CN109346155B - Emotion stimulation tree generation method and emotion soothing system based on cloud model - Google Patents

Emotion stimulation tree generation method and emotion soothing system based on cloud model Download PDF

Info

Publication number
CN109346155B
CN109346155B CN201811293327.7A CN201811293327A CN109346155B CN 109346155 B CN109346155 B CN 109346155B CN 201811293327 A CN201811293327 A CN 201811293327A CN 109346155 B CN109346155 B CN 109346155B
Authority
CN
China
Prior art keywords
soothing
emotion
tree
instances
cloud
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
Application number
CN201811293327.7A
Other languages
Chinese (zh)
Other versions
CN109346155A (en
Inventor
杨志晓
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Henan University of Animal Husbandry and Economy
Original Assignee
Henan University of Animal Husbandry and Economy
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Henan University of Animal Husbandry and Economy filed Critical Henan University of Animal Husbandry and Economy
Priority to CN201811293327.7A priority Critical patent/CN109346155B/en
Publication of CN109346155A publication Critical patent/CN109346155A/en
Application granted granted Critical
Publication of CN109346155B publication Critical patent/CN109346155B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • 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
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • 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
    • G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
    • 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
    • G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
    • A61M2021/0027—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the hearing sense
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
    • A61M2021/0044—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M21/00—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis
    • A61M2021/0005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus
    • A61M2021/0044—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense
    • A61M2021/005—Other devices or methods to cause a change in the state of consciousness; Devices for producing or ending sleep by mechanical, optical, or acoustical means, e.g. for hypnosis by the use of a particular sense, or stimulus by the sight sense images, e.g. video

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Psychology (AREA)
  • Acoustics & Sound (AREA)
  • Veterinary Medicine (AREA)
  • Anesthesiology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Hematology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Physics & Mathematics (AREA)
  • Child & Adolescent Psychology (AREA)
  • Developmental Disabilities (AREA)
  • Hospice & Palliative Care (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Manipulator (AREA)

Abstract

The invention discloses an emotional stimulation tree generation method and an emotion soothing system based on a cloud model, which are different from a current single-point type interactive method of 'emotional state → feedback emotion' and a fixed rigid space-time structure interactive model. And automatically generating a stimulus tree with uncertain space-time structure for a certain negative emotional state. The stimulus tree is ordered by a series of soothing examples in terms of time and space. This structured soothing model meets the progressive and multi-initiative co-ordination requirements of negative emotion soothing. The stimulus tree has dynamic variations and uncertainties in time, space, and soothing instances, which can reduce the soothing "fatigue" that can result from structural and instance repeatability.

Description

Emotion stimulation tree generation method and emotion soothing system based on cloud model
Technical Field
The invention belongs to the technical field of automatic emotion soothing, man-machine emotion interaction, emotion calculation, man-machine interaction and uncertain artificial intelligence, and particularly relates to an emotion stimulation tree generation method and an emotion soothing system based on a cloud model.
Background
Modern fast-paced working modes, workplace competition pressure, diseases, natural disasters and accidents often bring negative emotions of depression, sadness, solitary and the like to the parties, and the physical and psychological health of the parties is threatened. If proper intervention is not performed in time, negative emotion of audiences can be aggravated, psychological and physiological diseases are caused, and even social problems are caused.
Initially, people used manual intervention for psychological soothing. Such as psychological health consultation and psychological soothing after shaking. However, the manual method has disadvantages such as lag, low efficiency, and narrow feeling. In recent years, researchers have proposed an automatic emotion soothing technology, and applied modern scientific technology and equipment to recognize negative emotions of the audience as early as possible, and perform psychological intervention on the negative emotions of the audience in various modes such as text, voice, music, color, video, action and the like at proper time. Automated emotion soothing is expected to become a beneficial technical means for timely discovering and processing negative emotions and relieving the mental health of the audience.
Psychological soothing of a person in negative emotional states such as sadness, loneliness, etc. is a complex psychological process. Negative emotion soothing needs to be gradual, multiple actions are needed, and the negative emotion soothing has obvious space-time structural characteristics. In addition, different people have certain similarity to the emotional stimulus spatial-temporal structure such as the type, duration, sequence, number of the concurrently applied emotional stimuli and the like, but the difference exists. Even for the same person, if multiple emotional soothing needs to be performed, repeated emotional stimuli spatiotemporal structure may weaken the emotional soothing effect, causing so-called "soothing fatigue".
Therefore, a negative emotion soothing interaction model which is similar to a certain extent and has an uncertain space-time structure is researched, an emotion stimulation tree with a diversity space-time structure is generated, emotion soothing interaction is carried out, and the automatic emotion soothing effect is expected to be improved. This is a considerable problem to study.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a normal cloud model-based emotional stimulation tree which is expected and has uncertain and diversified spatio-temporal structures and a negative emotion soothing interaction system, so that the weakening of a soothing effect possibly brought by the emotional stimulation tree with the uncertain structure is avoided, and the automatic emotion soothing effect is improved.
The object of the invention is achieved in the following way:
a cloud model-based emotional stimulation tree generation method comprises the following steps:
step 1, setting digital characteristic values of various parameters of a cloud model of a stimulation tree, comprising the following steps: total number of administered clouds CI(ExI,EnI,HeI) The range of values DI, t of the total number of executions I is soothingiSoothing time cloud C implemented△ti(Ex△ti, En△ti,He△ti)，△tiValue range D Δ t ofi，tiNumber of soothing instances cloud C implemented in parallelNi(ExNi,EnNi,HeNi)， NiValue field DN ofiWherein ExI,EnI,HeIPeriods of respectively IWang, entropy and super entropy, Ex△ti,En△ti,He△tiRespectively is DeltatiExpectation, entropy and super entropy of (Ex)△ti,En△ti,He△ti) Are respectively NiDesired, entropy and super entropy, I ═ 1,2, …, I;
step 2, carrying out total times of cloud C for soothingI(ExI,EnI,HeI) I is generated as follows:
EnI’～N(EnI,HeI 2)，
I～N(ExI,EnI’2)，
rounding off I, and if I is less than 1, making I equal to 1; if I is larger than the upper limit of DI, making I equal to the upper limit of DI;
cloud to soothing time C△ti(Ex△ti,En△ti,He△ti) Δ t was generated for I ═ 1,2, …, I, respectively, by the following methodi：
En△ti’～N(En△ti,He△ti 2)，
△ti～N(Ex△ti,En△ti’2)，
If Δ tiLess than D Δ tiLower limit of (1), let Δ tiEqual to D Δ tiThe lower limit of (d); if Δ tiGreater than D Δ tiUpper limit of (1), let Δ tiEqual to D Δ tiThe upper limit of (d);
soothing instance number cloud C for parallel implementationNi(ExNi,EnNi,HeNi) N was generated by the following method for I ═ 1,2, …, I, respectivelyi：
EnNi’～N(EnNi,HeNi 2)，
Ni～N(ExNi,EnNi’2)，
NiRounded by rounding, and if Ni<1, order N i1 is ═ 1; if N is presentiGreater than DNiUpper limit of (1), let NiIs equal to DNiThe upper limit of (d);
step 3, recording the category number of the soothing resources as NCClass label is Ck(k＝1,2,…,NC) At time node ti(I-1, 2, …, I), randomly picking NiIndividual categories (allowing a category to be repeatedly selected), denoted Cj(j＝1,2,…, Ni) To class CjRandomly choosing a soothing instance, denoted as EijTo obtain NiA soothing example Eij(j＝1,2,…, Ni) (ii) a At Δ tiIn parallel, N is implementediA soothing example Eij(ii) a Repeating the step for I-1, 2, …, I to obtain the spatial-temporal structure emotional stimulus tree.
An emotional stimulus tree based on a cloud model, wherein the soothing intensity is embodied by the number of soothing instances implemented in parallel; the greater the number of concurrent soothing instances, the greater the soothing intensity; otherwise, the weaker the result is; parallel refers to implementing more than two (including two) soothing instances simultaneously over a certain period of time; multiple soothing instances implemented in parallel are referred to as a group of soothing instances;
along the time axis, the time node of the 1 st implementation of the soothing instance (group) is denoted t1Time node of 2 nd implementation of soothing instance (group) is denoted t2By analogy, the time node of the ith implementation of the soothing instance (group) is denoted tiAt most, I soothing instances (groups) were performed, with the I time node noted tI；
Note the soothing time of the ith implementation as Δ tiThen there is
ti+1＝ti+△ti(i＝1,2,…,I-1)
Where Δ tiIn minutes, total soothing time T
T＝∑I i＝1△ti
The number of soothing examples of the ith implementation is Ni(Ni1) the soothing example is noted as Eij(j＝1,2,…,Ni) Obtaining a spatiotemporal structure emotion soothing model; because of its tree-like structure, it can also be called a spatio-temporal structure emotion soothing tree, or a stimulus tree; each soothing instance is locatedThe location is called a leaf node, or simply a leaf.
An emotion soothing system of an emotion stimulation tree based on a cloud model comprises a negative emotion extraction module, an emotion soothing cloud center connected with the negative emotion extraction module, and an emotion soothing implementation module connected with the emotion soothing cloud center;
the negative emotion extraction module is responsible for extracting emotion state information of the user and outputting the identified negative emotion state to the emotion soothing cloud center;
the emotion soothing cloud center is responsible for receiving the negative emotion state output by the negative emotion extraction module, matching the negative emotion state with an emotion soothing strategy with an uncertain space-time structure, generating an emotion stimulation tree example with the uncertain space-time structure based on a normal cloud model method, and outputting the emotion stimulation tree example to the emotion soothing implementation module;
the emotion soothing implementation module is responsible for receiving and implementing instances of the spatiotemporal structured emotional stimulus tree from the cloud center, implementing emotion soothing for the user.
The user emotional state information extracted by the negative emotion extraction module comprises facial expressions, characters and physiological signals.
The emotion soothing cloud center comprises an emotion soothing resource group, an uncertain spatiotemporal structure emotion soothing strategy and an uncertain spatiotemporal structure emotion stimulation tree generation method submodule.
The soothing resources are organized in categories including text, pictures, voice, video and limb movements; each soothing resource category contains a number of soothing instances, each of which is one specific embodiment that can be used for emotional soothing; the emotion-soothing repository is responsible for collecting, organizing, storing, and updating emotion-soothing instances.
The terminal equipment for implementing emotion soothing by the emotion soothing implementation module comprises: the intelligent mobile phone comprises a smart phone, a tablet personal computer, a smart television, an intelligent sound box, an intelligent lamp, emotion interaction equipment and an emotion interaction robot.
The emotion soothing implementation module implements emotion soothing in a manner that comprises: pushing characters, playing voice, playing video, adjusting light color and implementing limb actions.
And the emotion soothing implementation module implements the soothing examples at each time point one by one according to the emotion stimulation tree examples, and performs emotion soothing on the user.
A computer-readable storage medium, in which a computer program is stored which is adapted to be executed by a processor, and which, when executed by the processor, carries out the steps of a cloud model-based affective stimulus tree generation method.
The invention has the beneficial effects that: different from the current single-point interactive method of 'emotional state → feedback emotion' and a fixed rigid space-time structure interactive model, the invention adopts the interactive method of 'emotional state → uncertainty space-time structure soothing resource group based on cloud model'. And automatically generating a stimulus tree with uncertain space-time structure for a certain negative emotional state. The stimulus tree is ordered by a series of soothing examples in terms of time and space. This structured soothing model meets the progressive and multi-initiative co-ordination requirements of negative emotion soothing. The stimulus tree has dynamic variations and uncertainties in time, space, and soothing instances, which can reduce the soothing "fatigue" that can result from structural and instance repeatability.
Drawings
FIG. 1 is a schematic diagram of an emotion soothing system;
FIG. 2 is a schematic illustration of a soothing resource category and a soothing example organization;
FIG. 3 is a total number of clouds for a soothing implementation;
FIG. 4 is a cloud example of soothing time;
FIG. 5 is a soothing example number cloud case implemented in parallel;
FIG. 6 shows an example of a spatiotemporal structure emotional stimuli tree 1;
FIG. 7 shows an example of spatiotemporal structure emotional stimuli tree 2.
Detailed Description
The invention is further described with reference to the following drawings and specific embodiments:
an emotion soothing system of an emotion stimulation tree based on a cloud model is shown in fig. 1 and comprises a negative emotion extraction module, an emotion soothing cloud center connected with the negative emotion extraction module and an emotion soothing implementation module connected with the emotion soothing cloud center.
The negative emotion extraction module is responsible for extracting information of the user, including facial expressions, characters and physiological signals, identifying the negative emotion state of the user, and outputting the negative emotion state to the emotion soothing cloud center.
The emotion soothing cloud center comprises an emotion soothing resource group, an emotion soothing strategy and a space-time emotion stimulation tree generation submodule based on a normal cloud model; and the cloud center receives the negative emotion state output by the negative emotion extraction module, matches the negative emotion state with an emotion soothing strategy with an uncertain spatiotemporal structure, and generates and outputs an emotion stimulation tree example with the uncertain spatiotemporal structure.
As shown in fig. 2, the soothing resources are organized in categories, including color, text, pictures, voice, video, and limb movements; each soothing resource category contains a number of soothing instances, each of which is one specific embodiment that can be used for emotional soothing; the emotion-soothing repository is responsible for collecting, organizing, storing, and updating emotion-soothing instances.
The emotion soothing strategy is as follows: the intensity of the soothing is reflected in the number of soothing instances implemented in parallel; the greater the number of concurrent soothing instances, the greater the soothing intensity; otherwise, the weaker the result is; parallel refers to implementing more than two (including two) soothing instances simultaneously over a certain period of time. Multiple soothing instances implemented in parallel are referred to as a group of soothing instances;
along the time axis, the time node of the 1 st implementation of the soothing instance (group) is denoted t1Time node of 2 nd implementation of soothing instance (group) is denoted t2By analogy, the time node of the ith implementation of the soothing instance (group) is denoted tiAt most, I soothing instances (groups) were performed, with the I time node noted tI；
Note the soothing time of the ith implementation as Δ tiThen there is
ti+1＝ti+△ti(i＝1,2,…,I-1)
Where Δ tiIn minutes, total soothing time T
T＝∑I i＝1△ti
The number of soothing examples of the ith implementation is Ni(Ni1) the soothing example is noted as Eij(j＝1,2,…,Ni) A spatiotemporal structure emotion-soothing model can be obtained. Because of its tree-like structure, it may also be referred to as a spatio-temporal structure emotion-soothing tree, or stimulus tree, herein simply referred to as stimulus tree; the position of each soothing instance is called a leaf node or leaf for short;
the shape of the order is x-N (Ex, En)2) The expression (x) indicates that x follows a normal distribution with Ex as expected and En as standard deviation.
The emotional stimulation tree generation method based on the cloud model comprises the following steps:
step 1, setting digital characteristic values of various parameters of a cloud model of a stimulation tree, comprising the following steps: total number of administered clouds CI(ExI＝5,EnI＝1,HeI0.2), the range of values DI of the total number of executions I is {1,2,3,4,5,6,7,8}, tiSoothing time cloud C implemented△ti(Ex△ti＝30,En△ti＝5,He△ti＝1)，tiSoothing time Δ t of treatmentiValue range D Δ t ofi＝[10,60]，tiNumber of soothing instances cloud C implemented in parallelNi(ExNi＝3,EnNi＝0.5, HeNi＝0.1)，NiValue field DN ofi1,2,3,4,5, wherein ExI,EnI,HeIExpectation, entropy and super-entropy, Ex, of I, respectively△ti,En△ti,He△tiRespectively is DeltatiExpectation, entropy and super entropy of (Ex)△ti,En△ti,He△ti) Are respectively NiDesired, entropy and super entropy, I ═ 1,2, …, I;
step 2, carrying out total times of cloud C for soothingI(ExI＝5,EnI＝1,HeI0.2), I was generated as follows:
EnI’～N(1,0.22)，
I～N(5,EnI’2)，
rounding off I, and if I is less than 1, making I equal to 1; if I is greater than the upper limit 8 of DI, let I equal the upper limit 8 of DI;
cloud to soothing time C△ti(Ex△ti＝30,En△ti＝5,He△ti1), Δ t is generated for I1, 2, …, I, respectively, according to the following methodi：
En△ti’～N(5,12)，
△ti～N(30,En△ti’2)，
If Δ tiLess than D Δ tiLower limit of 10, let Δ tiEqual to D Δ tiThe lower limit of (3) 10; if Δ tiGreater than D Δ tiUpper limit of 60, let Δ tiEqual to D Δ tiThe upper limit of (5) 60;
soothing instance number cloud C for parallel implementationNi(ExNi＝3,EnNi＝0.5,HeNi0.1), N was generated for I1, 2, …, I, respectively, according to the following methodi：
EnNi’～N(0.5,0.12)，
Ni～N(3,EnNi’2)，
NiRounded by rounding, and if Ni<1, order N i1 is ═ 1; if N is presentiGreater than DNiUpper limit of 5, let NiIs equal to DNiThe upper limit of (5);
step 3, recording the category number of the soothing resources as NCClass label is Ck(k＝1,2,…,NC) At time node ti(I-1, 2, …, I), randomly picking NiIndividual categories (allowing a category to be repeatedly selected), denoted Cj(j＝1,2,…, Ni) To class CjRandomly choosing a soothing instance, denoted as EijTo obtain NiA soothing example Eij(j＝1,2,…, Ni) (ii) a At Δ tiIn parallel, N is implementediA soothing example Eij(ii) a Repeating the step for I-1, 2, …, I to obtain the spatial-temporal structure emotional stimulus tree.
The method for generating the spatiotemporal emotional stimulation tree based on the normal cloud model is repeated for 1000 times, the obtained I value and the times are shown in the following table 1,
value of I 1 2 3 4 5 6 7 8
Number of times of obtaining I value 0 12 48 227 396 252 54 11
It should be noted that the number of times the value of I is obtained in the table may be slightly different for different runs.
The total number of administered soothing clouds made up of the 1000 cloud droplets (I values achieved) is shown in fig. 3, where the horizontal axis represents the total number of administered soothing I and the vertical axis represents the certainty μ of the cloud droplet I.
For any normal cloud model C (Ex, En, He), the certainty μ of cloud droplet x reveals that cloud droplet x can represent the degree to which the cloud model expects Ex, and μ is a random number with a tendency to stabilize, and is calculated according to the following formula:
En’～N(En,He2) En' is a random realization value of En obtained according to a normal distribution,
Figure BDA0001849800990000071
the certainty μ of a cloud droplet x is understood as the probability that the cloud model takes the value of x, but this probability is a random number with a tendency to stabilize, which is expected to be the value taken when the superentropy He is 0.
Table 1 illustrates that the total number of soothing implements I is the total number of soothing implements cloud CI(ExI＝5,EnI＝1,HeI0.2), the number of times 1 is obtained is 0, with the maximum probability of 5, then 6, 4, 7, 3, 2, 8, respectively, thereby realizing uncertainty generation of the total number of soothing executions I.
The total number of cloud numerical characteristic values of the soothing implementation can be changed to obtain I values with various desired uncertainty characteristics.
In this embodiment, the same time cloud-soothing numerical characteristic C is used for any I, i.e., I is 1,2, …, I△ti(Ex△ti＝30,En△ti＝5,He△ti1) and therefore they have the same uncertainty characteristics, without distinguishing the value of i, the soothing time cloud being shown in figure 4, in which the horizontal axis represents the cloud drop generated, i.e. the soothing time Δ t to be carried outiThe vertical axis represents the certainty of cloud droplets, and it can be seen that the generated soothing time also has no effectCertainty.
The value of the time-soothing cloud digital feature can be changed, or the time-soothing cloud digital feature C at different i can be changed△ti(Ex△ti,En△ti,He△ti) With different values, obtaining Δ t with various desired uncertainty characteristicsiThe value is obtained.
In this embodiment, for the number of pacifying instances cloud implemented in parallel, the same numerical feature value C is used for I ═ 1,2, …, I respectivelyNi(ExNi＝3,EnNi＝0.5,HeNi0.1) and therefore they have the same uncertainty characteristics, do not distinguish between the values of i, repeat 1000 times, and obtain NiThe values and times thereof are shown in table 2 below,
Nivalue of 1 2 3 4 5
Obtaining NiNumber of values 6 141 703 146 4
Note that N is obtained from the above table for different runsiThe number of values may be slightly different.
The generated cloud of the number of soothing instances is shown in fig. 5, in which the horizontal axis represents the generated cloud droplets, i.e. the number of soothing instances N to be implemented in paralleliAnd the vertical axis represents the certainty of cloud droplets, it can be seen that there is also uncertainty in the number of soothing instances generated for parallel implementation.
The values of the number of concurrently implemented soothing instances cloud digital features may be changed or the number of concurrently implemented soothing instances cloud digital features C at different i may be leftNi(ExNi,EnNi,HeNi) With different values, obtaining a number N of soothing instances of parallel implementation with various required uncertainty characteristicsi。
A spatio-temporal structure stimulus tree parameter generated by applying the method: i-5. N1＝3.N2＝3.N3＝4.N4＝3. N5＝2.△t1＝31.△t2＝29.△t3＝32.△t4＝28.△t5An example spatiotemporal structure emotional stimuli tree is shown in fig. 6.
Another spatio-temporal structure stimulus tree parameter generated using the above method: 4. N. I ═ 4.N1＝3.N2＝2.N3＝3. N4＝3.△t1＝28.△t2＝30.△t3＝32.△t4An example of a spatiotemporal structural emotional stimuli tree is shown in fig. 7.
An uncertain space-time structure emotional stimulation tree generation method based on a normal cloud model and an emotion soothing interaction system are characterized in that: the following time characteristics are provided: 1) the overall soothing process consists of I time periods, and the value of I is random and is a random positive integer conforming to normal distribution; 2) time length Δ t of each time segmenti(I ═ 1,2, …, I) is random and is a random number that fits a normal distribution; 3) the overall soothing time T is dynamically changing;
has the following spatial characteristics: 1) number of soothing instances N for a certain time nodeiRandom numbers are random numbers that conform to a normal distribution; 2) at a certain timeThe selected soothing resource categories of the nodes are not fixed and invariable; 4) the selected soothing instances are not necessarily the same for the same category of soothing resources.
The emotion-soothing cloud center of the uncertain spatiotemporal structure emotion stimulus tree pushes the generated stimulus tree instances to the emotion-soothing implementation module.
The emotion soothing implementation module receives and is responsible for implementing a space-time structured emotion stimulation tree example from a cloud center and implementing emotion soothing for a user; implementing the soothing examples of each time point one by one according to the emotional stimulation tree examples, and performing emotional soothing on the user; implementing an emotional stimulation tree example through terminal equipment including a smart phone, a tablet computer, a smart television, a smart sound, a smart lamp, emotional interaction equipment and an emotional interaction robot; the implementation mode comprises the steps of pushing characters, playing voice, playing video, adjusting light color, implementing limb actions and the like.
The variable space-time structure stimulation tree reduces the soothing fatigue caused by repeatability of the variable type of leaf nodes, the variable instance of the leaf nodes, the variable number of the soothing instances implemented each time, the variable length of the soothing time implemented each time and other uncertainties and diversity, and improves the soothing effect.
Different from the current 'single-point' type interactive method of 'emotional state → feedback emotion' and a fixed rigid space-time structure interactive model, the invention adopts the interactive method of 'emotional state → uncertain space-time structure soothing resource group'. And automatically generating a stimulus tree with uncertain space-time structure for a certain negative emotional state. The stimulus tree is ordered by a series of soothing examples in terms of time and space. This structured soothing model meets the progressive and multi-initiative co-ordination requirements of negative emotion soothing. The stimulus tree has dynamic variations and uncertainties in time, space, and soothing instances, which can reduce the soothing "fatigue" that can result from structural and instance repeatability.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various changes and modifications can be made without departing from the overall concept of the present invention, and these should also be considered as the protection scope of the present invention.

Claims (10)

1. A cloud model-based emotional stimulation tree generation method is characterized by comprising the following steps: the method comprises the following steps:
step 1, setting digital characteristic values of various parameters of a cloud model of a stimulation tree, comprising the following steps: total number of administered clouds CI(ExI,EnI,HeI) Value range DI for the total number of executions I, time node t for the ith execution of the soothing instance or group of soothing instancesiSoothing time cloud C implemented△ti(Ex△ti,En△ti,He△ti) Soothing time Δ t of the ith implementationiValue range D Δ t ofiTime node t of the ith implementation of the soothing instance or group of soothing instancesiNumber of soothing instances cloud C implemented in parallelNi(ExNi,EnNi,HeNi) Number of soothing instances N of the ith implementationiValue field DN ofiWherein ExI,EnI,HeIExpectation, entropy and super-entropy, Ex, of I, respectively△ti,En △ti,He△tiRespectively is DeltatiExpectation, entropy and super entropy of (Ex)△ti,En△ti,He△ti) Are respectively NiDesired, entropy and super entropy, I ═ 1,2, …, I;
step 2, carrying out total times of cloud C for soothingI(ExI,EnI,HeI) I is generated as follows:
Figure FDA0003422259080000011
I～N(ExI,EnI’2)，
rounding off I, and if I is less than 1, making I equal to 1; if I is larger than the upper limit of DI, making I equal to the upper limit of DI;
cloud to soothing time C△ti(Ex△ti,En△ti,He△ti) Each of which is equal to i1,2, …, I, producing Δ t according to the following methodi：
Figure FDA0003422259080000012
△ti～N(Ex△ti,En△ti’2)，
If Δ tiLess than D Δ tiLower limit of (1), let Δ tiEqual to D Δ tiThe lower limit of (d); if Δ tiGreater than D Δ tiUpper limit of (1), let Δ tiEqual to D Δ tiThe upper limit of (d);
soothing instance number cloud C for parallel implementationNi(ExNi,EnNi,HeNi) N was generated by the following method for I ═ 1,2, …, I, respectivelyi：
Figure FDA0003422259080000013
Ni～N(ExNi,EnNi’2)，
NiRounded by rounding, and if Ni<1, order Ni1 is ═ 1; if N is presentiGreater than DNiUpper limit of (1), let NiIs equal to DNiThe upper limit of (d);
step 3, recording the category number of the soothing resources as NCClass label is Ck(k＝1,2,…,NC) At time node ti(I-1, 2, …, I), randomly picking NiA category, allowing the category to be selected repeatedly, denoted as Cj(j＝1,2,…,Ni) For class CjRandomly choosing a soothing instance, denoted as EijTo obtain NiA soothing example Eij(j＝1,2,…,Ni) (ii) a At Δ tiIn parallel, N is implementediA soothing example Eij(ii) a Repeating the step for I-1, 2, …, I to obtain the spatial-temporal structure emotional stimulus tree.
2. The cloud model-based emotional stimulus tree generation method of claim 1, wherein:
the intensity of the soothing is reflected in the number of soothing instances implemented in parallel; the greater the number of concurrent soothing instances, the greater the soothing intensity; otherwise, the weaker the result is; parallel means that more than two soothing instances are implemented simultaneously over a certain period of time; multiple soothing instances implemented in parallel are referred to as a group of soothing instances;
along the time axis, the time node of the 1 st implementation soothing instance or group of soothing instances is denoted t1The time node of the 2 nd implementation of the soothing instance or group of soothing instances is denoted t2By analogy, the time node at which the soothing instance or group of soothing instances is implemented for the ith time is denoted tiAt most, I soothing instances or groups of soothing instances are implemented, with the I time node denoted as tI；
Note the soothing time of the ith implementation as Δ tiThen there is
ti+1＝ti+△ti(i＝1,2,…,I-1)，
Where Δ tiIn minutes, total soothing time T
T＝∑I i＝1△ti，
The number of soothing examples of the ith implementation is Ni(Ni1) and its soothing example is marked as Eij(j＝1,2,…,Ni) Obtaining a spatial-temporal structure emotion soothing model; because of its tree-like structure, it can also be called a spatio-temporal structure emotion soothing tree, or a stimulus tree; the location of each soothing instance is referred to as a leaf node, or simply leaf.
3. An emotion soothing system based on the cloud model emotional stimulus tree of the method of claim 1, wherein:
the negative emotion extraction module, the emotion soothing cloud center connected with the negative emotion extraction module and the emotion soothing implementation module connected with the emotion soothing cloud center are formed;
the negative emotion extraction module is responsible for extracting emotion state information of the user and outputting the identified negative emotion state to the emotion soothing cloud center;
the emotion soothing cloud center is responsible for receiving the negative emotion state output by the negative emotion extraction module, matching the negative emotion state with an emotion soothing strategy with an uncertain space-time structure, generating an emotion stimulation tree example with the uncertain space-time structure based on a normal cloud model method, and outputting the emotion stimulation tree example to the emotion soothing implementation module;
the emotion soothing implementation module is responsible for receiving and implementing instances of the spatiotemporal structured emotional stimulus tree from the cloud center, implementing emotion soothing for the user.
4. An emotion soothing system for a cloud model based emotional stimulus tree of claim 3, wherein: the user emotional state information extracted by the negative emotion extraction module comprises facial expressions, characters and physiological signals.
5. An emotion soothing system for a cloud model based emotional stimulus tree of claim 3, wherein: the emotion soothing cloud center comprises an emotion soothing resource group, an uncertain spatiotemporal structure emotion soothing strategy and an uncertain spatiotemporal structure emotion stimulation tree generation method submodule.
6. An emotion soothing system for a cloud model based emotional stimulus tree of claim 3, wherein: the soothing resources are organized in categories including text, pictures, voice, video and limb movements; each soothing resource category contains a number of soothing instances, each of which is one specific embodiment that can be used for emotional soothing; the emotion-soothing repository is responsible for collecting, organizing, storing, and updating emotion-soothing instances.
7. An emotion soothing system for a cloud model based emotional stimulus tree of claim 3, wherein: the terminal equipment for implementing emotion soothing by the emotion soothing implementation module comprises: the intelligent mobile phone comprises a smart phone, a tablet personal computer, a smart television, an intelligent sound box, an intelligent lamp, emotion interaction equipment and an emotion interaction robot.
8. An emotion soothing system for a cloud model based emotional stimulus tree of claim 3, wherein: the emotion soothing implementation module implements emotion soothing in a manner that comprises: pushing characters, playing voice, playing video, adjusting light color and implementing limb actions.
9. An emotion soothing system for a cloud model based emotional stimulus tree as claimed in any of claims 3 to 8, wherein: and the emotion soothing implementation module implements the soothing examples at each time point one by one according to the emotion stimulation tree examples, and performs emotion soothing on the user.
10. A computer-readable storage medium characterized by: the computer-readable storage medium has stored thereon a computer program which is executable by a processor, and which, when being executed by the processor, carries out the steps of the method according to any one of claims 1-2.
CN201811293327.7A 2018-10-31 2018-10-31 Emotion stimulation tree generation method and emotion soothing system based on cloud model Active CN109346155B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811293327.7A CN109346155B (en) 2018-10-31 2018-10-31 Emotion stimulation tree generation method and emotion soothing system based on cloud model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811293327.7A CN109346155B (en) 2018-10-31 2018-10-31 Emotion stimulation tree generation method and emotion soothing system based on cloud model

Publications (2)

Publication Number Publication Date
CN109346155A CN109346155A (en) 2019-02-15
CN109346155B true CN109346155B (en) 2022-03-11

Family

ID=65313221

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811293327.7A Active CN109346155B (en) 2018-10-31 2018-10-31 Emotion stimulation tree generation method and emotion soothing system based on cloud model

Country Status (1)

Country Link
CN (1) CN109346155B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101692261A (en) * 2009-09-02 2010-04-07 北京科技大学 Individualized emotion model applied to child user playmate robot and application method thereof
CN103116646A (en) * 2013-02-26 2013-05-22 浙江大学 Cloud gene expression programming based music emotion recognition method

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN205686296U (en) * 2016-06-22 2016-11-16 山西省交通科学研究院 A kind of device alleviating driver's emotion elevator motor-car driving safety
CN106682386A (en) * 2016-11-02 2017-05-17 河南工业大学 Space-time structured emotional soothing tree and its generation method and emotional soothing interaction system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101692261A (en) * 2009-09-02 2010-04-07 北京科技大学 Individualized emotion model applied to child user playmate robot and application method thereof
CN103116646A (en) * 2013-02-26 2013-05-22 浙江大学 Cloud gene expression programming based music emotion recognition method

Also Published As

Publication number Publication date
CN109346155A (en) 2019-02-15

Similar Documents

Publication Publication Date Title
Sarkar et al. Self-supervised learning for ecg-based emotion recognition
Mahon Posthumanism: A guide for the perplexed
Naser et al. Recognition of emotions induced by music videos using DT-CWPT
CN109789550A (en) Control based on the social robot that the previous role in novel or performance describes
Sun et al. Creative segment: a descriptive theory applied to computer-aided sketching
CN109766845B (en) Electroencephalogram signal classification method, device, equipment and medium
Bozhkov et al. EEG-based subject independent affective computing models
Teo et al. Classification of affective states via EEG and deep learning
Gatt et al. Face2text: Collecting an annotated image description corpus for the generation of rich face descriptions
Jordan et al. After nature: on bodies, consciousness, and causality
Petrantonakis et al. EEG-based emotion recognition using hybrid filtering and higher order crossings
CN109346155B (en) Emotion stimulation tree generation method and emotion soothing system based on cloud model
Stajić et al. Emotion recognition based on deap database physiological signals
Praveen et al. Recursive joint attention for audio-visual fusion in regression based emotion recognition
Fatima et al. Gender recognition using EEG during mobile game play
CN106682386A (en) Space-time structured emotional soothing tree and its generation method and emotional soothing interaction system
Colin et al. Reinforcement learning and insight in the artificial pigeon
Nicolas-Alonso et al. Ensemble learning for classification of motor imagery tasks in multiclass brain computer interfaces
CN109411076A (en) A kind of emotion with preference consoles tree generation method and its emotion interactive system
Markova et al. Automated recognition of affect and stress evoked by audio-visual stimuli
Tavakolian et al. Selecting better EEG channels for classification of mental tasks
CN104461016B (en) The machine personality technique of expression and device of product
CN111582489B (en) Distributed deployment decision-making system and method of ultrasonic artificial intelligent model
Haider et al. Issues and challenges in designing P300 and SSVEP paradigms
CN109411077A (en) A kind of uncertain space-time structure emotion consoles tree generation method and emotion consoles system

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