CN112214607B - Interactive method, psychological intervention system, terminal and medium based on artificial intelligence - Google Patents
Interactive method, psychological intervention system, terminal and medium based on artificial intelligence Download PDFInfo
- Publication number
- CN112214607B CN112214607B CN202010929851.XA CN202010929851A CN112214607B CN 112214607 B CN112214607 B CN 112214607B CN 202010929851 A CN202010929851 A CN 202010929851A CN 112214607 B CN112214607 B CN 112214607B
- Authority
- CN
- China
- Prior art keywords
- node information
- information
- character
- key
- emotion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/165—Evaluating the state of mind, e.g. depression, anxiety
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The embodiment of the invention discloses an interaction method based on artificial intelligence, which comprises the following steps: obtaining dialogue information input by a user, and obtaining at least one key node information according to the dialogue information; predicting predicted node information corresponding to the at least one key node information according to the psychological knowledge graph; generating an intervention strategy according to the prediction node information; the psychological knowledge map is composed of a plurality of five-tuple structures which are related to each other, wherein each five-tuple structure comprises character node information, and event node information, emotion node information, cognitive node information and behavior node information which are related to the character node information. The invention can improve the effectiveness and accuracy of intervention and improve the consultation efficiency. The invention also provides a psychological intervention system, a terminal and a medium.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an interaction method, a psychological intervention system, a terminal and a medium based on artificial intelligence.
Background
The technical implementation process of the knowledge graph comprises six parts, namely knowledge acquisition, knowledge fusion, knowledge storage, query-type semantic understanding, knowledge retrieval and visual display, and represents the latest development direction of the current knowledge organization and retrieval technology. At present, the application of knowledge graph mainly focuses on the aspects of commercial search engine, question and answer system, e-commerce platform, social network site and the like.
The general form of psychological counseling is that a help seeker and a consultant counselor carry out counseling face to face, and with the development of computer technology, self-service type psychological counseling based on web pages gradually appears, and the counseling mode is helpful for expanding the availability of psychological counseling services, but the user experience of the mode is poor, and the interaction is lacked.
Disclosure of Invention
Based on this, it is necessary to propose an artificial intelligence based interaction method, a psychological intervention system, a terminal and a medium for addressing the above problems.
An artificial intelligence based interaction method, comprising: obtaining dialogue information input by a user, and obtaining at least one key node information according to the dialogue information; predicting predicted node information corresponding to the at least one key node information according to the psychological knowledge graph; generating an intervention strategy according to the prediction node information; the psychological knowledge map is composed of a plurality of five-tuple structures which are related to each other, wherein each five-tuple structure comprises character node information, and event node information, emotion node information, cognitive node information and behavior node information which are related to the character node information.
A psychological intervention system, comprising: the acquisition module is used for acquiring dialogue information input by a user and acquiring at least one key node information according to the dialogue information; the prediction module is used for predicting the prediction node information corresponding to the at least one key node information according to the psychological knowledge graph; the intervention module is used for generating an intervention strategy according to the prediction node information; the psychological knowledge map is composed of a plurality of five-tuple structures which are related to each other, wherein each five-tuple structure comprises character node information, and event node information, emotion node information, cognitive node information and behavior node information which are related to the character node information.
A psychological intervention terminal, comprising: a processor coupled to the memory and a memory having a computer program stored therein, the processor executing the computer program to implement the method as described above.
A storage medium storing a computer program executable by a processor to implement a method as described above.
The embodiment of the invention has the following beneficial effects:
at least one key node information is obtained from the dialogue information of the user, the prediction node information corresponding to the at least one key node information is predicted according to the psychological knowledge graph, the node information can be accurately predicted, and the pertinence and the effectiveness of an intervention strategy are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Wherein:
FIG. 1 is a schematic representation of a psychological knowledgemap provided by the present invention;
FIG. 2 is a schematic flow chart diagram of one embodiment of a method for constructing a psychological knowledgebase map provided by the present invention;
FIG. 3 is a flow chart diagram illustrating an embodiment of an artificial intelligence based interaction method provided by the present invention;
fig. 4 is a schematic flowchart of an embodiment of a method for acquiring information of at least one key node according to the present invention;
FIG. 5 is a schematic diagram of a psychological intervention system according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an embodiment of a psychological intervention terminal provided by the present invention;
fig. 7 is a schematic structural diagram of an embodiment of a storage medium provided in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
With the development of computer technology, self-help psychological grooming based on web pages gradually appears, and the grooming mode helps to expand the availability of psychological grooming services, but the user experience of the mode is poor and the interaction is lacked.
In the embodiment, in order to solve the above problem, an artificial intelligence interaction method is provided, which can accurately predict the behavior of the user, provide an effective intervention suggestion, and improve the psychological intervention effect on the user.
Referring to fig. 1, fig. 1 is a schematic diagram of a psychological knowledge-map provided by the present invention.
As shown in fig. 1, the psychological knowledge-map is composed of a plurality of five-element structures associated with each other, each of which includes character node information, and event node information, emotion node information, cognitive node information, and behavior node information associated with the character node information. For example, the character node information Pe1 is connected to the event node information Ev1, the emotion node information Em1, the cognitive node information Co1, and the behavior node information Be1 to form a five-tuple structure. The character node information Pe2 is connected with the event node information Ev1, the emotion node information Em2, the cognitive node information Co1 and the behavior node information Be2 to form another five-tuple structure. The two five-tuple structures are connected through event node information Ev1 and cognitive node information Co1, that is, when people Pe1 and Pe2 face the same event Ev1, the people have the same cognitive Co1, but the emotion of Pe1 is Em1, the action made is Be1, the emotion of Pe2 is Em2, and the action made is Be 2. Other five-tuple structures in the psychological knowledgemap are also related to each other by similar relationships.
It should be noted that only 6 quintet structures are shown in fig. 1, and the psychological knowledge map contains a large number of quintet structures associated with each other in practical use.
Referring to fig. 2, fig. 2 is a schematic flow chart of an embodiment of the method for constructing a psychological knowledge base according to the present invention. The method for constructing the psychological knowledge map comprises the following steps:
s101: the method comprises the steps of obtaining training information, extracting character node information in the training information, and extracting event node information, emotion node information, cognitive node information and behavior node information which are related to the character node information.
In a specific implementation scenario, training information is obtained, where the training information may be medical records, medical audios, videos, and the like input by a user, or may be various information organized by the user. The extraction of the character node information in the training information can be realized by a method such as semantic recognition, and the like, and can also obtain the character node information specified by the user. One or more character node information may be included in the training information.
After character node information is extracted, cognitive exploration is conducted on training information by taking character node information as a center, cognitive node information related to the character node information is obtained, event inquiry is conducted, event node information related to the character node information is obtained, behavior analysis is conducted, behavior node information related to the character node information is obtained, emotion mining is conducted, and emotion node information related to the character node information is obtained.
S102: and constructing a quintuple structure of the character node information and event node information, emotion node information, cognitive node information and behavior node information which are associated with the character node information, and generating a psychological knowledge map according to the quintuple structure.
In a specific implementation scenario, character node information, event node information, emotion node information, cognitive node information and behavior node information associated with the character node information are combined in a correlated manner to construct a five-tuple structure. And associating the multiple quintuple structures through the same node information to generate the psychological knowledge map.
Referring to fig. 3, fig. 3 is a flowchart illustrating an interaction method based on artificial intelligence according to an embodiment of the present invention. The invention provides an interaction method based on artificial intelligence, which comprises the following steps:
s201: and acquiring dialogue information input by a user, and acquiring at least one key node information according to the dialogue information.
In this embodiment, the user may initiate a program to enter dialogue information, such as narration of recent experiences and feelings, when psychological counseling or psychological intervention is desired. Furthermore, simple man-machine conversation can be carried out with the user according to a preset chat model, and conversation information input by the user can be obtained.
And extracting the dialogue information input by the user to obtain at least one piece of key node information. At least one key node information corresponds to at most four of character node information, event node information, emotion node information, cognitive node information and behavior node information in the quintuple structure. Specifically, the person node information of the user, such as sex, age, native place, and the like, can be acquired by a simple inquiry. And extracting information of the dialogue information by adopting a preset information extraction algorithm to obtain at least one piece of key node information. For example, the key node information is object node information, event node information, emotion node information and cognitive node information.
In other implementation scenarios, when the user registers to use the program, the user may be required to fill in personal information and perform personal basic information collection, thereby obtaining the character node information.
In other implementation scenarios, when performing human-computer interaction with a user, including video interaction and voice interaction, the appearance characteristics and expression characteristics of the user can be obtained, so that character node information and emotion node information can be further obtained.
In the implementation scenario, after the dialogue information is acquired, the dialogue information is analyzed through at least one of a speech emotion recognition algorithm, a semantic emotion recognition algorithm and an expression emotion recognition algorithm, and at least one piece of key node information is acquired. In other implementation scenarios, the information of at least one key node may also be obtained through a deep learning neural network.
S202: and predicting the predicted node information corresponding to the at least one key node information according to the psychological knowledge graph.
In a specific implementation scenario, the predicted node information corresponding to the at least one key node information acquired in step S201 is predicted according to the psychological knowledge graph. Specifically, the key node information acquired in step S201 corresponds to character node information, event node information, emotion node information, and cognitive node information. And finding out matched prediction node information in the psychological knowledge graph according to the corresponding character node information, event node information, emotion node information and cognitive node information, wherein in the implementation scene, the prediction node information is behavior node information.
In other implementation scenarios, it is also possible that the at least one piece of key node information corresponds to character node information, event node information, emotion node information, and behavior node information, and the prediction node information corresponds to cognitive node information. Specifically, the at least one key node information corresponds to at most four of character node information, event node information, emotion node information, cognitive node information, and behavior node information in the quintuple structure, and the predicted node information corresponds to the remaining at least one of the character node information, event node information, emotion node information, cognitive node information, and behavior node information in the quintuple structure.
In this implementation scenario, the person node information, the event node information, the emotion node information, and the cognitive node information corresponding to at least one piece of key node information can Be found in the psychological knowledge graph, for example, the person node information Pe1, the event node information Ev1, the emotion node information Em1, and the cognitive node information Co1 in fig. 1, and it can Be inferred that the predicted node information is the behavior node information Be 1.
In other implementation scenarios, the person node information, the event node information, the emotion node information, and the cognitive node information that completely match at least one key node information cannot Be found in the psychological knowledge graph, for example, partially match with the person node information Pe1 and partially match with the person node information Pe2, partially match with the emotion node information Em1 and partially match with the emotion node information Em2, and match with the event node information Ev1 and the cognitive node information Co1, it can Be inferred that the predicted node information is behavior node information, possibly part of behavior node information Be1, Be2, or Be1 and part of Be 2.
S203: and generating an intervention strategy according to the predicted node information.
In a specific implementation scenario, a corresponding intervention strategy is generated according to the predicted node information. For example, the predicted node information is behavior node information, and an intervention policy may be generated according to the predicted behavior node information. Specifically, the behavior node information is a depressed mood, insomnia, inappetence, etc., and this can be intervened, for example, to suggest that the user participates in a collective activity more, and exercises are appropriately performed.
The intervention strategy may be provided to the user or may be provided to the consultant for reference by the consultant.
In the implementation scenario, the psychological consulting ability of the consultant is mathematically modeled to form data for machine learning, for example, cases processed by the consultant and processing strategies are collated to obtain consulting processing information, and the consulting processing information is mathematically modeled to generate corresponding data. And training the neural network by using the data to obtain a pre-trained intervention neural network, inputting the predicted node information into the intervention neural network, and obtaining an intervention strategy matched with the predicted node information.
As can be seen from the above description, in this embodiment, at least one piece of key node information is obtained from the dialog information of the user, and the predicted node information corresponding to the at least one piece of key node information is predicted according to the psychological knowledge graph, so that the node information can be accurately predicted, the pertinence and the effectiveness of the intervention strategy are improved, and further, the intervention strategy is provided to the consultant, so that the work efficiency of the consultant can be effectively improved.
Referring to fig. 4, fig. 4 is a flowchart illustrating an embodiment of a method for acquiring information of at least one key node according to the present invention. The method for acquiring the information of at least one key node comprises the following steps:
s301: and acquiring dialogue information input by a user, acquiring slot information of the current key node information according to the dialogue information, and judging whether the slot information meets the information collection requirement of the current key node. If not, go to step S302, and if so, go to step S303.
In a specific implementation scenario, specific slot information is set for each key node information. For example, key node information corresponding to person node information is provided with slot information such as gender, character characteristics, personality characteristics, taste, physiological characteristics, appearance characteristics, and the like. And judging whether the slot information acquired according to the conversation information meets the information collection requirement of the current key node information, for example, if the current key node information is the key node information corresponding to the character node information, judging whether the slot information of the key node information is completely collected. In other implementation scenarios, the key node information may be used for matching the psychological knowledge graph only by collecting part of the slot information, so that it may be determined whether the slot information of the key node information is completely collected according to the information collection requirement of the current key node information.
S302: acquiring key information meeting the information collection requirement, and guiding a user to provide the key information through a preset psychological conversation technology.
In a specific implementation scenario, if the slot information does not satisfy the information collection requirement of the current key node, obtaining key information that satisfies the information collection requirement, for example, if the current key node information is key node information corresponding to character node information, and the key information that needs to be collected is a favorite, guiding the user to provide favorite key information through a preset psychological conversation technology.
Furthermore, a current conversation scene is obtained according to the conversation information, a preset psychological conversation technical model matched with the conversation scene is selected, the speed, tone and the like of the human-computer interaction are finely adjusted, and meanwhile, a voice synthesis module with high simulation human voice is introduced, so that a human feels that the robot has emotion in the conversation process, and the emotion of the user can be better pacified. For example, if the current conversation scene is a conversation scene in which the user is in excited emotion, the speech speed may be slowed down, and the user may perform human-computer interaction with soft speech to calm the emotion of the user.
Furthermore, emotion mining and/or event mining are carried out on the dialogue information, mining results are obtained, and emotion responses and/or content responses matched with the mining results are fed back to the user. For example, emotion mining and/or event mining can be performed through a preset algorithm, if the current emotion of the user is sad and the encountered event is campus overlord, the matched emotional response and/or content response can be used for encouraging and soothing the user in a gentle tone, and the effect of soothing the user is achieved.
S303: step S301 is executed with the next key node information as the current key node information.
In a specific implementation scenario, step S301 is executed with the next key node information as the current key node information until all slot information of the key node information is collected.
As can be seen from the above description, in this embodiment, key information meeting the information collection requirement is acquired according to the dialog information, a preset psychological conversation technology model matching the dialog scene is selected, the user is guided to provide the key information by the preset psychological conversation technology, emotion mining and/or event mining are performed on the dialog information, an emotion response and/or a content response matching the dialog information are fed back to the user, and the user can be better soothed while sufficient key information is acquired.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of a psychological intervention system according to the present invention. The psychological intervention system 10 provided by the invention comprises an acquisition module 11, a prediction module 12 and an intervention module 13.
The obtaining module 11 is configured to obtain session information input by a user, and obtain at least one piece of key node information according to the session information. The prediction module 12 is configured to predict predicted node information corresponding to the at least one key node information according to the psychological knowledge-graph. The intervention module 13 is configured to generate an intervention policy according to the predicted node information. The psychological knowledge map is composed of a plurality of five-element structures which are related with each other, and each five-element structure comprises character node information, and event node information, emotion node information, cognitive node information and behavior node information which are related with the character node information.
The obtaining module 11 is further configured to obtain slot information of the current key node according to the session information, and determine whether the slot information meets an information collection requirement of the current key node information; if the slot information does not meet the information collection requirement of the current key node information, acquiring key information meeting the information collection requirement; and guiding the user to provide key information through preset psychological conversation technology.
The obtaining module 11 is further configured to obtain a current conversation scene according to the conversation information, and select a preset psychology conversation technology model matching the conversation scene.
The obtaining module 11 is further configured to perform emotion mining and/or event mining on the dialog information, and feed back an emotional response and/or a content response matching the dialog information to the user.
The obtaining module 11 is further configured to obtain at least one piece of key node information through at least one of a speech emotion recognition algorithm, a semantic emotion recognition algorithm, and an expression emotion recognition algorithm.
At least one piece of key node information corresponds to at most four pieces of character node information, event node information, emotion node information, cognitive node information and behavior node information in a quintuple structure; the predicted node information corresponds to remaining at least one of character node information, event node information, emotion node information, cognitive node information, and behavior node information in the quintuple structure.
The psychological intervention system 10 further comprises a training module 14, wherein the training module 14 is configured to obtain training information and extract character node information in the training information; extracting event node information, emotion node information, cognitive node information and behavior node information which are associated with character node information; and constructing a quintuple structure of the character node information and event node information, emotion node information, cognitive node information and behavior node information which are associated with the character node information, and generating a psychological knowledge map according to the quintuple structure.
As can be seen from the above description, in this embodiment, the central management intervention system acquires at least one piece of key node information from the dialog information of the user, predicts the predicted node information corresponding to the at least one piece of key node information according to the psychological knowledge graph, can accurately predict the node information, improves the pertinence and the effectiveness of the intervention strategy, guides the user to provide the key information by using a preset psychological conversation technology, performs emotion mining and/or event mining on the dialog information, feeds back an emotion response and/or a content response matched with the dialog information to the user, and can obtain sufficient key information and feed back emotion and content of the user, thereby better placating the user.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a psychological intervention terminal according to an embodiment of the present invention. The prediction terminal 20 includes a processor 21 and a memory 22. The processor 21 is coupled to a memory 22. The memory 22 has stored therein a computer program which is executed by the processor 21 when in operation to implement the method as shown in fig. 2-4. The detailed methods can be referred to above and are not described herein.
As can be seen from the above description, in this embodiment, the central management intervention terminal acquires at least one piece of key node information from the dialog information of the user, predicts the predicted node information corresponding to the at least one piece of key node information according to the psychological knowledge graph, can accurately predict the node information, improves the pertinence and the effectiveness of the intervention strategy, guides the user to provide the key information by using a preset psychological conversation technology, performs emotion mining and/or event mining on the dialog information, feeds back an emotion response and/or a content response matched with the dialog information to the user, and can obtain sufficient key information and feed back emotion and content of the user, thereby better placating the user.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a storage medium according to an embodiment of the present invention. The storage medium 30 stores at least one computer program 31, and the computer program 31 is used for being executed by a processor to implement the method shown in fig. 2 to 4, and the detailed method can be referred to above and is not described herein again. In one embodiment, the computer readable storage medium 30 may be a memory chip in a terminal, a hard disk, or other readable and writable storage tool such as a removable hard disk, a flash disk, an optical disk, or the like, and may also be a server or the like.
As can be seen from the above description, the computer program in the storage medium in this embodiment may be configured to obtain at least one piece of key node information from the dialog information of the user, predict the predicted node information corresponding to the at least one piece of key node information according to the psychological knowledge graph, accurately predict the node information, improve the pertinence and the effectiveness of the intervention strategy, guide the user to provide the key information by using a preset psychological conversation technology, perform emotion mining and/or event mining on the dialog information, feed back an emotion response and/or a content response matching the dialog information to the user, obtain sufficient key information, feed back emotion and content of the user, and better sooth the user.
Different from the prior art, the method and the device have the advantages that the prediction node information corresponding to at least one key node information is predicted according to the psychological knowledge graph, accurate prediction can be performed by means of artificial intelligence, the intervention effectiveness is improved, the intervention strategy is generated according to the prediction node information, the working efficiency of a consultant can be effectively improved, the key information is guided to be provided for a user through the preset psychological conversation technology, emotion mining and/or event mining are performed on the conversation information, the emotion response and/or content response matched with the conversation information is fed back to the user, the emotion and content feedback can be given to the user while sufficient key information is obtained, and the user can be better soothed.
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 hardware related to instructions of a computer program, and the program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (8)
1. An interaction method based on artificial intelligence is characterized by comprising the following steps:
acquiring training information, and extracting one or more character node information in the training information, wherein the training information comprises diagnosis and treatment records, diagnosis and treatment audios and videos;
performing cognitive exploration on the training information by taking the character node information as a center, acquiring cognitive node information associated with the character node information, performing event inquiry, acquiring event node information associated with the character node information, performing behavior analysis, acquiring behavior node information associated with the character node information, performing emotion mining, and acquiring emotion node information associated with the character node information;
constructing a quintuple structure of the character node information and the event node information, the emotion node information, the cognitive node information and the behavior node information which are associated with the character node information, and generating a psychological knowledge graph according to the quintuple structure;
obtaining dialogue information input by a user, and obtaining at least one key node information according to the dialogue information;
predicting predicted node information corresponding to the at least one key node information according to the psychological knowledge graph;
generating an intervention strategy according to the prediction node information;
the at least one key node information corresponds to at most four of the character node information, the event node information, the emotion node information, the cognitive node information and the behavior node information in the quintuple structure;
the predicted node information corresponds to the remaining at least one of the character node information, the event node information, the emotion node information, the cognitive node information, and the behavior node information in the five-tuple structure.
2. The artificial intelligence based interaction method of claim 1, wherein the step of obtaining key node information according to the dialogue information comprises:
acquiring slot information of a current key node according to the conversation information, and judging whether the slot information meets the information collection requirement of the current key node information;
if the slot information does not meet the information collection requirement of the current key node information, acquiring key information meeting the information collection requirement;
and guiding the user to provide the key information through preset psychological conversation technology.
3. The artificial intelligence based interaction method according to claim 2, wherein the step of guiding the user to provide the key information through the preset psychologic conversation technology model comprises:
and acquiring a current conversation scene according to the conversation information, and selecting the preset psychological conversation technology model matched with the conversation scene.
4. The artificial intelligence based interaction method according to claim 2, wherein the step of guiding the user to provide the key information through the preset psychologic conversation technology model comprises:
and performing emotion mining and/or event mining on the dialogue information, and feeding back emotion response and/or content response matched with the dialogue information to a user.
5. The artificial intelligence based interaction method of claim 1, wherein the step of obtaining at least one key node information according to the dialogue information comprises:
and acquiring the at least one key node information through at least one of a speech emotion recognition algorithm, a semantic emotion recognition algorithm and an expression emotion recognition algorithm.
6. A psychological intervention system, comprising:
the training module is used for acquiring training information and extracting one or more character node information in the training information, wherein the training information comprises diagnosis and treatment records, diagnosis and treatment audios and videos; performing cognitive exploration on the training information by taking the character node information as a center, acquiring cognitive node information associated with the character node information, performing event inquiry, acquiring event node information associated with the character node information, performing behavior analysis, acquiring behavior node information associated with the character node information, performing emotion mining, and acquiring emotion node information associated with the character node information; constructing a quintuple structure of the character node information and the event node information, the emotion node information, the cognitive node information and the behavior node information which are associated with the character node information, and generating a psychological knowledge graph according to the quintuple structure;
the acquisition module is used for acquiring dialogue information input by a user and acquiring at least one key node information according to the dialogue information;
the prediction module is used for predicting the prediction node information corresponding to the at least one key node information according to the psychological knowledge graph;
the intervention module is used for generating an intervention strategy according to the prediction node information;
the at least one key node information corresponds to at most four of the character node information, the event node information, the emotion node information, the cognitive node information and the behavior node information in the quintuple structure;
the predicted node information corresponds to the remaining at least one of the character node information, the event node information, the emotion node information, the cognitive node information, and the behavior node information in the five-tuple structure.
7. A psychological intervention terminal, comprising: a processor coupled to the memory and a memory having a computer program stored therein, the processor executing the computer program to implement the method of any of claims 1-5.
8. A storage medium, characterized in that a computer program is stored, which computer program is executable by a processor to implement the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010929851.XA CN112214607B (en) | 2020-09-07 | 2020-09-07 | Interactive method, psychological intervention system, terminal and medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010929851.XA CN112214607B (en) | 2020-09-07 | 2020-09-07 | Interactive method, psychological intervention system, terminal and medium based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112214607A CN112214607A (en) | 2021-01-12 |
| CN112214607B true CN112214607B (en) | 2021-06-11 |
Family
ID=74049392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010929851.XA Active CN112214607B (en) | 2020-09-07 | 2020-09-07 | Interactive method, psychological intervention system, terminal and medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112214607B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112685645A (en) * | 2021-01-13 | 2021-04-20 | 敖客星云(北京)科技发展有限公司 | Intelligent education recommendation method, system, equipment and medium based on knowledge graph |
| CN113096773B (en) * | 2021-03-31 | 2022-06-21 | 上海暖禾临床心理诊所有限公司 | System and method for collecting and processing cognitive information |
| CN113792137B (en) * | 2021-08-26 | 2023-06-09 | 广东云徙智能科技有限公司 | Method, system, intelligent terminal and storage medium for searching middle-stage research and development materials |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN108345690A (en) * | 2018-03-09 | 2018-07-31 | 广州杰赛科技股份有限公司 | Intelligent answer method and system |
| 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 |
| CN110476169A (en) * | 2018-01-04 | 2019-11-19 | 微软技术许可有限责任公司 | Due emotional care is provided in a session |
| CN111581396A (en) * | 2020-05-06 | 2020-08-25 | 西安交通大学 | Event graph construction system and method based on multi-dimensional feature fusion and dependency syntax |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9805128B2 (en) * | 2015-02-18 | 2017-10-31 | Xerox Corporation | Methods and systems for predicting psychological types |
| CN106108921A (en) * | 2016-08-19 | 2016-11-16 | 北京中盛凯新科技发展有限公司 | A kind of psychosoma assessment and nursing and interfering system |
| US11551804B2 (en) * | 2017-05-11 | 2023-01-10 | Microsoft Technology Licensing, Llc | Assisting psychological cure in automated chatting |
| CN109960723B (en) * | 2019-04-12 | 2021-11-16 | 浙江连信科技有限公司 | Interaction system and method for psychological robot |
| CN110442700A (en) * | 2019-08-12 | 2019-11-12 | 珠海格力电器股份有限公司 | Man-machine more wheel dialogue methods and system, smart machine for human-computer interaction |
| CN110955764B (en) * | 2019-11-19 | 2021-04-06 | 百度在线网络技术（北京）有限公司 | Scene knowledge graph generation method, man-machine conversation method and related equipment |
| CN111430033A (en) * | 2020-03-24 | 2020-07-17 | 浙江连信科技有限公司 | Psychological assessment method based on human-computer interaction and electronic equipment |
| CN111564202B (en) * | 2020-04-30 | 2021-05-28 | 深圳市镜象科技有限公司 | Psychological counseling method based on man-machine conversation, psychological counseling terminal and storage medium |
-
2020
- 2020-09-07 CN CN202010929851.XA patent/CN112214607B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105068661A (en) * | 2015-09-07 | 2015-11-18 | 百度在线网络技术（北京）有限公司 | Man-machine interaction method and system based on artificial intelligence |
| CN107870994A (en) * | 2017-10-31 | 2018-04-03 | 北京光年无限科技有限公司 | Man-machine interaction method and system for intelligent robot |
| CN110476169A (en) * | 2018-01-04 | 2019-11-19 | 微软技术许可有限责任公司 | Due emotional care is provided in a session |
| CN108345690A (en) * | 2018-03-09 | 2018-07-31 | 广州杰赛科技股份有限公司 | Intelligent answer method and system |
| 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 |
| CN111581396A (en) * | 2020-05-06 | 2020-08-25 | 西安交通大学 | Event graph construction system and method based on multi-dimensional feature fusion and dependency syntax |
Non-Patent Citations (2)
| Title |
|---|
| A Practical Approach to Constructing a Knowledge Graph for Cybersecurity;Yan Jia 等;《Engineering》;20180209;第4卷(第1期);53-60 * |
| 时空叙事可视化理论与方法研究;王双;《中国博士学位论文全文数据库 基础科学辑》;20180615(第06期);A008-7 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112214607A (en) | 2021-01-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112214607B (en) | Interactive method, psychological intervention system, terminal and medium based on artificial intelligence | |
| US11226673B2 (en) | Affective interaction systems, devices, and methods based on affective computing user interface | |
| US10770062B2 (en) | Adjusting a ranking of information content of a software application based on feedback from a user | |
| JP2019159309A (en) | Method and apparatus for determining speech interaction satisfaction | |
| KR20190016653A (en) | System and method for providing intelligent counselling service | |
| US20180317840A1 (en) | Assessing adherence fidelity to behavioral interventions using interactivity and natural language processing | |
| Baur et al. | eXplainable cooperative machine learning with NOVA | |
| JP6804763B2 (en) | Dialogue system, dialogue device and computer program for it | |
| US20190295199A1 (en) | Intelligent legal simulator | |
| Yannakakis | Preference learning for affective modeling | |
| Shen et al. | Kwickchat: A multi-turn dialogue system for aac using context-aware sentence generation by bag-of-keywords | |
| CN112632252A (en) | Dialogue response method, dialogue response device, computer equipment and storage medium | |
| CN116796857A (en) | LLM model training method, device, equipment and storage medium thereof | |
| Rodellar‐Biarge et al. | Towards the search of detection in speech‐relevant features for stress | |
| CN110931002B (en) | Man-machine interaction method, device, computer equipment and storage medium | |
| JP5685014B2 (en) | Discussion soundness calculation device | |
| Rath et al. | Prediction of a Novel Rule-Based Chatbot Approach (RCA) using Natural Language Processing Techniques | |
| CN114267324A (en) | Voice generation method, device, equipment and storage medium | |
| KR102306953B1 (en) | Method of medical support based on voice recognition | |
| CN112905763A (en) | Session system development method, device, computer equipment and storage medium | |
| Carl | Empirical Translation Process Research: Past and Possible Future Perspectives | |
| CN108806716A (en) | For the matched method and apparatus of computerization based on emotion frame | |
| CN111783473A (en) | Method and device for identifying best answer in medical question and answer and computer equipment | |
| CN110543466B (en) | Intelligent robot data processing method and device based on character model | |
| KR20200141863A (en) | System for providing personal recording data based ai chatting service |
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 |