CN110866146B - Video recommendation method and device, computer equipment and storage medium - Google Patents
Video recommendation method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110866146B CN110866146B CN201911174632.9A CN201911174632A CN110866146B CN 110866146 B CN110866146 B CN 110866146B CN 201911174632 A CN201911174632 A CN 201911174632A CN 110866146 B CN110866146 B CN 110866146B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- heart rate
- historical
- obtaining
- 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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Psychiatry (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Developmental Disabilities (AREA)
- Computational Linguistics (AREA)
- Social Psychology (AREA)
- Pulmonology (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
- Psychology (AREA)
- Child & Adolescent Psychology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The application relates to a video recommendation method, a video recommendation device, computer equipment and a storage medium. The method comprises the following steps: acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information; obtaining user comprehensive characteristics based on the user state information, the user evaluation information and historical user data; and sequencing and recommending videos to be recommended based on the user comprehensive characteristics. According to the video recommendation method, the video recommendation device, the computer equipment and the storage medium, the user state information and the user evaluation information are obtained, the user comprehensive characteristics are obtained based on the user state information, the user evaluation information and historical user data, videos to be recommended are ranked and recommended based on the user comprehensive characteristics, the health information, the heart rate information and the emotion information of the user are combined to perform video recommendation on the user, recommendation favorable for the physical condition of the user can be made, the evaluation dimensionality is large, and the effect is good.
Description
Technical Field
The present application relates to the field of face recognition technologies, and in particular, to a video recommendation method and apparatus, a computer device, and a storage medium.
Background
With the arrival of the electronic information era, the rapid development of social economy brings various product types, so that the purchasing purpose of a user can reflect the inherent individual characteristics more, and on the basis of meeting the material requirement, a recommendation system mines the preference information of the user according to the historical behaviors of the user, such as clicking, purchasing, collecting and the like, and further carries out personalized recommendation. Social media such as amazon, tianmao, jingdong and the like electronic commerce websites, facebook, twitter, billow microblog and the like are added with a recommendation function on the basis of the original business.
Most of the current users can use the internet skillfully, so that the social economy development is brought, but with the advancement of aging society, the individual activity is reduced, the occupation of the online time has important influence on the physical health of the users, and especially, the reading of videos occupies a large amount of time of the users. The traditional video recommendation system is based on preference information of user active behaviors, and recommendation based on the information further stimulates the user to browse preference videos, so that the purpose is based on constructing a recommendation-watching loop of forward feedback. However, the active preference information does not represent that the health and spirit of the user are beneficial, and under the national strive to advance the concept of big health, how to effectively utilize the health information to carry out health recommendation with the function of adjustment guidance has important significance. The traditional video recommendation method cannot make recommendations which are beneficial to the physical conditions of the users according to the health information of the users, has less evaluation dimensionality and poor recommendation effect.
Disclosure of Invention
Based on this, it is necessary to provide a video recommendation method, an apparatus, a computer device, and a storage medium for solving the technical problems that the conventional video recommendation method cannot make a recommendation on the physical condition of a user favorably according to the health information of the user, and the dimensionality is small and the recommendation effect is poor.
A method of video recommendation, the method comprising:
acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
obtaining user comprehensive characteristics based on the user state information, the user evaluation information and historical user data;
and sequencing and recommending videos to be recommended based on the user comprehensive characteristics.
In one embodiment, the method further comprises the following steps: before the obtaining of the user state information and the user evaluation information, the method further comprises:
and acquiring a face image when the user watches the video.
In one embodiment, the acquiring the user status information and the user evaluation information includes:
and acquiring health information of the user, and acquiring heart rate information and emotion information of the user based on the face image.
In one embodiment, the acquiring heart rate information of the user based on the face image comprises:
carrying out Euler image amplification on the face image;
calculating the average value of pixels of the amplified human face image to obtain an original heart rate signal;
carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal;
heart rate information of the user is derived based on the power spectral density of the raw heart rate signal.
In one embodiment, the obtaining of emotion information of the user based on the face image comprises:
obtaining an emotion feature sequence based on the face image;
and carrying out normalization processing on the emotion characteristic sequence to obtain the emotion information of the user.
In one embodiment, the obtaining of the user comprehensive characteristics based on the user state information, the user evaluation information and the historical user data includes:
obtaining the comprehensive similarity between the current user and the historical user and the comprehensive score of the current user based on the user state information, the user evaluation information and the historical user data;
and obtaining the comprehensive characteristics of the user based on the comprehensive similarity and the comprehensive score.
In one embodiment, the sorting and recommending videos to be recommended based on the user comprehensive characteristics includes:
obtaining the most similar user from the historical users based on the user comprehensive characteristics;
sorting videos to be recommended based on the history scores of the most similar users;
and performing video recommendation based on the sequencing result.
A video recommendation device, the device comprising:
the information acquisition module is used for acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
the characteristic acquisition module is used for acquiring user comprehensive characteristics based on the user state information, the user evaluation information and historical user data;
and the recommending module is used for sequencing and recommending the videos to be recommended based on the user comprehensive characteristics.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
obtaining user comprehensive characteristics based on the user state information, the user evaluation information and historical user data;
and sequencing and recommending videos to be recommended based on the user comprehensive characteristics.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
obtaining user comprehensive characteristics based on the user state information, the user evaluation information and historical user data;
and sequencing and recommending videos to be recommended based on the user comprehensive characteristics.
According to the video recommendation method, the video recommendation device, the computer equipment and the storage medium, the user state information and the user evaluation information are obtained, the user state information comprises the health information, the heart rate information and the emotion information, the user comprehensive characteristics are obtained based on the user state information, the user evaluation information and the historical user data, videos to be recommended are ranked and recommended based on the user comprehensive characteristics, the users are subjected to video recommendation by combining the health information, the heart rate information and the emotion information of the users, the recommendation favorable for the body conditions of the users can be made, the evaluation dimensionality is large, and the effect is good.
Drawings
Fig. 1 is a flowchart illustrating a video recommendation method according to an embodiment of the present invention;
FIG. 2 is a block diagram of a video recommendation apparatus according to an embodiment of the present invention;
FIG. 3 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, fig. 1 is a flowchart illustrating a video recommendation method according to an embodiment of the invention.
In this embodiment, the video recommendation method includes:
Illustratively, the user state information is physical conditions of the user when watching the video, such as health information, heart rate information, and emotion information, and in other embodiments, the user state information may include other physical condition information; the user evaluation information is the scores of the users for the videos.
And step 110, obtaining user comprehensive characteristics based on the user state information, the user evaluation information and the historical user data.
Illustratively, based on the historical user data, a comparison is made with the historical users to derive a user profile.
And 120, sequencing and recommending videos to be recommended based on the comprehensive characteristics of the users.
Illustratively, videos to be recommended are sorted based on the user database and the user comprehensive characteristics, and video recommendation is performed based on a sorting result.
According to the video recommendation method, the user state information and the user evaluation information are obtained, the user state information comprises health information, heart rate information and emotion information, the user comprehensive characteristics are obtained based on the user state information, the user evaluation information and historical user data, videos to be recommended are ranked and recommended based on the user comprehensive characteristics, the health information, the heart rate information and the emotion information of the user are combined to perform video recommendation on the user, recommendation favorable for the physical condition of the user can be made, the evaluation dimensionality is large, and the effect is good.
In another embodiment, the obtaining of the user state information and the user evaluation information further comprises obtaining a face image of the user when watching the video. Illustratively, the acquiring of the face image of the user comprises face detection positioning, face image preprocessing and face recognition output. Specifically, the system identifies whether the human face is input by the human face, accurately positions the position of the human face, and can effectively complete the human face detection and positioning through a Haar cascade filter in an OpenCV library; the method comprises the following steps that the preprocessing of a face image comprises normalization processing, specifically comprises geometric and gray level processing, wherein the geometric normalization means that a machine adjusts the recognized face to the same position and size so as to extract information, and the gray level normalization means that the image is preprocessed by illumination compensation, a filter and the like; the face recognition output includes distinguishing faces by comparing the faces in each frame of image with the faces in the server database, and the face _ recognition library of Python can be used to complete the system design.
In another embodiment, the obtaining of the user state information and the user evaluation information comprises obtaining health information of the user, and obtaining heart rate information and emotion information of the user based on the face image. As can be understood, the user rating information is the rating of the user on the current video. Illustratively, the health information of the user includes medical history information including conditions such as diabetes, ventilation, hypertension, obesity, coronary heart disease, hyperlipidemia, hyperuricemia, etc. [0,1 ]]Characterization, construct a utility [0,1 ] for each user]Characterized discrete sequence L u And the discrete sequence is stored.
Specifically, acquiring heart rate information of a user based on a face image comprises performing Euler image amplification on the face image; calculating the average value of pixels of the amplified face image to obtain an original heart rate signal; carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal; heart rate information for the user is derived based on the power spectral density of the original heart rate signal. The method comprises the following specific steps:
1. a face region in the dynamic image information is detected.
The face region can be detected by using an existing algorithm, for example, an Adaboost face detection algorithm in the OpenCV of the computer vision open source library, and for each detected face, a rectangular region containing the face region is returned. In other embodiments, other algorithms may be employed for face detection.
2. And carrying out Euler image amplification on the face image.
When the time of the dynamic image lasts for a period of time, for example, lasts for 20s, euler image amplification is performed on the dynamic image in the window, and the euler image amplification comprises the following steps: spatial filtering (pyramid multiresolution decomposition of a video sequence), temporal filtering (temporal band-pass filtering of an image of each scale to obtain a plurality of interesting frequency bands), amplifying filtering results (differential approximation of signals of each frequency band by using a Taylor series), and synthesizing images (synthesizing amplified images).
3. And calculating the average value of pixels of the amplified face image to obtain an original heart rate signal.
And (3) separating RGB channels of each frame of image after the Euler image is amplified, and respectively calculating the average value of pixels in the region of interest to obtain three sections of original heart rate signals P1 (t), P2 (t) and P3 (t).
4. And carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal.
Normalizing each original heart rate signal to obtain:
wherein mu i ,σ i The mean and standard deviation of the heart rate signal, respectively, and the value of i is 1,2,3.
After each section of original heart rate signals are subjected to normalization processing, band-pass filtering processing needs to be carried out on signals in a window so as to eliminate the influence of low-frequency respiration signals and high-frequency noise on heart rate detection results. Considering that the heart rate range of a normal person is [45, 180], the upper and lower cut-off frequencies of the band-pass filter are set to 0.75Hz and 3Hz, respectively.
And performing fast Fourier transform on the three original heart rate signal sequences after normalization and band-pass filtering to respectively obtain the power spectral densities of the three original heart rate signal sequences.
5. Heart rate information for the user is derived based on the power spectral density of the original heart rate signal.
Respectively calculating the maximum values Max1, max2 and Max3 of the power spectral density, mean1, mean2 and Mean3, and calculating the proportion
Selecting a channel signal with the maximum median value of xi 1, xi 2 and xi 3, and taking the frequency corresponding to the maximum value of the power spectral density as the heart rate R t 。
Heart rate information represented by R t After normalization, R is calculated as the standard deviation.
Specifically, obtaining emotion information of a user based on a face image comprises obtaining an emotion feature sequence based on the face image; and carrying out normalization processing on the emotion characteristic sequence to obtain emotion information of the user. The method comprises the following specific steps:
the design was performed using the real Computer Stick accelerator of intel, and the Openvino development kit. Labels containing happiness, calmness and sadness can be output directly based on the face image. Discretizing the label into [0,1,2 ]]Thereby generating an emotional characteristic E t And (4) sequencing.
Emotional information is composed of t After normalization, E was calculated as the standard deviation. It will be appreciated that in other embodiments, other tools may be employed for the recognition of the mood of the face image.
In another embodiment, the step of integrating the user state information and the user evaluation information to obtain the user integrated feature comprises the step of obtaining the integrated similarity between the current user and the historical user and the integrated score of the current user based on the user state information and the user evaluation information; and obtaining the comprehensive characteristics of the user based on the comprehensive similarity and the comprehensive score. The method comprises the following specific steps:
1. calculating user health information L u Calculating the similarity LS of the health information of the historical user through cosine similarity u-v (u, v are different users, respectively); calculating the similarity between the evaluation information of the user and the evaluation information of the historical user, and calculating the evaluation similarity GS through cosine similarity u-v According to LS u-v And GS u-v Calculating the comprehensive similarity QS u-v The calculation formula is as follows:
QS u-v ＝λ sim ×R u-v +(1-λ sim )E u-v
wherein λ sim ∈(0,1)。
Obtaining a comprehensive similarity matrix QS UV (U, V represent a user set).
2. Acquiring heart rate information and emotion information of all users on all watching videos, wherein the heart rate information and the emotion information comprise heart rate fluctuation normalization characteristics R u-k And mood swing normalization feature E u-k (wherein u is the user, k is the video), calculating the comprehensive health fluctuation characteristics, and the calculation formula is as follows:
Z u-k ＝λ flu ×R u-k +(1-λ flu )E u-k
wherein λ is flu ∈(0,1)。
According to Z u-k Calculating health feature H u-k The overall health fluctuation characteristics are inversely related to the health characteristics, and the higher the fluctuation, the worse the health index. The calculation formula is as follows:
meanwhile, the evaluation information of all users on all watched videos is obtained, and the normalized grading feature G is obtained u-k 。
According to health characteristics H u-k And a scoring feature G u-k Calculating a composite score
The calculation method is as follows:
S u-k ＝λ sco ×R u-k +(1-λ sco )E u-k
wherein λ is sco ∈(0,1)。
Construction of a Scoring matrix S UK (U represents a user set and K represents a video set).
It can be understood that the comprehensive characteristics of the user are comprehensive evaluation of the comprehensive similarity and the comprehensive score.
In another embodiment, the ordering and recommending videos to be recommended based on the user comprehensive characteristics comprises obtaining the most similar users from historical users based on the user comprehensive characteristics; sequencing videos to be recommended based on the history scores of the most similar users; and performing video recommendation based on the sequencing result. The method comprises the following specific steps:
based on comprehensive scoring matrix S UK And the overall similarity matrix QS UV Obtaining the scores P of the users with the maximum similarity with the current user on different videos K (K represents a video collection) and is based on a score P K And (4) sorting videos to be recommended, for example, ranking videos with higher scores in the front, and displaying video data corresponding to the sorted videos on a display interface to recommend the videos to the user.
It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least some of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 2, there is provided a video recommendation apparatus including: an information obtaining module 200, a feature obtaining module 210, and a recommending module 220, wherein:
the information acquisition module 200 is configured to acquire user state information and user evaluation information, where the user state information includes health information, heart rate information, and emotion information;
the information obtaining module 200 is further configured to obtain health information of the user, and obtain heart rate information and emotion information of the user based on the face image.
The information obtaining module 200 is further configured to:
carrying out Euler image amplification on the face image;
calculating the average value of pixels of the amplified face image to obtain an original heart rate signal;
carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal;
heart rate information for the user is derived based on the power spectral density of the original heart rate signal.
The information obtaining module 200 is further configured to:
obtaining an emotion characteristic sequence based on the face image;
and carrying out normalization processing on the emotion characteristic sequence to obtain the emotion information of the user.
The feature obtaining module 210 is configured to obtain a user comprehensive feature based on the user state information, the user evaluation information, and the historical user data;
the feature obtaining module 210 is further configured to:
obtaining the comprehensive similarity between the current user and the historical user and the comprehensive score of the current user based on the user state information, the user evaluation information and the historical user data;
and obtaining the comprehensive characteristics of the user based on the comprehensive similarity and the comprehensive score.
And the recommending module 220 is configured to sort and recommend videos to be recommended based on the user comprehensive characteristics.
A recommendation module 220, further configured to:
obtaining the most similar user from the historical users based on the comprehensive characteristics of the users;
sequencing videos to be recommended based on the history scores of the most similar users;
and performing video recommendation based on the sequencing result.
For specific limitations of the video recommendation apparatus, reference may be made to the above limitations of the video recommendation method, which is not described herein again. The modules in the video recommendation device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 3. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a video recommendation method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
obtaining user comprehensive characteristics based on the user state information, the user evaluation information and historical user data;
and sequencing and recommending the videos to be recommended based on the comprehensive characteristics of the users.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
and acquiring a face image when the user watches the video.
In one embodiment, the processor when executing the computer program further performs the steps of:
the health information of the user is obtained, and the heart rate information and the emotion information of the user are obtained based on the face image.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out Euler image amplification on the face image;
calculating the average value of pixels of the amplified face image to obtain an original heart rate signal;
carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal;
heart rate information of the user is derived based on the power spectral density of the raw heart rate signal.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
obtaining an emotion characteristic sequence based on the face image;
and carrying out normalization processing on the emotion characteristic sequence to obtain emotion information of the user.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
obtaining the comprehensive similarity between the current user and the historical user and the comprehensive score of the current user based on the user state information, the user evaluation information and the historical user data;
and obtaining the comprehensive characteristics of the user based on the comprehensive similarity and the comprehensive score.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
obtaining the most similar user from the historical users based on the comprehensive characteristics of the users;
ordering videos to be recommended based on the historical scores of the most similar users;
and performing video recommendation based on the sequencing result.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
obtaining user comprehensive characteristics based on the user state information, the user evaluation information and historical user data;
and sequencing and recommending the videos to be recommended based on the comprehensive characteristics of the users.
In one embodiment, the computer program when executed by the processor further performs the steps of:
and acquiring a face image when the user watches the video.
In one embodiment, the computer program when executed by the processor further performs the steps of:
the health information of the user is obtained, and the heart rate information and the emotion information of the user are obtained based on the face image.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out Euler image amplification on the face image;
calculating the average value of pixels of the amplified face image to obtain an original heart rate signal;
carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal;
heart rate information of the user is derived based on the power spectral density of the raw heart rate signal.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining an emotion feature sequence based on the face image;
and carrying out normalization processing on the emotion characteristic sequence to obtain emotion information of the user.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining the comprehensive similarity between the current user and the historical user and the comprehensive score of the current user based on the user state information, the user evaluation information and the historical user data;
and obtaining the comprehensive characteristics of the user based on the comprehensive similarity and the comprehensive score.
In one embodiment, the computer program when executed by the processor further performs the steps of:
obtaining the most similar user from the historical users based on the comprehensive characteristics of the users;
ordering videos to be recommended based on the historical scores of the most similar users;
and performing video recommendation based on the sequencing result.
According to the video recommendation method, the video recommendation device, the computer equipment and the storage medium, the user state information and the user evaluation information are obtained, the user state information comprises the health information, the heart rate information and the emotion information, the comprehensive user characteristics are obtained based on the user state information, the user evaluation information and historical user data, videos to be recommended are ranked and recommended based on the comprehensive user characteristics, the users are subjected to video recommendation by combining the health information, the heart rate information and the emotion information of the users, the favorable recommendation to the body conditions of the users can be made, the evaluation dimensionality is large, and the effect is good.
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 instructions of a computer program, which 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 (Rambus) direct RAM (RDRAM), direct Rambus Dynamic RAM (DRDRAM), and Rambus Dynamic RAM (RDRAM), among others.
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-mentioned embodiments 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 invention. 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 application shall be subject to the appended claims.
Claims (8)
1. A method for video recommendation, the method comprising:
acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information, and the user state information is data of a user watching a video;
obtaining comprehensive similarity between the current user and the historical user and comprehensive scores of the current user based on the user state information, the user evaluation information and historical user data, and obtaining comprehensive user characteristics based on the comprehensive similarity and the comprehensive scores, wherein the historical user data comprises health information of the historical user and evaluation information of the historical user;
and obtaining the most similar user from the historical users based on the user comprehensive characteristics, sequencing videos to be recommended based on the historical scores of the most similar users, and recommending videos which are beneficial to physical conditions to the current user based on the sequencing result.
2. The method of claim 1, wherein obtaining user status information and user rating information further comprises:
and acquiring a face image when the user watches the video.
3. The method of claim 2, wherein the obtaining user status information and user rating information comprises:
and acquiring health information of the user, and acquiring heart rate information and emotion information of the user based on the face image.
4. The method of claim 3, wherein the obtaining heart rate information of the user based on the face image comprises:
carrying out Euler image amplification on the face image;
calculating the average value of pixels of the amplified human face image to obtain an original heart rate signal;
carrying out normalization processing, band-pass filtering processing and fast Fourier transform on the original heart rate signal to obtain the power spectral density of the original heart rate signal;
heart rate information of the user is derived based on the power spectral density of the original heart rate signal.
5. The method of claim 3, wherein the obtaining of emotion information of the user based on the face image comprises:
obtaining an emotion feature sequence based on the face image;
and carrying out normalization processing on the emotion characteristic sequence to obtain emotion information of the user.
6. A video recommendation apparatus, characterized in that the apparatus comprises:
the information acquisition module is used for acquiring user state information and user evaluation information, wherein the user state information comprises health information, heart rate information and emotion information;
the characteristic acquisition module is used for obtaining the comprehensive similarity between the current user and the historical user and the comprehensive score of the current user based on the user state information, the user evaluation information and the historical user data, and obtaining the comprehensive characteristic of the user based on the comprehensive similarity and the comprehensive score, wherein the historical user data comprises the health information of the historical user and the evaluation information of the historical user;
and the recommendation module is used for obtaining the most similar user from the historical users based on the comprehensive characteristics of the users, sequencing videos to be recommended based on the historical scores of the most similar user, and recommending videos which are favorable for physical conditions to the current user based on the sequencing result.
7. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911174632.9A CN110866146B (en) | 2019-11-26 | 2019-11-26 | Video recommendation method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911174632.9A CN110866146B (en) | 2019-11-26 | 2019-11-26 | Video recommendation method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110866146A CN110866146A (en) | 2020-03-06 |
| CN110866146B true CN110866146B (en) | 2022-11-11 |
Family
ID=69656051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911174632.9A Active CN110866146B (en) | 2019-11-26 | 2019-11-26 | Video recommendation method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866146B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111782875B (en) * | 2020-07-06 | 2023-10-13 | 聚好看科技股份有限公司 | Video search recommendation method, recipe recommendation method based on refrigerator and server |
| CN114449342B (en) * | 2022-01-21 | 2024-02-27 | 腾讯科技（深圳）有限公司 | Video recommendation method, device, computer readable storage medium and computer equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327234A (en) * | 2015-07-02 | 2017-01-11 | 中兴通讯股份有限公司 | Information recommendation method and apparatus |
| CN106919632A (en) * | 2015-12-28 | 2017-07-04 | 广州华多网络科技有限公司 | Video recommendation method and device based on main broadcaster's appearance |
| CN106407418A (en) * | 2016-09-23 | 2017-02-15 | Tcl集团股份有限公司 | A face identification-based personalized video recommendation method and recommendation system |
| CN108197595A (en) * | 2018-01-23 | 2018-06-22 | 京东方科技集团股份有限公司 | A kind of method, apparatus, storage medium and computer for obtaining evaluation information |
| CN109284417B (en) * | 2018-08-27 | 2022-11-22 | 广州飞磨科技有限公司 | Video pushing method and device, computer equipment and storage medium |
-
2019
- 2019-11-26 CN CN201911174632.9A patent/CN110866146B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866146A (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9852327B2 (en) | Head-pose invariant recognition of facial attributes | |
| Ullman et al. | Visual features of intermediate complexity and their use in classification | |
| Xia et al. | Bottom–up visual saliency estimation with deep autoencoder-based sparse reconstruction | |
| KR101835333B1 (en) | Method for providing face recognition service in order to find out aging point | |
| Liu et al. | Log-Euclidean metrics for contrast preserving decolorization | |
| CN110866146B (en) | Video recommendation method and device, computer equipment and storage medium | |
| CN112395500A (en) | Content data recommendation method and device, computer equipment and storage medium | |
| Lin et al. | Automatic age estimation system for face images | |
| CN110807139A (en) | Picture identification method and device, computer readable storage medium and computer equipment | |
| CN106056083A (en) | Information processing method and terminal | |
| CN110750673B (en) | Image processing method, device, equipment and storage medium | |
| CN111340213B (en) | Neural network training method, electronic device, and storage medium | |
| CN116863522A (en) | Acne grading method, device, equipment and medium | |
| CN113538070A (en) | User life value cycle detection method and device and computer equipment | |
| CN110807693A (en) | Album recommendation method, device, equipment and storage medium | |
| CN111325705A (en) | Image processing method, device, equipment and storage medium | |
| CN110298684B (en) | Vehicle type matching method and device, computer equipment and storage medium | |
| CN111339358A (en) | Movie recommendation method and device, computer equipment and storage medium | |
| CN115827877A (en) | Proposal auxiliary combination method, device, computer equipment and storage medium | |
| Shi et al. | Gradient-guided color image contrast and saturation enhancement | |
| Wang et al. | A study of convolutional sparse feature learning for human age estimate | |
| US20220101407A1 (en) | Method for determining a recommended product, electronic apparatus, and non-transitory computer-readable storage medium | |
| Li et al. | Fabric defect detection based on deep-handcrafted feature and weighted low-rank matrix representation | |
| Rodriguez et al. | Improved likelihood ratios for face recognition in surveillance video by multimodal feature pairing | |
| Ghalleb et al. | Demographic Face Profiling Based on Age, Gender and Race |
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 |