CN113934942A - Recommendation method combining offline immersion exhibition and recommendation - Google Patents
Recommendation method combining offline immersion exhibition and recommendation Download PDFInfo
- Publication number
- CN113934942A CN113934942A CN202111202592.1A CN202111202592A CN113934942A CN 113934942 A CN113934942 A CN 113934942A CN 202111202592 A CN202111202592 A CN 202111202592A CN 113934942 A CN113934942 A CN 113934942A
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation
- layer
- exhibition
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Computer Hardware Design (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a recommendation method combining offline immersion exhibition and recommendation, which comprises the following steps: firstly, acquiring user experience data, and acquiring a character dimension of a user through the user data; secondly, based on a recommendation algorithm model, predicting the interest degree of the user in the experience exhibition hall through the model, and performing corresponding recommendation in the later period; and finally, setting a feedback mechanism in each exhibition room to learn the character dimension of the user and quantizing. The method is applied to an online sinking exhibition scene, more collected experience data of the user participating in the immersion exhibition are collected, the data source is AI heart stream data of the user participating in the immersion exhibition process, different contents are recommended through the recommendation system technology, the experience of the user participating in the immersion exhibition is different, and the improvement of the experience of tourists is improved.
Description
Technical Field
The invention relates to the technical field of computer data processing, in particular to a recommendation method combining offline immersion exhibition and recommendation.
Background
Experience recommendation has become an important component of offline experience shows, and aims to match appropriate items with appropriate users according to historical user characteristics. Existing personalized recommendation models estimate the likelihood of a user adopting a certain commodity based on historical interaction behaviors such as purchases and clicks, and some of these methods have proven to be effective online. But personalized recommendations have not been used by the online experience.
Recommendations are divided into personalized recommendations and general recommendations. The general recommendation refers to the discovery of personalized interest characteristics of the user through the analysis and mining of user behaviors and item information. For the offline experience exhibition recommendation, the experience feeling of the user is an important factor of the experience recommendation. To the best of my knowledge, no research has been done to date on the use of personalized recommendations for offline use.
In fact, there is no clear interaction between the user and the project during the online experience show. Different users may experience different impressions of the offline experience due to the unique personality. For example, the exhibition visited by youngsters who compare trends is mostly a trend community exhibition, and the sense of fantasy world exhibition is reduced; compared with the trend community exhibition, people with stronger knowledge exploration desire tend to be more fantastic in the world exhibition. Thus, the user's participation in the experience show is driven by its own attributes. Incorporating user personality analysis into experience recommendations may provide accurate referral clues. However, there are two important difficulties how to efficiently integrate user performance into experience recommendations:
what the user's character is obtained. For offline experience shows, what character is built can promote experience recommendations.
How to construct the characters of the user, the user rarely and definitely explains the sensitivity of the user to the characters of the user, so the characters of the user to the exhibition need to be recommended from a feedback mechanism of the user to establish a data-driven method.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a recommendation method combining offline immersion exhibition and recommendation, and overcomes the defects of the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a recommendation method combining offline immersion exhibition and recommendation is characterized in that:
the method comprises the following steps:
firstly, acquiring user experience data, and acquiring a character dimension of a user through the user data; secondly, based on a recommendation algorithm model, predicting the interest degree of the user in the experience exhibition hall through the model, and performing corresponding recommendation in the later period; finally, setting a feedback mechanism in each exhibition room to learn the character dimension of the user and quantizing the character dimension;
the recommendation algorithm model uses an ABtest method, the ABtest method is to make two or more selection strategies for the same recommendation system, and the ABtest method comprises a multilayer perceptron and a collaborative filtering model; and a part of users use a multi-layer perceptron scheme, another part of users use a collaborative filtering model scheme, then the use condition of the users is recorded through logs, relevant indexes are analyzed through structured log data, and therefore the scheme is more in line with the expected design target, and finally all the flow is switched to the scheme in line with the target.
According to the optimized scheme, the multilayer perceptron comprises an input layer, an embedded layer, a nerve cooperation filter layer, an NCF layer, a hidden layer and an output layer;
the embedding layer is arranged above the input layer and is a full connection layer used for mapping the sparse representation of the input layer into a dense vector; the embedding of the user obtained by the input layer, i.e. a dense vector, can be regarded as a latent vector; then, the user embedding and the project embedding are sent to a nerve cooperation filter layer; the neural cooperation filter layer is a multi-layer recommendation algorithm model structure and maps potential vectors into prediction scores; each of the NCF layers can be customized to discover the underlying structure of the user-item interaction; the dimension size of the hidden layer determines the capability of the model; the final output layer is the prediction scoreTraining through minimizationAnd its target value yuiThe point-by-point loss is carried out;
the prediction model is formulated as follows:
whereinIs the user's prediction score for the project, P ∈M×K,Q∈N×KA latent factor matrix representing users and items, respectively; thetafModel parameters representing an interaction function f; since the function f is defined as a multi-layer recommendation algorithm model, it can be defined as:
wherein phioutAnd phixExpressed as the output layer and the xth neural cooperation filter layer mapping functions, respectively, for a total of X neural cooperation filter layers.
The basic principle of the collaborative filtering model is as follows: according to the preferences of all users for the articles or the information, a user group similar to the taste and the preferences of the current users is found, and then recommendation is carried out for the current users based on the historical preferences of the users.
Due to the adoption of the technology, compared with the prior art, the invention has the beneficial effects that:
the method is applied to an online sinking exhibition scene, more collected experience data of the user participating in the immersion exhibition are collected, the data source is AI heart stream data of the user participating in the immersion exhibition process, different contents are recommended through the recommendation system technology, the experience of the user participating in the immersion exhibition is different, and the improvement of the experience of tourists is improved.
Drawings
FIG. 1 is a diagram of a preferred system architecture of 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.
Examples
As shown in fig. 1, a recommendation method combining offline immersion exhibition and recommendation includes the following steps:
firstly, acquiring user experience data, and acquiring a character dimension of a user through the user data; secondly, based on a recommendation algorithm model, predicting the interest degree of the user in the experience exhibition hall through the model, and performing corresponding recommendation in the later period; and finally, setting a feedback mechanism in each exhibition room to learn the character dimension of the user and quantizing.
The recommendation algorithm model uses an ABtest method, the ABtest method is to make two or more selection strategies for the same recommendation system, and the ABtest method comprises a multilayer perceptron and a collaborative filtering model; and a part of users use a multi-layer perceptron scheme, another part of users use a collaborative filtering model scheme, then the use condition of the users is recorded through logs, relevant indexes are analyzed through structured log data, and therefore the scheme is more in line with the expected design target, and finally all the flow is switched to the scheme in line with the target.
In the above method, the basis for obtaining the user experience data is: in psychology, cardiac Flow (Flow) refers to a mental state that a person exhibits while concentrating on performing a certain behavior. Such as the mental state an artist would exhibit at the time of creation. People are often reluctant to be disturbed while in this state, also known as being resistant to interruptions, a feeling that places an individual's mental effort entirely on an activity. The heart flow is generated with high excitement and fullness. Mihary and Chekson mihary define the sensation of heart flow as a sensation of complete attention being placed on an activity, with the sensation of heart flow being highly exciting and filling.
Based on the cardiovascular experience and understanding of the exhibition culture, several key features are proposed as follows: sense of control, clear goals, concentration, loss of self-awareness, time experience distortion, willingness to engage, sensitivity to art, fusion of behavior and awareness, skill and challenge balance, immediate feedback.
These key features will be described in turn herein. The control feeling is the controllable feeling of the user to the activity in the activity process, so that the user can obtain the common feeling in the experience process. Whether the user drives the target to be the direction when the target is clear or not, if the user does not have a clear target when visiting the exhibition, the user can know the exhibition more clearly along with the layer-by-layer progression of the exhibition, and therefore the clear target is formed. Attention is focused on a non-perfect rational neural mechanism, and in a narrow range, the pleasure brought by activities can be experienced only by excluding external interference from the attention range. The loss of self-consciousness is the perception of the user to the existence of the user, and after the user is completely integrated with the exhibition hall, the sense of separation from the surrounding world disappears, and the user completely loses the self-consciousness. Time experience distortion refers to a reduction in experience immersion versus time lapse, such as may be experienced for a long time without feeling the passage of time, or may be experienced for a much longer time but with a long time. The participation will reflect the emotion and subjective idea of human beings, such as whether the exhibition meets the psychological expectation of the user, and whether the user is willing to participate in the experience or interaction of the exhibition. Sensitivity to art reflects user acceptance, sensitivity, and pleasure to art. The fusion of behaviors and consciousness is that a user is used as an organism, and muscle reaction is fused with consciousness in behavior psychology when environmental objects stimulate, so that the consciousness, emotion, memory, authenticity to belief and the like of the user can be objectively reflected. The skill and challenge balance is to judge that when the user and each fine motion of the participating activities are blended into the skill through the skill game challenge, the user can feel unconstrained action freedom to cope with the psychological change in the competition. The timely feedback is a definite two-way interaction, is one of standards of brands for improving user experience, and is also visual data of more direct habitual behaviors of users.
The multilayer perceptron in the ABTest method comprises an input layer, an embedded layer, a nerve cooperation filter layer, an NCF layer, a hidden layer and an output layer.
Multi-layer perceptrons (MLP) is a model of a feed-forward artificial recommendation algorithm that maps multiple data sets of an input onto a single data set of an output. Multi-layer perceptrons (MLPs), deep feed forward networks (deep feed forward networks), also known as feed forward recommendation algorithm models (fed forward neural networks) or multi-layer perceptrons (MLPs), are typical deep learning models. This model is called forward (fed forward) because the information flows through the function of X, through intermediate calculations that define f, and finally to the output y. There is no feedback (feedback) connection between the output of the model and the model itself. When the feed forward recommendation algorithm models are extended to include feedback connections, they are referred to as recurrent neural network models. Hidden layer the hidden layer is an important concept of the proposed algorithm model, which refers to the layers in the middle, except the input and output layers. The input and output layers are visible from the outside and become visible layers, while the intermediate layer is not directly exposed and is a black box part of the model, which is difficult to interpret and is generally called hidden layer. The hidden layer considers that: the f () function is an activation function (activation function), and generally, there is a Sigmoid function or a Tanh function. The recommended algorithm model is to connect a plurality of single neurons, and the output of one neuron is the input of another neuron. A multi-layer perceptron is used as an algorithm model, data of user personal emotion information is used as input of the model, ID numbers of content materials are used as output of the model, ID distribution is carried out according to the number of the material contents, model calculation of a multi-classification task is carried out, the material ID with the highest user liking degree is recommended, the recommended result contains certain probability, a feedback mechanism is designed in the process, the user needs to select liking and disliking in the process of participating in exhibition, the algorithm model needs to be trained continuously, and the model is upgraded and iterated, so that the accuracy of the recommended result is increased continuously.
The embedding layer is arranged above the input layer and is a full connection layer used for mapping the sparse representation of the input layer into a dense vector; embedding of the user obtained by the input layer, i.e. a dense vectorCan be regarded as a potential vector; then, the user embedding and the project embedding are sent to a nerve cooperation filter layer; the neural cooperation filter layer is a multi-layer recommendation algorithm model structure and maps potential vectors into prediction scores; each of the NCF layers can be customized to discover the underlying structure of the user-item interaction; the dimension size of the hidden layer determines the capability of the model; the final output layer is the prediction scoreTraining through minimizationAnd its target value yuiWith point-by-point losses in between.
The prediction model is formulated as follows:
whereinIs the user's prediction score for the project, P ∈M×K,Q∈N×KA latent factor matrix representing users and items, respectively; thetafModel parameters representing an interaction function f; since the function f is defined as a multi-layer recommendation algorithm model, it can be defined as:
wherein phioutAnd phixExpressed as the output layer and the xth neural cooperation filter layer mapping functions, respectively, for a total of X neural cooperation filter layers.
The basic principle of the collaborative filtering model in the ABTest method is as follows: according to the preferences of all users for the articles or the information, a user group similar to the taste and the preferences of the current users is found, and then recommendation is carried out for the current users based on the historical preferences of the users.
The system uses a python language, a server-side program is written by a java program, the Grpc technology is used as a cross-program-language communication means of the system, communication between java and the python language is achieved, and a set of mechanisms is provided by a Remote Procedure Call (RPC) framework, so that the application programs can communicate with one another and the system conforms to a server/client model. When in use, the client calls the interface provided by the server as calling a local function.
The method is applied to an online sinking exhibition scene, more collected experience data of the user participating in the immersion exhibition are collected, the data source is AI heart stream data of the user participating in the immersion exhibition process, different contents are recommended through the recommendation system technology, the experience of the user participating in the immersion exhibition is different, and the improvement of the experience of tourists is improved.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like, indicate orientations and positional relationships based on those shown in the drawings, and are used only for convenience of description and simplicity of description, and do not indicate or imply that the equipment or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be considered as limiting the present invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (3)
1. A recommendation method combining offline immersion exhibition and recommendation is characterized in that: the method comprises the following steps:
firstly, acquiring user experience data, and acquiring a character dimension of a user through the user data;
secondly, based on a recommendation algorithm model, predicting the interest degree of the user in the experience exhibition hall through the model, and performing corresponding recommendation in the later period;
finally, setting a feedback mechanism in each exhibition room to learn the character dimension of the user and quantizing the character dimension;
the recommendation algorithm model uses an ABtest method, the ABtest method is to make two or more selection strategies for the same recommendation system, and the ABtest method comprises a multilayer perceptron and a collaborative filtering model; and a part of users use a multi-layer perceptron scheme, another part of users use a collaborative filtering model scheme, then the use condition of the users is recorded through logs, relevant indexes are analyzed through structured log data, and therefore the scheme is more in line with the expected design target, and finally all the flow is switched to the scheme in line with the target.
2. The method for recommending offline immersive exhibition in combination with recommendation as claimed in claim 1, wherein:
the multilayer perceptron comprises an input layer, an embedded layer, a nerve cooperation filter layer, an NCF layer, a hidden layer and an output layer;
the embedding layer is arranged above the input layer and is a full connection layer used for mapping the sparse representation of the input layer into a dense vector; the embedding of the user obtained by the input layer, i.e. a dense vector, can be regarded as a latent vector; then, the user embedding and the project embedding are sent to a nerve cooperation filter layer; neural cooperative filter layer namelyA multi-tiered recommendation algorithm model structure that maps potential vectors to prediction scores; each of the NCF layers can be customized to discover the underlying structure of the user-item interaction; the dimension size of the hidden layer determines the capability of the model; the final output layer is the prediction scoreTraining through minimizationAnd its target value yuiThe point-by-point loss is carried out;
the prediction model is formulated as follows:
whereinIs the user's prediction score for the project, P ∈M×K,Q∈N×KA latent factor matrix representing users and items, respectively; thetafModel parameters representing an interaction function f; since the function f is defined as a multi-layer recommendation algorithm model, it can be defined as:
wherein phioutAnd phixExpressed as the output layer and the xth neural cooperation filter layer mapping functions, respectively, for a total of X neural cooperation filter layers.
3. The method for recommending offline immersive exhibition in combination with recommendation as claimed in claim 2, wherein: the basic principle of the collaborative filtering model is as follows: according to the preferences of all users for the articles or the information, a user group similar to the taste and the preferences of the current users is found, and then recommendation is carried out for the current users based on the historical preferences of the users.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111202592.1A CN113934942A (en) | 2021-10-15 | 2021-10-15 | Recommendation method combining offline immersion exhibition and recommendation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111202592.1A CN113934942A (en) | 2021-10-15 | 2021-10-15 | Recommendation method combining offline immersion exhibition and recommendation |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113934942A true CN113934942A (en) | 2022-01-14 |
Family
ID=79279833
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111202592.1A Pending CN113934942A (en) | 2021-10-15 | 2021-10-15 | Recommendation method combining offline immersion exhibition and recommendation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113934942A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116149484A (en) * | 2023-03-03 | 2023-05-23 | 湖北工业大学 | Immersive experience method for assisting non-genetic culture propagation and related device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929136A (en) * | 2018-08-30 | 2020-03-27 | 北京京东尚科信息技术有限公司 | Personalized recommendation method and device |
CN111291274A (en) * | 2020-03-02 | 2020-06-16 | 苏州大学 | Article recommendation method, device, equipment and computer-readable storage medium |
CN111695965A (en) * | 2020-04-26 | 2020-09-22 | 清华大学 | Product screening method, system and equipment based on graph neural network |
CN112395323A (en) * | 2020-09-18 | 2021-02-23 | 江苏园上园智能科技有限公司 | Interaction method based on user experience data |
-
2021
- 2021-10-15 CN CN202111202592.1A patent/CN113934942A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110929136A (en) * | 2018-08-30 | 2020-03-27 | 北京京东尚科信息技术有限公司 | Personalized recommendation method and device |
CN111291274A (en) * | 2020-03-02 | 2020-06-16 | 苏州大学 | Article recommendation method, device, equipment and computer-readable storage medium |
CN111695965A (en) * | 2020-04-26 | 2020-09-22 | 清华大学 | Product screening method, system and equipment based on graph neural network |
CN112395323A (en) * | 2020-09-18 | 2021-02-23 | 江苏园上园智能科技有限公司 | Interaction method based on user experience data |
Non-Patent Citations (1)
Title |
---|
杨磊: "基于自注意力机制的协同推荐算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 05, pages 138 - 1479 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116149484A (en) * | 2023-03-03 | 2023-05-23 | 湖北工业大学 | Immersive experience method for assisting non-genetic culture propagation and related device |
CN116149484B (en) * | 2023-03-03 | 2023-11-07 | 湖北工业大学 | Immersive experience method for assisting non-genetic culture propagation and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hasson et al. | Mirroring and beyond: coupled dynamics as a generalized framework for modelling social interactions | |
Graziano et al. | Interpersonal attraction from an evolutionary psychology perspective: Women's reactions to dominant and prosocial men | |
Little et al. | Attraction independent of detection suggests special mechanisms for symmetry preferences in human face perception | |
Yee | The Proteus effect: Behavioral modification via transformations of digital self-representation | |
Yannakakis et al. | Modeling players | |
Sagar et al. | Creating connection with autonomous facial animation | |
US20190122121A1 (en) | Method and system for generating individual microdata | |
Tanevska et al. | A socially adaptable framework for human-robot interaction | |
Nolfi | Emergence of communication in embodied agents: co-adapting communicative and non-communicative behaviours | |
Cleeremans et al. | Consciousness matters: phenomenal experience has functional value | |
US20160027024A1 (en) | Gathering and providing consumer intelligence | |
Tulsulkar et al. | Can a humanoid social robot stimulate the interactivity of cognitively impaired elderly? A thorough study based on computer vision methods | |
Li et al. | Facial feedback for reinforcement learning: a case study and offline analysis using the tamer framework | |
Dell’Anna et al. | Evolving fuzzy logic systems for creative personalized socially assistive robots | |
CN113383345A (en) | Method and system for defining emotion machine | |
Waterworth et al. | Human-experiential design of presence in everyday blended reality | |
Núñez-Pacheco et al. | Getting into someone else's soul: communicating embodied experience | |
CN113934942A (en) | Recommendation method combining offline immersion exhibition and recommendation | |
Hale | Using novel methods to examine the role of mimicry in trust and rapport | |
Buheji | Socio-economic issues storytelling for closing intergenerational gap | |
Lim | Emotions, behaviour and belief regulation in an intelligent guide with attitude | |
Kim et al. | A pilot study of a nature-based virtual reality program on mental health among Korean immigrants during the COVID-19 pandemic | |
Laming | On the behavioural interpretation of neurophysiological observation | |
Harjunen | Perception of facial emotional expressions and touch in virtual face-to-face interaction | |
Kirsh | Atmosphere, mood, and scientific explanation |
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 |