CN112423038A - Video recommendation method, terminal and storage medium - Google Patents
Video recommendation method, terminal and storage medium Download PDFInfo
- Publication number
- CN112423038A CN112423038A CN202011235670.3A CN202011235670A CN112423038A CN 112423038 A CN112423038 A CN 112423038A CN 202011235670 A CN202011235670 A CN 202011235670A CN 112423038 A CN112423038 A CN 112423038A
- Authority
- CN
- China
- Prior art keywords
- video
- user
- identity information
- preset
- video application
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000001960 triggered effect Effects 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000013507 mapping Methods 0.000 claims description 28
- 238000012216 screening Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/02—Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Graphics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a video recommendation method, a terminal and a storage medium, wherein the method comprises the following steps: when a video recommendation instruction triggered by a user is received, acquiring user identity information; acquiring a video application history use record corresponding to the user identity information; acquiring a common video application corresponding to the user identity information according to a video application history use record corresponding to the user identity information; carrying out multiple rounds of conversations with the user according to a preset multiple rounds of conversation algorithms to obtain a user search intention; performing video search according to the search intention of the user in the common video application to obtain a first video search result; and displaying the first video search result. The invention solves the problem that the obtained search result can not meet the personalized requirements of the user when the video is searched and matched based on the keywords provided by the user.
Description
Technical Field
The invention relates to the field of intelligent terminals, in particular to a video recommendation method, a terminal and a computer readable storage medium.
Background
With the richness of cultural entertainment life and the rise of various video platforms and video software, nowadays, the types of video programs which can be watched by users are more and more, so that how to search videos which are interesting to the users from massive videos and recommend the videos to the users is the current research focus. At present, most of videos are searched from the whole network only based on keywords provided by a user, and videos matched with the keywords are recommended to the user, but the videos searched in the mode cannot meet the requirement of user personalization.
Disclosure of Invention
The invention mainly aims to provide a video recommendation method, a terminal and a computer readable storage medium, and aims to solve the problem that the existing video search and matching based on keywords provided by a user cannot obtain search results meeting the personalized requirements of the user.
In order to achieve the above object, the present invention provides a video recommendation method, comprising the steps of:
when a video recommendation instruction triggered by a user is received, acquiring user identity information;
acquiring a video application history use record corresponding to the user identity information;
acquiring a common video application corresponding to the user identity information according to a video application history use record corresponding to the user identity information;
carrying out multiple rounds of conversations with the user according to a preset multiple rounds of conversation algorithms to obtain a user search intention;
performing video search according to the search intention of the user in the common video application to obtain a first video search result;
and displaying the first video search result.
Optionally, the step of presenting the first video search result includes:
calculating the weight of each video in the first video search result according to a preset algorithm;
and according to the weight of each video, sequencing and displaying each video in the first video search result according to the weight.
Optionally, the step of presenting the first video search result further comprises, before the step of presenting the first video search result:
judging whether a video exists in the first video searching result;
if yes, executing the step of displaying the first video search result;
if not, obtaining the video application meeting the preset screening condition according to the historical use records of other videos except the common videos corresponding to the user identity information and the preset screening condition;
and performing video search according to the user search intention in the video application meeting the preset screening condition to obtain a second video search result, and displaying the second video search result.
Optionally, the step of obtaining the commonly used video application corresponding to the user identity information according to the video application history usage record corresponding to the user identity information includes:
selecting the video application which meets the preset screening condition as the common video application corresponding to the user identity information according to the video application historical use record and the preset screening condition corresponding to the user identity information, wherein the video application historical use record comprises the historical use accumulated time of the video application, the user historical use accumulated times of the video application, the historical use accumulated times of the video application within the preset time before the current time, the historical use accumulated time of the video application within the preset time before the current time or the last use time of the video application.
Optionally, the step of performing multiple rounds of conversations with the user according to a preset multiple round of conversation algorithm to obtain the search intention of the user includes:
selecting a word slot from word slots which are not filled with slot values in a preset word slot combination as a word slot to be filled;
determining a corresponding answer of the word slot to be filled according to a preset word slot and dialect mapping relation, and feeding back the answer to a user so that the user feeds back voice response according to the answer;
extracting at least one slot value from the voice response fed back by the user;
filling the obtained slot values into corresponding word slots in the word slot combination;
judging whether word slots with unfilled slot values exist in the word slot combination;
if yes, returning to the step of selecting one word slot from word slots which are not filled with slot values in the preset word slot combination as a word slot to be filled;
and if not, acquiring the search intention of the user according to the slot value of each word slot in the word slot combination.
Optionally, when receiving a video recommendation instruction triggered by a user, the step of obtaining user identity information includes:
when a video recommendation voice instruction triggered by a user is received, acquiring voice data corresponding to the voice instruction;
performing voiceprint calculation on the voice data to obtain voiceprint characteristics;
and obtaining user identity information corresponding to the voiceprint characteristics according to a preset mapping relation between the user identity information and the voiceprint characteristics.
Optionally, the step of performing voiceprint calculation on the voice data and acquiring a voiceprint feature includes:
acquiring the frequency, amplitude and speech rate of the voice data;
correspondingly acquiring a weight corresponding to the frequency, a weight corresponding to the amplitude and a weight corresponding to the speech rate of the voice data according to a preset mapping relation between the frequency and the weight, a preset mapping relation between the amplitude and the weight and a preset mapping relation between the speech rate and the weight;
and calculating the sum of the weight corresponding to the frequency, the weight corresponding to the amplitude and the weight corresponding to the speech speed as the voiceprint characteristics corresponding to the voice data.
Optionally, when receiving a video recommendation instruction triggered by a user, the step of obtaining user identity information includes:
when a video recommendation instruction triggered by a user is received, acquiring a current user image;
and carrying out face recognition on the current user image to acquire user identity information.
To achieve the above object, the present invention further provides a terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the video recommendation method as described above.
To achieve the above object, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when being executed by a processor, implements the steps of the video recommendation method as described above.
According to the video recommendation method, the terminal and the computer-readable storage medium, the user identity information is acquired when a video recommendation instruction triggered by a user is received; acquiring a video application history use record corresponding to the user identity information; acquiring a common video application corresponding to the user identity information according to a video application history use record corresponding to the user identity information; carrying out multiple rounds of conversations with the user according to a preset multiple rounds of conversation algorithms to obtain a user search intention; performing video search according to the search intention of the user in the common video application to obtain a first video search result; and displaying the first video search result. Because the use habit of the video application of the user is determined according to the user identity, and corresponding video search is carried out in the video application conforming to the use habit of the user, the searched video more conforms to the individual requirements of the user, and the user experience is improved.
Drawings
FIG. 1 is a schematic diagram of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a video recommendation method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a video recommendation method according to a second embodiment of the present invention;
FIG. 4 is a flowchart illustrating a video recommendation method according to a third embodiment of the present invention;
fig. 5 is a flowchart illustrating a video recommendation method according to a fourth embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a hardware structure of a terminal provided in various embodiments of the present invention. The terminal comprises a communication module 01, a memory 02, a processor 03 and the like. Those skilled in the art will appreciate that the terminal shown in fig. 1 may also include more or fewer components than shown, or combine certain components, or a different arrangement of components. The processor 03 is connected to the memory 02 and the communication module 01, respectively, and the memory 02 stores a computer program, which is executed by the processor 03 at the same time.
The communication module 01 may be connected to an external device through a network. The communication module 01 may receive data sent by an external device, and may also send data, instructions, and information to the external device, where the external device may be an electronic device such as a mobile phone, a tablet computer, a notebook computer, and a desktop computer.
The memory 02 may be used to store software programs and various data. The memory 02 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function (acquiring user identity information when receiving a video recommendation instruction triggered by a user), and the like; the storage data area may store data or information created according to the use of the terminal, or the like. Further, the memory 02 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
The processor 03, which is a control center of the terminal, connects various parts of the entire terminal using various interfaces and lines, and performs various functions of the terminal and processes data by operating or executing software programs and/or modules stored in the memory 02 and calling data stored in the memory 02, thereby integrally monitoring the terminal. Processor 03 may include one or more processing units; preferably, the processor 03 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 03.
Although not shown in fig. 1, the terminal may further include a circuit control module, where the circuit control module is used for being connected to a mains supply to implement power control and ensure normal operation of other components.
Those skilled in the art will appreciate that the terminal structure shown in fig. 1 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
Various embodiments of the method of the present invention are presented in terms of the above-described hardware architecture.
Referring to fig. 2, in a first embodiment of the video recommendation method of the present invention, the video recommendation method includes the steps of:
step S10, when a video recommendation instruction triggered by a user is received, user identity information is obtained;
in this embodiment, when a user needs a terminal to recommend a related video, a video recommendation instruction is triggered, and the video recommendation instruction triggered by the user may be in the form of a gesture, voice, an action, a remote controller, or the like. When a video recommendation instruction triggered by a user is received, identity information of the user triggering the video recommendation instruction is acquired first. The method for acquiring the user identity information by the terminal comprises the steps of acquiring voice information sent by a user when the user triggers a video recommendation instruction in a voice form, identifying the voice information to acquire the user identity information, carrying out face identification on the user through a camera built in the terminal or an external camera connected with the terminal to acquire the user identity information when the user triggers the video recommendation instruction through gestures or actions, displaying an input frame on a display screen of the terminal when the user triggers the video recommendation instruction, directly inputting the user identity information in the input frame by the user, or sending an acquisition request to the user terminal when the user triggers the video recommendation instruction so that the user inputs the user identity information on the user terminal, and sending the user information input by the user to the terminal by the user terminal.
Step S20, obtaining the video application history use record corresponding to the user identity information;
when a user uses a video application installed on a terminal every time, the identity information of the user is obtained, and the use condition of the time is stored in a video application history use record corresponding to the user identity information, wherein the use condition comprises records such as the name and the use duration of the used video application. After the terminal acquires the user identity information, the terminal acquires the video application history use record corresponding to the user identity information. For example, the user whose terminal acquires the current video recommendation triggering instruction is a female owner in a family, and a history use record corresponding to the female owner is acquired.
Step S30, obtaining a common video application corresponding to the user identity information according to the video application history usage record corresponding to the user identity information;
after the terminal acquires the video application history use record corresponding to the user identity information, one video application in the video applications recorded in the video application history use record is determined to be used as the common video application corresponding to the user identity information according to the video application history use record in the video application history use record.
Specifically, step S30 includes:
step S31, selecting, according to the video application historical usage record corresponding to the user identity information and a preset screening condition, a video application meeting the preset screening condition as a commonly used video application corresponding to the user identity information, where the video application historical usage record includes a historical usage accumulated time of the video application, a user historical usage accumulated number of times of the video application, a historical usage accumulated number of times of the video application within a preset time before the current time, a historical usage accumulated time of the video application within a preset time before the current time, or a last usage time of the video application.
After the terminal acquires the video application historical use record corresponding to the user identity information, according to preset screening conditions, counting the historical use accumulated times, the historical use accumulated time, the last use time of each video application, the historical use times of each video application in the preset time before the current time or the historical use time of each video application in the preset time before the current time of each video application in the video application historical use record. And then selecting the video application with the preset screening condition as the common video application according to the counted result. For example, if the preset screening condition is that the historical use times in the last month are the maximum, the historical use times of each video application in the last month are counted, and then the video application with the maximum historical use times in the last month is used as the common video application. For another example, if the preset screening condition is that the historical use time is longest, then the historical use accumulated time of each video application is counted, and then the video application corresponding to the historical use accumulated time is used as the common video application corresponding to the user information. For another example, if the preset filtering condition is the accumulated historical usage number, the accumulated historical usage number of each video application is counted, and the video application with the largest accumulated historical usage number is used as the commonly used video application. For another example, if the preset screening condition is historical use time in one month, the use time of each video application in the last month is counted, and then the video application with the most use time in the last month is taken as the common video application. For another example, if the preset screening condition is the video application used for the last time, the last time of each video application is counted, then the video applications are sorted according to the sequence of the last time of each video application, and the last video application in the sorting result is used as the common video application.
Step S40, carrying out multiple rounds of dialogue with the user according to a preset multiple rounds of dialogue algorithm to obtain the search intention of the user;
after the user triggers the video recommendation instruction, the terminal needs to confirm the user requirements, that is, the search intention of the user is confirmed, in order to recommend videos meeting the user requirements more accurately. And the terminal adopts a multi-turn dialogue algorithm to carry out multi-turn dialogue with the user until the user search intention is determined to be obtained, and the dialogue is stopped.
Specifically, the step S40 includes:
step S41, selecting a word slot from word slots which are not filled with slot values in a preset word slot combination as a word slot to be filled;
step S42, determining the corresponding answer of the word slot to be filled according to the preset mapping relation between the word slot and the dialect, and feeding back the answer to the user so that the user feeds back voice reply according to the answer;
step S43, extracting at least one slot value from the voice response fed back by the user;
step S44, filling the obtained value of each slot into each corresponding word slot in the word slot combination;
step S45, judging whether the word slot combination has a word slot with unfilled slot value; if yes, go back to step S41; if not, go to step S46;
and step S46, acquiring the search intention of the user according to the slot value of each word slot in the word slot combination.
The terminal stores a preset word slot combination, the word slot combination is composed of a plurality of word slots, and corresponding dialogues are preset for each word slot. The terminal selects a word slot from unfilled word slots of the current word slot combination as a word slot to be filled in the current conversation, then the terminal acquires a corresponding conversation of the word slot to be filled according to a preset mapping relation between the word slot and the conversation, determines the return of the word slot, feeds the return back to a user to open the current conversation, the feedback mode can be played in a voice mode or displayed in a text mode on a display screen of the terminal, then the user receives a reply based on the return, after receiving the reply, the terminal extracts a slot value of at least one word slot from the reply, fills the slot value into the word slot combination, judges whether unfilled word slots exist in the word slot combination or not after filling, if unfilled word slots exist, determines that information required by the user for searching intention exists, and repeats the steps, namely opens a new conversation until all word slots in the word slot combination are filled completely, if all word slots filled in the word slot combination are filled, namely the terminal has acquired all information required for determining the search intention of the user, the search intention of the user can be determined according to the slot values of all the word slots in the word slot combination.
For example, the terminal first outputs "hello! I, your AI movie assistant ", the user answers" want to watch movie ", the terminal extracts information according to" want to watch movie "answered by the user, and obtains that the video type that the user needs to search is movie, but the search range is too wide, and needs to further confirm the search intention of the user, and the terminal outputs" ask what movie you want to watch? And when the terminal confirms that the user can confirm the search intention, the terminal stops the conversation.
It should be noted that the language understanding method used by the embedded language understanding module in the multi-turn dialogue mechanism may be a rule-based understanding method, a generative model-based method (e.g., a random finite state machine, a statistical machine translation or a dynamic bayesian network), a discriminant model-based method (e.g., CRF, SVM or MEMM), or a deep learning method (e.g., BiLSTM + CRF, CNN or seq2 seq).
Step S50, performing video search in the common video application according to the search intention of the user to obtain a first video search result;
and step S60, displaying the first video search result.
The terminal may link its own search engine to a search entry in each installed video application in the terminal. After the terminal determines the common video application, a search engine of the terminal is linked to a search entry in the common video application, then video search is performed in the common video application according to the search intention of the user, and a search result fed back by the search engine of the common video application is obtained and used as a first video search result. And after the first video search result is obtained, displaying the first video search result on a terminal display area, so that a user performs subsequent selection operation or click playing operation and the like according to the displayed first video search result. When the first video search result is presented to the user, the video names and the thumbnails in the first video search result may be presented in a list form, or the video names and the thumbnails may be presented in a matrix form, where the presentation manner is not limited.
Specifically, step S60 includes:
step S61, calculating the weight of each video in the first video search result according to a preset algorithm;
and step S62, according to the weight of each video, sequencing and displaying each video in the first video search result according to the weight.
The first video search result usually includes a plurality of videos, the plurality of videos need to be arranged in a certain order, the weight of each video is usually calculated by adopting a preset algorithm, and then the video information is ordered according to the weight. The preset algorithm may be an algorithm preset by the terminal, or may be calculated by a preset algorithm in a vertical search engine in video application. The factors considered in calculating the weight of each video are different, and the calculated weight is also different, and for example, the degree of interest of a website to a net friend, the number of times video information is viewed, the date of update on the website, and the like can be all factors considered in calculating the ranking weight of each video information. The weight of the video on the website with high interest of the net friends is high. The more the video is browsed, the higher the corresponding weight is; the later the upload time on the website, the higher the corresponding weight.
It should be noted that the steps S20-S30 and S40 may be executed in the order of steps S20-S30 and step S40, or in the order of steps S40 and steps S20-S30, or in the order of steps S20-S30 and step S40.
The method comprises the steps that user identity information is obtained when a video recommendation instruction triggered by a user is received; acquiring a video application history use record corresponding to the user identity information; acquiring a common video application corresponding to the user identity information according to a video application history use record corresponding to the user identity information; carrying out multiple rounds of conversations with the user according to a preset multiple rounds of conversation algorithms to obtain a user search intention; performing video search according to the search intention of the user in the common video application to obtain a first video search result; and displaying the first video search result. Because the use habit of the video application of the user is determined according to the user identity, and corresponding video search is carried out in the video application conforming to the use habit of the user, the searched video conforms to the individual requirements of the user better, and the user experience is improved.
Further, referring to fig. 3, fig. 3 is a flowchart illustrating a second embodiment of the video recommendation method according to the first embodiment of the video recommendation method, where in this embodiment, step S60 includes:
step S70, judging whether the first video search result has a video; if yes, go to step S60; if not, go to step S61;
step S61, according to the historical use records of other videos except the common videos corresponding to the user identity information and preset screening conditions, obtaining the video application which meets the preset screening conditions as a target video application;
and step S62, performing video search according to the user search intention in the target video application, obtaining a second video search result, and displaying the second video search result.
In this embodiment, when the terminal searches for a video matching the search intention of the user by using the vertical search engine of the common video application, and a video conforming to the search intention is not searched, the first search result does not include a video, so before displaying the first search result of the video, it is determined whether a video conforming to the search intention of the user is searched in the common video application, and if a video conforming to the search intention of the user is searched, the video is directly displayed. If the video meeting the search intention of the user is not searched out, selecting one video application meeting the preset screening condition from other video applications except the common video application as a target video application according to the preset screening condition, for example, a video application with the highest accumulated number of historical uses, the highest accumulated time of historical uses, the highest number of uses within a preset time, the highest used time within a preset time or the latest used time is selected as the target video application from other video applications except the commonly used video application, then linking the search engine to a search entry of a target video application, performing video search according with the search intention of the user, obtaining a second video search result, displaying the second video search result on a terminal display area, and the user can perform subsequent selection operation or click playing operation and the like according to the displayed second video search result. When the second video search result is presented to the user, the video names and the thumbnails in the first video search result may be presented in a list form, or the video names and the thumbnails may be presented in a matrix form, where the presentation manner is not limited.
It should be noted that, when it is determined that there is no video matching the user search intention in the first search result, the search engine itself may be linked to search entries of other video applications except the common video application, and video searches meeting the user search intention are performed respectively to obtain video search results fed back by the video applications except the common video application, and then the number of videos in the video search results fed back by the video applications except the common video application is counted, and the video search result with the largest number of videos is taken as the second video search result and displayed.
In the embodiment, under the condition that the video matched with the search intention of the user is not searched in the common video application, one video application which best meets the use habit of the user is automatically selected from other video applications, and the video matched with the search intention of the user is searched in the video application, so that the searched video can also meet the personalized requirement of the user.
Further, referring to fig. 4, fig. 4 is a flowchart illustrating a third embodiment of the video recommendation method according to the first embodiment and the second embodiment of the video recommendation method of the present application, in this embodiment, step S10 includes:
step S11, when a video recommendation voice instruction triggered by a user is received, acquiring voice data corresponding to the voice instruction;
step S12, carrying out voiceprint calculation on the voice data to obtain voiceprint characteristics;
in this embodiment, when the user uses a voice-form video recommendation voice instruction to trigger the video recommendation function of the terminal, and the terminal receives the voice instruction, the terminal collects voice data in the voice instruction, performs voiceprint calculation on the voice data, and obtains a voiceprint feature.
Specifically, step S12 includes:
step S121, obtaining the frequency, amplitude and speech rate of the voice data;
step S122, correspondingly acquiring a weight corresponding to the frequency, a weight corresponding to the amplitude and a weight corresponding to the speech rate of the voice data according to a preset mapping relation between the frequency and the weight, a preset mapping relation between the amplitude and the weight and a preset mapping relation between the speech rate and the weight;
step S123, calculating a sum of the weight corresponding to the frequency, the weight corresponding to the amplitude, and the weight corresponding to the speech rate as the voiceprint feature corresponding to the speech data.
The terminal presets the mapping relation between frequency and weight, the mapping relation between amplitude and weight and the mapping relation between speech speed and weight. In the preset mapping relationship between the frequencies and the weights, the frequencies and the weights can be in one-to-one correspondence, or the frequencies can be divided into a plurality of ranges, and each frequency range is in one-to-one correspondence with the weight; similarly, in the preset mapping relationship between the amplitudes and the weights, the amplitudes and the weights may be in one-to-one correspondence, or the amplitudes may be divided into a plurality of ranges, each amplitude range is in one-to-one correspondence with the weight, and different amplitudes correspond to different weights; in the mapping relationship between the preset speech rate and the weight, the speech rate and the weight may be in one-to-one correspondence, or the speech rate may be divided into a plurality of ranges, each speech rate range is in one-to-one correspondence with the weight, and different speech rates correspond to different weights. After the terminal obtains the voice data, the voice data is analyzed, the frequency, the amplitude and the speech speed in the voice data are extracted, then a preset mapping relation between the frequency and the weight, a preset mapping relation between the amplitude and the weight and a preset mapping relation between the speech speed and the weight are called, the weight corresponding to the frequency, the weight corresponding to the amplitude and the weight corresponding to the speech speed in the voice data are respectively determined, then the three weights are summed, a weight sum is obtained, and the weight sum is used as the voiceprint feature corresponding to the voice data.
And step S13, obtaining user identity information corresponding to the voiceprint features according to the preset mapping relation between the user identity information and the voiceprint features.
The terminal is preset with mapping relations between user identity information and voiceprint features, and after the voiceprint features are obtained, the preset mapping relations between the user identity information and the voiceprint features are called, the obtained voiceprint features are matched, and user identity information corresponding to the voiceprint features is matched.
This embodiment obtains user's identity information through voiceprint recognition to do not need the user to upload identity information, it is more convenient and intelligent.
Further, referring to fig. 5, fig. 5 is a flowchart illustrating a fourth embodiment of the video recommendation method according to the foregoing embodiment of the video recommendation method of the present application, wherein in the present embodiment, step S10 includes:
step S14, when a video recommendation instruction triggered by a user is received, acquiring a current user image;
and step S15, performing face recognition on the current user image to acquire user identity information.
In this embodiment, when a user triggers a video recommendation instruction to start a video recommendation function of a terminal, after the terminal receives the video recommendation instruction, the terminal starts an internal camera or an external camera connected to the terminal to acquire a user image within a preset range in front of the terminal, performs face recognition on the current user image by using a face recognition algorithm to obtain a user face feature, and then obtains user identity information corresponding to the recognized face feature according to a mapping relationship between pre-stored user identity information and the face feature.
The embodiment acquires the user identity information through face recognition, so that the user does not need to upload the identity information, the method is more convenient and intelligent, and compared with other methods for recognizing the user identity information, the method is higher in accuracy.
The invention also proposes a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be the Memory 02 in the terminal of fig. 1, and may also be at least one of a ROM (Read-Only Memory)/RAM (Random Access Memory), a magnetic disk, and an optical disk, and the computer-readable storage medium includes several pieces of information for enabling the terminal to perform the method according to the embodiments of the present invention.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for video recommendation, comprising the steps of:
when a video recommendation instruction triggered by a user is received, acquiring user identity information;
acquiring a video application history use record corresponding to the user identity information;
acquiring a common video application corresponding to the user identity information according to a video application history use record corresponding to the user identity information;
carrying out multiple rounds of conversations with the user according to a preset multiple rounds of conversation algorithms to obtain a user search intention;
performing video search according to the search intention of the user in the common video application to obtain a first video search result;
and displaying the first video search result.
2. The video recommendation method of claim 1, wherein said step of presenting the first video search result comprises:
calculating the weight of each video in the first video search result according to a preset algorithm;
and according to the weight of each video, sequencing and displaying each video in the first video search result according to the weight.
3. The video recommendation method of claim 2, wherein said step of presenting said first video search result is preceded by the step of:
judging whether a video exists in the first video searching result;
if yes, executing the step of displaying the first video search result;
if not, obtaining the video application meeting the preset screening condition according to the historical use records of other videos except the common videos corresponding to the user identity information and the preset screening condition;
and performing video search according to the user search intention in the video application meeting the preset screening condition to obtain a second video search result, and displaying the second video search result.
4. The video recommendation method according to any one of claims 1 to 3, wherein the step of obtaining the commonly used video application corresponding to the user identity information according to the video application history usage record corresponding to the user identity information comprises:
selecting the video application which meets the preset screening condition as the common video application corresponding to the user identity information according to the video application historical use record and the preset screening condition corresponding to the user identity information, wherein the video application historical use record comprises the historical use accumulated time of the video application, the user historical use accumulated times of the video application, the historical use accumulated times of the video application within the preset time before the current time, the historical use accumulated time of the video application within the preset time before the current time or the last use time of the video application.
5. The video recommendation method according to claim 4, wherein said step of performing multiple rounds of dialog with the user according to a preset multiple round of dialog algorithm to obtain the user's search intention comprises:
selecting a word slot from word slots which are not filled with slot values in a preset word slot combination as a word slot to be filled;
determining a corresponding answer of the word slot to be filled according to a preset word slot and dialect mapping relation, and feeding back the answer to a user so that the user feeds back voice response according to the answer;
extracting at least one slot value from the voice response fed back by the user;
filling the obtained slot values into corresponding word slots in the word slot combination;
judging whether word slots with unfilled slot values exist in the word slot combination;
if yes, returning to the step of selecting one word slot from word slots which are not filled with slot values in the preset word slot combination as a word slot to be filled;
and if not, acquiring the search intention of the user according to the slot value of each word slot in the word slot combination.
6. The video recommendation method according to claim 5, wherein the step of obtaining the user identity information when receiving the video recommendation command triggered by the user comprises:
when a video recommendation voice instruction triggered by a user is received, acquiring voice data corresponding to the voice instruction;
performing voiceprint calculation on the voice data to obtain voiceprint characteristics;
and obtaining user identity information corresponding to the voiceprint characteristics according to a preset mapping relation between the user identity information and the voiceprint characteristics.
7. The video recommendation method according to claim 6, wherein said step of performing voiceprint calculation on said voice data and obtaining voiceprint features comprises:
acquiring the frequency, amplitude and speech rate of the voice data;
correspondingly acquiring a weight corresponding to the frequency, a weight corresponding to the amplitude and a weight corresponding to the speech rate of the voice data according to a preset mapping relation between the frequency and the weight, a preset mapping relation between the amplitude and the weight and a preset mapping relation between the speech rate and the weight;
and calculating the sum of the weight corresponding to the frequency, the weight corresponding to the amplitude and the weight corresponding to the speech speed as the voiceprint characteristics corresponding to the voice data.
8. The video recommendation method according to claim 7, wherein the step of obtaining user identity information when receiving a video recommendation instruction triggered by a user comprises:
when a video recommendation instruction triggered by a user is received, acquiring a current user image;
and carrying out face recognition on the current user image to acquire user identity information.
9. A terminal, characterized in that the terminal comprises a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the video recommendation method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the video recommendation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011235670.3A CN112423038A (en) | 2020-11-06 | 2020-11-06 | Video recommendation method, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011235670.3A CN112423038A (en) | 2020-11-06 | 2020-11-06 | Video recommendation method, terminal and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112423038A true CN112423038A (en) | 2021-02-26 |
Family
ID=74780568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011235670.3A Pending CN112423038A (en) | 2020-11-06 | 2020-11-06 | Video recommendation method, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112423038A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688260A (en) * | 2021-08-31 | 2021-11-23 | 维沃移动通信有限公司 | Video recommendation method and device |
| CN114283032A (en) * | 2021-11-25 | 2022-04-05 | 青岛海尔科技有限公司 | Shoe cabinet management method, device and shoe cabinet |
| CN118296183A (en) * | 2024-06-05 | 2024-07-05 | 南京奇果智能科技有限公司 | Short video intelligent recommendation system and method based on interest modeling classification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008153872A (en) * | 2006-12-15 | 2008-07-03 | Dainippon Printing Co Ltd | Program recording system using one-segment, program recording method, and server |
| CN107357875A (en) * | 2017-07-04 | 2017-11-17 | 北京奇艺世纪科技有限公司 | A kind of voice search method, device and electronic equipment |
| CN109992371A (en) * | 2017-12-29 | 2019-07-09 | 广东欧珀移动通信有限公司 | Applied program processing method, device, electronic equipment, computer readable storage medium |
| CN110059224A (en) * | 2019-03-11 | 2019-07-26 | 深圳市橙子数字科技有限公司 | Video retrieval method, device, equipment and the storage medium of projector apparatus |
| CN111698562A (en) * | 2019-03-12 | 2020-09-22 | 青岛海尔多媒体有限公司 | Control method and device of television equipment, television equipment and storage medium |
-
2020
- 2020-11-06 CN CN202011235670.3A patent/CN112423038A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008153872A (en) * | 2006-12-15 | 2008-07-03 | Dainippon Printing Co Ltd | Program recording system using one-segment, program recording method, and server |
| CN107357875A (en) * | 2017-07-04 | 2017-11-17 | 北京奇艺世纪科技有限公司 | A kind of voice search method, device and electronic equipment |
| CN109992371A (en) * | 2017-12-29 | 2019-07-09 | 广东欧珀移动通信有限公司 | Applied program processing method, device, electronic equipment, computer readable storage medium |
| CN110059224A (en) * | 2019-03-11 | 2019-07-26 | 深圳市橙子数字科技有限公司 | Video retrieval method, device, equipment and the storage medium of projector apparatus |
| CN111698562A (en) * | 2019-03-12 | 2020-09-22 | 青岛海尔多媒体有限公司 | Control method and device of television equipment, television equipment and storage medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688260A (en) * | 2021-08-31 | 2021-11-23 | 维沃移动通信有限公司 | Video recommendation method and device |
| CN113688260B (en) * | 2021-08-31 | 2025-02-14 | 维沃移动通信有限公司 | Video recommendation method and device |
| CN114283032A (en) * | 2021-11-25 | 2022-04-05 | 青岛海尔科技有限公司 | Shoe cabinet management method, device and shoe cabinet |
| CN118296183A (en) * | 2024-06-05 | 2024-07-05 | 南京奇果智能科技有限公司 | Short video intelligent recommendation system and method based on interest modeling classification |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112423038A (en) | Video recommendation method, terminal and storage medium | |
| US11176453B2 (en) | System and method for detangling of interleaved conversations in communication platforms | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| US20200070348A1 (en) | Article searching method and robot thereof | |
| CN107871001B (en) | Audio playing method and device, storage medium and electronic equipment | |
| CN110069724A (en) | The quick jump method of application program, device, electronic equipment and storage medium | |
| CN110472136B (en) | Query result pushing method and device, storage medium and computer equipment | |
| KR101694727B1 (en) | Method and apparatus for providing note by using calculating degree of association based on artificial intelligence | |
| CN112532507B (en) | Method and device for presenting an emoticon, and for transmitting an emoticon | |
| CN111540355B (en) | Personalized setting method and device based on voice assistant | |
| CN110457454A (en) | A kind of dialogue method, server, conversational system and storage medium | |
| CN112052784A (en) | Article searching method, device, equipment and computer readable storage medium | |
| CN112579944A (en) | Page jump processing method and device and electronic equipment | |
| CN109558531A (en) | News information method for pushing, device and computer equipment | |
| CN105718239B (en) | A kind of method and apparatus of voice input | |
| CN110110146A (en) | Video clip searching method, device, medium and equipment based on artificial intelligence | |
| CN109697349A (en) | Terminal unlock method, device, computer equipment and storage medium | |
| CN116016421A (en) | Method, computing device readable storage medium, and computing device for facilitating media-based content sharing performed in a computing device | |
| CN106356056B (en) | Audio recognition method and device | |
| CN112417107A (en) | Information processing method and device | |
| KR101678779B1 (en) | Method for recommending contents using metadata and apparatus for performing the method | |
| CN118245589B (en) | Task type dialogue method, storage medium and computer device | |
| CN110929014B (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| CN110456920A (en) | Semantic analysis-based content recommendation method and device | |
| CN112825256B (en) | Guiding method, device, equipment and computer storage medium for recording voice packet function |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210226 |