory), a hard disk (hard disk drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. An information processing method for screening psychological crisis of primary and secondary school students is characterized by comprising the following steps:
after the identity information of the target user is judged to be the identity of the primary and secondary school students, receiving a dialogue corpus text sent by the target user through a user side;
determining a corpus text matched with the dialogue corpus text, and sending the matched corpus text to a user side so as to enable the user side and the target user to establish multiple rounds of dialogue interaction;
after multi-turn dialogue interaction, acquiring all corpus texts determined in the multi-turn dialogue interaction process;
determining data under a plurality of preset indexes based on all the corpus texts;
and determining the psychological crisis level of the target user based on the data and a preset strategy.
2. The information processing method for mental crisis screening of elementary and secondary school students according to claim 1, characterized by further comprising:
determining intervention strategy information corresponding to the psychological crisis grade;
acquiring feedback information which is sent by the user side and corresponds to the intervention strategy information;
and determining the current crisis level of the target user based on the feedback information.
3. The information processing method for mental crisis screening of primary and secondary school students according to claim 1, wherein the determining data under a plurality of preset indexes based on the whole corpus text comprises:
determining whether the emotion categories corresponding to all the corpus texts contain target emotion categories or not based on all the corpus texts;
and if the target emotion category is contained, determining the data of all the corpus texts under a plurality of preset indexes.
4. The information processing method for mental crisis screening of primary and secondary school students according to claim 1, wherein determining data under a plurality of preset indexes based on the entire corpus text comprises:
extracting a first target characteristic text of all the corpus texts to determine the current emotion category of the target user based on the first target characteristic text;
extracting a second target characteristic text of all the corpus texts to determine the emotion intensity of the target user based on the second target characteristic text;
extracting a second target feature text of the all corpus texts to determine whether the all corpus texts contain a target event based on the second target feature text;
and extracting a third target characteristic text of all the corpus texts to determine cognitive deviation information based on the third target characteristic text.
5. The information processing method for mental crisis screening of primary and secondary school students according to claim 1, wherein before determining the corpus text adapted to the dialog corpus text and sending the adapted corpus text to the user side to enable the user side to establish multiple dialog interactions with the target user, the method further comprises:
and establishing a conversation content pool, so that each corpus text fed back to the target user by the user side in the content pool corresponds to a plurality of corpus texts capable of expressing the same semantics.
6. The information processing method for mental crisis screening of primary and secondary school students according to claim 5, wherein determining the corpus text adapted to the dialogue corpus text and sending the adapted corpus text to the user side so that the user side establishes multiple rounds of dialogue interaction with the target user comprises:
converting the dialogue corpus text sent by the target user through the user side into a vector;
performing semantic analysis on the dialogue corpus text to obtain semantic information;
and determining the corpus text fed back to the target user in a content pool based on the vector and the semantic information.
7. An information processing apparatus for screening psychological crisis of primary and secondary school students, comprising:
the receiving unit is configured to receive the dialogue corpus text sent by the target user through the user terminal after the identity information of the target user is judged to be the identity of the primary and secondary school students;
the first determining unit is configured to determine a corpus text matched with the dialogue corpus text and send the matched corpus text to the user side so that the user side and the target user can establish multiple rounds of dialogue interaction;
the obtaining unit is configured to obtain all corpus texts determined in the multi-round conversation interaction process after the multi-round conversation interaction;
a second determination unit configured to determine data under a plurality of preset indexes based on the entire corpus text;
a third determination unit configured to determine a psychological crisis level of the target user based on the data and a preset calculation strategy.
8. The information processing apparatus for mental crisis screening of elementary and secondary school students according to claim 7, characterized by further comprising:
a fourth determination unit configured to determine intervention strategy information corresponding to the psychological crisis level;
an obtaining unit configured to obtain feedback information corresponding to the intervention policy information sent by the user side;
a fifth determination unit configured to determine a current crisis level of the target user based on the feedback information.
9. An electronic device comprising one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of training an emotion recognition model as recited in any of claims 1-6.
10. A computer storage medium storing computer instructions for causing a computer to perform the method of training a emotion recognition model according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110321958.0A CN112951429A (en) | 2021-03-25 | 2021-03-25 | Information processing method and device for screening psychological crisis of primary and secondary school students |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110321958.0A CN112951429A (en) | 2021-03-25 | 2021-03-25 | Information processing method and device for screening psychological crisis of primary and secondary school students |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112951429A true CN112951429A (en) | 2021-06-11 |
Family
ID=76228274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110321958.0A Pending CN112951429A (en) | 2021-03-25 | 2021-03-25 | Information processing method and device for screening psychological crisis of primary and secondary school students |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112951429A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116913527A (en) * | 2023-09-14 | 2023-10-20 | 北京健康有益科技有限公司 | Hypertension evaluation method and system based on multi-round dialogue frame |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018133761A1 (en) * | 2017-01-17 | 2018-07-26 | 华为技术有限公司 | Method and device for man-machine dialogue |
| WO2018196684A1 (en) * | 2017-04-24 | 2018-11-01 | 北京京东尚科信息技术有限公司 | Method and device for generating conversational robot |
| CN110379445A (en) * | 2019-06-20 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Method for processing business, device, equipment and storage medium based on mood analysis |
| CN111667926A (en) * | 2020-06-06 | 2020-09-15 | 中国科学院心理研究所 | Psychological consultation (conversation) system and method based on artificial intelligence |
| CN111694938A (en) * | 2020-04-27 | 2020-09-22 | 平安科技（深圳）有限公司 | Emotion recognition-based answering method and device, computer equipment and storage medium |
-
2021
- 2021-03-25 CN CN202110321958.0A patent/CN112951429A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018133761A1 (en) * | 2017-01-17 | 2018-07-26 | 华为技术有限公司 | Method and device for man-machine dialogue |
| WO2018196684A1 (en) * | 2017-04-24 | 2018-11-01 | 北京京东尚科信息技术有限公司 | Method and device for generating conversational robot |
| CN110379445A (en) * | 2019-06-20 | 2019-10-25 | 深圳壹账通智能科技有限公司 | Method for processing business, device, equipment and storage medium based on mood analysis |
| CN111694938A (en) * | 2020-04-27 | 2020-09-22 | 平安科技（深圳）有限公司 | Emotion recognition-based answering method and device, computer equipment and storage medium |
| CN111667926A (en) * | 2020-06-06 | 2020-09-15 | 中国科学院心理研究所 | Psychological consultation (conversation) system and method based on artificial intelligence |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116913527A (en) * | 2023-09-14 | 2023-10-20 | 北京健康有益科技有限公司 | Hypertension evaluation method and system based on multi-round dialogue frame |
| CN116913527B (en) * | 2023-09-14 | 2023-12-05 | 北京健康有益科技有限公司 | Hypertension evaluation method and system based on multi-round dialogue frame |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| O'dea et al. | A linguistic analysis of suicide-related Twitter posts | |
| Abulof | Normative concepts analysis: unpacking the language of legitimation | |
| Skowron | Affect listeners: Acquisition of affective states by means of conversational systems | |
| WO2016085409A1 (en) | A method and system for sentiment classification and emotion classification | |
| KR102353545B1 (en) | Method and Apparatus for Recommending Disaster Response | |
| CN108681749B (en) | Privacy information discrimination method based on network social platform | |
| CN111134694A (en) | Psychological consultation analysis method and device based on human-computer interaction | |
| CN105095415A (en) | Method and apparatus for confirming network emotion | |
| CN116662522B (en) | Question answer recommendation method, storage medium and electronic equipment | |
| Ríssola et al. | Anticipating depression based on online social media behaviour | |
| Shen et al. | Exploiting temporal information in a two-stage classification framework for content-based depression detection | |
| Victor et al. | Machine learning techniques for depression analysis on social media-case study on bengali community | |
| CN118013963A (en) | Method and device for identifying and replacing sensitive words | |
| CN112951429A (en) | Information processing method and device for screening psychological crisis of primary and secondary school students | |
| Bhaumik et al. | Adapting emotion detection to analyze influence campaigns on social media | |
| CN109739976A (en) | Network social intercourse platform privacy discriminating method, system, storage medium and computer | |
| Xu et al. | Network-based prediction of the disclosure of ideation about self-harm and suicide in online counseling sessions | |
| CN117407507A (en) | Event processing method, device, equipment and medium based on large language model | |
| CN115408500A (en) | Question-answer consistency evaluation method and device, electronic equipment and medium | |
| Sakthi et al. | CyberHelp: Sentiment Analysis on Social Media Data Using Deep Belief Network to Predict Suicidal Ideation of Students | |
| Bonacin et al. | An ontological model for supporting intention-based information sharing on collaborative problem solving | |
| Bonacin et al. | An ontological model for representing pragmatic aspects of collaborative problem solving | |
| Mathimagal et al. | Intellectual behaviour of student based on education data determined by opinion mining | |
| Wen et al. | A Gramulator analysis of gendered language in cable news reportage | |
| Guerrero-Sosa et al. | A Fuzzy Approach to Detecting Suspected Disinformation in Videos |
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 |