CN117311839A - Play control method, device, equipment and storage medium - Google Patents
Play control method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117311839A CN117311839A CN202311116832.5A CN202311116832A CN117311839A CN 117311839 A CN117311839 A CN 117311839A CN 202311116832 A CN202311116832 A CN 202311116832A CN 117311839 A CN117311839 A CN 117311839A
- Authority
- CN
- China
- Prior art keywords
- playing
- requirement information
- text
- play
- information
- 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 70
- 238000004458 analytical method Methods 0.000 claims abstract description 126
- 238000003058 natural language processing Methods 0.000 claims abstract description 27
- 230000015654 memory Effects 0.000 claims description 33
- 230000002452 interceptive effect Effects 0.000 claims description 20
- 230000003993 interaction Effects 0.000 description 12
- 230000009471 action Effects 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000003672 processing method Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/445—Program loading or initiating
- G06F9/44505—Configuring for program initiating, e.g. using registry, configuration files
- G06F9/4451—User profiles; Roaming
Abstract
The present disclosure provides a play control method, a device, equipment and a storage medium, wherein the play control method includes: receiving playing requirement information; carrying out slice analysis on the playing target according to the playing requirement information so as to determine a slice analysis result; generating a first Prompt text based on the slice analysis result and the playing requirement information; inputting the first promt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first promt text; and controlling the playing of the playing target based on the playing strategy. The present disclosure may provide a user with more accurate, flexible, and personalized play control. That is, the user can obtain a playing strategy suitable for himself at the slice level of the playing target according to personal preference, thereby improving the individuation degree of the playing experience and better meeting the individuation requirement.
Description
Technical Field
The present disclosure relates to the field of playback control technologies, and in particular, to a playback control method, apparatus, device, and storage medium.
Background
With the rapid development and widespread use of video content, there is an increasing demand for viewing video on various platforms. However, the individualization and diversity requirements of the viewing experience have resulted in conventional fixed play speed approaches that do not fully satisfy the needs of the user.
There are some personalized video playing speed methods that provide different playing speed options according to user preferences and viewing habits. However, it generally provides only a fixed play speed option, and does not allow adaptive play control according to user preferences and feedback, resulting in an unsatisfactory viewing experience.
Disclosure of Invention
In view of this, in order to solve the above technical problems, the present disclosure provides a play control method, apparatus, device, and storage medium.
According to a first aspect of an embodiment of the present disclosure, there is provided a play control method, including:
receiving playing requirement information;
performing slice analysis on the playing target according to the playing requirement information to determine a slice analysis result;
generating a first Prompt text based on the slice analysis result and the play requirement information;
inputting the first Prompt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first Prompt text;
and controlling the playing of the playing target based on the playing strategy.
Optionally, the receiving the playing requirement information includes:
responding to the setting operation for the playing target, and popping up an interactive interface; the interactive interface comprises an information input inlet for inputting the playing requirement information;
And receiving the playing requirement information based on the information input inlet.
Optionally, the information input portal includes at least one of:
and a demand information input box corresponding to the playing demand information, wherein the demand information options corresponding to the playing demand information.
Optionally, the performing slice analysis on the playing target according to the playing requirement information to determine a slice analysis result includes:
generating a second Prompt text according to the playing requirement information;
inputting the second Prompt text into a preset analysis platform, so that the preset analysis platform performs slice analysis on the playing target based on the second Prompt text to determine the slice analysis result.
Optionally, the inputting the second promt text into the preset analysis platform, so that the preset analysis platform performs slice analysis on the playing target based on the second promt text to determine the slice analysis result, including:
acquiring text information corresponding to the playing target;
and inputting the second Prompt text into the preset analysis platform, so that the preset analysis platform performs slicing analysis on the text information based on the second Prompt text to determine the slicing analysis result.
Optionally, the playing policy includes a correspondence between at least one time period and at least one sub-playing policy, where the at least one time period corresponds to the at least one sub-playing policy one by one, and the time period is a time period of a minute level.
Optionally, the playing target includes a video to be played and/or an audio to be played.
According to a second aspect of the embodiments of the present disclosure, there is provided a play control device, including:
the receiving module is used for receiving the playing requirement information;
the determining module is used for carrying out slice analysis on the playing target according to the playing requirement information so as to determine a slice analysis result;
the method is also used for generating a first Prompt text based on the slice analysis result and the play requirement information;
the method further comprises the steps of inputting the first Prompt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first Prompt text;
and the control module is used for controlling the playing of the playing target based on the playing strategy.
According to a third aspect of embodiments of the present disclosure, there is provided an electronic device comprising:
A processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to perform the play control method as described in the first aspect.
According to a fourth aspect of embodiments of the present disclosure, there is provided a non-transitory computer-readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform the play control method as described in the first aspect.
The technical scheme provided by the embodiment of the disclosure can comprise the following beneficial effects: in the method, the scenario of the playing target can be subjected to slicing analysis based on the playing requirement information of the user, and then the playing strategy of the playing target is adaptively determined based on the slicing analysis result and the playing requirement information, so that the playing of the playing target is controlled by the playing strategy, and more accurate, flexible and personalized playing control can be provided for the user. That is, the user can obtain a playing strategy suitable for himself at the slice level of the playing target according to personal preference, thereby improving the individuation degree of the playing experience and better meeting the individuation requirement.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a flowchart illustrating a play control method according to an exemplary embodiment.
Fig. 2 is a schematic diagram of a play control interface shown according to an exemplary embodiment.
FIG. 3 is a schematic diagram of an interactive interface shown according to an exemplary embodiment.
Fig. 4 is a block diagram illustrating a play control device according to an exemplary embodiment.
Fig. 5 is a block diagram of an electronic device, shown in accordance with an exemplary embodiment.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods of some embodiments of the present disclosure.
The embodiment of the disclosure provides a play control method. According to the method, the scenario of the playing target can be subjected to slicing analysis based on the playing requirement information of the user, and then the playing strategy of the playing target is adaptively determined based on the slicing analysis result and the playing requirement information, so that the playing of the playing target is controlled by the playing strategy, and more accurate, flexible and personalized playing control can be provided for the user. That is, the user can obtain a playing strategy suitable for himself at the slice level of the playing target according to personal preference, thereby improving the individuation degree of the playing experience and better meeting the individuation requirement.
In one exemplary embodiment, a play control method is provided, which is applicable to an electronic device. Referring to fig. 1, the method may include:
s110, receiving playing requirement information;
s120, carrying out slice analysis on the playing target according to the playing requirement information so as to determine a slice analysis result;
s130, generating a first Prompt text based on a slice analysis result and play requirement information;
s140, inputting the first promt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first promt text;
s150, controlling the playing of the playing target based on the playing strategy.
In step S110, the play requirement information may include play preferences, comments or suggestions, such as, but not limited to, skipping a specific actor, playing only a certain character, skipping a suspense scenario, a required play speed, and the like. That is, in this step, the user may specify a favorite or dislike character, episode, or specific period of time, or express various play demands such as preference for play speed.
The user may directly input the playing requirement information to the electronic device, for example, the user may input the playing requirement information through a touch display screen of the electronic device. The user may also input the play requirement information to the electronic device through other devices, for example, the user may input the play requirement information to the electronic device through a remote controller. Of course, in addition to the above-described manner, the user may input the playing requirement information to the electronic device in other manners, so that the electronic device receives the playing requirement information, which is not limited.
In step S120, the playing target may include audio to be played, video to be played, or other targets to be played, which is not limited.
In this step, after receiving the play requirement information for the play target, the electronic device may perform slice analysis on the play target based on the play requirement information. That is, the electronic device may perform slice level analysis on the scenario of the play target based on the play requirement information, so as to obtain a slice analysis result corresponding to the play requirement information.
It should be noted that, by analyzing the content of the playing target by using scenario analysis technology (such as algorithms including scene recognition, scenario promotion analysis, and role relationship, etc.), analysis including aspects of scene change, scenario development, role interaction, etc., the development and gist of the scenario of the playing target can be deeply understood.
In the step, the electronic device can analyze the content focused in the playing requirement information to the slice level of the playing target by using the scenario analysis technology, so as to obtain the slice analysis results in the aspects of scene change, plot development, role interaction and the like related to the playing requirement information, thereby facilitating the subsequent control of the playing target. The slice analysis results may include slices based on information such as characters, scenes, or story types, among others.
In step S130, after the electronic device obtains the slice analysis result corresponding to the play requirement information, the slice analysis result and the play requirement information may be combined to generate a corresponding promt text, which may be recorded as a first promt text.
The Prompt text typically includes a question or requested text Prompt, which is input text for directing a natural language processing model (e.g., a GPT model) to generate corresponding content.
In step S140, after the electronic device obtains the first promt text generated based on the slice analysis result corresponding to the play requirement information, the first promt text may be input to a corresponding preset natural language processing model (GPT (generating Pre-trained Transformer) model). The preset GPT model can output a corresponding playing strategy based on the received first Prompt text so as to guide the playing of the playing target in the follow-up process. Moreover, the preset GPT model in the step has the autonomous learning capability, and not only can the playing strategy corresponding to the first Prompt text output be based, but also the autonomous learning can be performed based on the first Prompt text input each time so as to know the playing habit of the user, so that a more proper playing strategy can be provided for the user along with the increase of the use frequency of the user.
The GPT model is a deep learning model which is trained by available data and is generated by texts and is different from a small model which is focused on a specific task such as go playing or machine translation, and the GPT model is more similar to the brain of a human being, has two attributes of large-scale and pre-training, can be pre-trained on massive general data, and can greatly improve generalization, universality, practicability and the like of the model.
In step S150, after the electronic device obtains the playing policy, the playing of the playing target can be controlled based on the playing policy, so that the playing of the playing target can better meet the playing requirement of the user, thereby improving the personalized playing experience of the user.
The playing policy may include a correspondence between at least one time period and at least one sub-playing policy, where the at least one time period corresponds to the at least one sub-playing policy one by one. That is, each time period in the play policy may configure a corresponding sub-play policy to better provide finer play control for the user. For example, a play policy may include adjusting the play speed over a particular period of time to focus on character conversations, important episodes, or portions of interest to the user.
The time period in the playing strategy can be a time period of a minute level, so that the refinement degree of playing control is better improved, and personalized playing requirements are better met.
The playing strategy output by the preset GPT model can be applied to a video player to realize self-adaptive viewing experience. And dividing the video to be played according to different time periods according to the playing strategy, and associating the video with the corresponding playing speed. Then, the video player can automatically adjust the playing speeds of different time periods in the video to be played so as to improve the quality of the viewing experience. For example, the video player may automatically adjust the play speed during a key scene, character conversation, or user preferred time period according to the direction of the play policy.
In addition, in the method, the video player of the electronic device can also monitor whether the user inputs a new playing requirement in real time, and can dynamically adjust the video to be played (namely, the part which is not played and needs to be played in the video) according to the received new playing requirement so as to provide more optimized viewing experience.
The method provides a self-adaptive play strategy generation method, which is used for analyzing a play target by slicing based on play requirement information input by a user, so that analysis and understanding of scenario by electronic equipment are realized. And then generating an appropriate playing strategy based on the playing requirement information and the slice analysis result so as to control the playing of the playing target, thereby improving the viewing experience.
In addition, the play policy may divide the play targets in time periods on the order of minutes, so that the user may more precisely adjust and optimize the viewing experience. Each time period can be set with corresponding playing speed, caption language, skipped scene, etc. to meet the playing requirement of users in different time periods, so that the playing content accords with personal taste.
The method has flexibility and adaptability and can be applied in different scenes. Whether an online video platform (such as a video streaming platform), a mobile application program (such as a video on demand application, a video social application and the like), an intelligent device (such as an intelligent television) or other scenes for watching video content, the method can generate a proper playing strategy according to the user requirement and a preset GPT model, so that the playing experience is more personalized and comfortable.
In one exemplary embodiment, a play control method is provided, which is applicable to an electronic device. In the method, receiving the playing requirement information may include:
s210, responding to a setting operation for a playing target, and popping up an interactive interface; the interactive interface comprises an information input inlet for inputting playing requirement information;
S220, receiving playing requirement information based on the information input entrance.
In step S210, the information input entry may include a requirement information input box corresponding to the playing requirement information, or may include a requirement information option corresponding to the playing requirement information, or may include other entries for receiving the playing requirement information, which is not limited.
The setting operation refers to an operation for calling out the interactive interface. The setting operation may include a single click, a double click, a sliding operation of a setting trajectory, or the like, which is not limited.
In some embodiments of the present invention, in some embodiments,
when playing video, setting a player interface and a play control interface on a play interface of the video. The play control interface may set an option for calling the interactive interface, and the option may be, for example, a "smart speed option (shown in fig. 2). After the user clicks the "intelligent speed-doubling" option, an interactive interface can be popped up on the playing interface of the video (refer to fig. 3). The interactive interface may include an information input portal for inputting the play requirement information, and the user may input the play requirement information based on the portal.
It should be noted that, in addition to the above manner, the interactive interface may be called out in other manners, which is not limited thereto.
In step S220, when the information input portal includes a requirement information input box, the user can input the personalized requirement through the requirement information input box by typing or voice, so as to realize the input of the playing requirement information. When the information input inlet comprises the requirement information options, the user can select the required options through the requirement information options, so that the input of the playing requirement information is completed.
In some embodiments of the present invention, in some embodiments,
the information input portal may include both a demand information input box and a demand information option. The user may directly input his viewing preference, opinion or suggestion through the requirement information input box (refer to "input your play requirement information" in fig. 3), or may select the desired viewing preference, opinion or suggestion through the requirement information option (refer to "skip actor a", "see only actor B", "skip suspense scenario", "play the episode for 25 minutes, and" suspense scenario play speed set to 0.5 "in fig. 3). Such as skipping a particular actor, looking at only a certain character, skipping suspense scenario, etc.
After the user finishes inputting and selecting the playing requirement information, the user can click on the 'submit' option, and the user input and selected option can be recorded to be used as an important basis for generating the playing strategy subsequently.
Note that, the input of the play requirement information may be performed by other means than the above, and this is not limited thereto.
In the method, the user is encouraged to participate and feed back actively through setting the interactive interface, so that the user feels that the opinion and the idea are valued. The user can express own requirements through the input box, and can select own requirements through the options, so that interaction in the playing process is realized, the interaction can increase the participation degree and satisfaction degree of the user, and the acceptance degree and loyalty degree of the user to company products or services are improved.
In one exemplary embodiment, a play control method is provided, which is applicable to an electronic device. In the method, slice analysis is performed on a playing target according to playing requirement information to determine a slice analysis result, which may include:
s310, generating a second Prompt text according to the playing requirement information;
s320, inputting the second promt text into a preset analysis platform, so that the preset analysis platform performs slice analysis on the playing target based on the second promt text to determine a slice analysis result.
In step S310, after the electronic device obtains the play requirement information, the play requirement information may be processed, so as to obtain a sympt text corresponding to the play requirement information, which may be denoted as a second sympt text.
In step S320, after the electronic device obtains the second promt text, the second promt text may be input into the corresponding preset analysis platform. The preset analysis platform can carry out slice analysis on the playing target based on the second Prompt text, so that a slice analysis result is generated and output.
When the preset analysis platform performs slice analysis on the playing target based on the second Prompt text, text information (such as a script) corresponding to the playing target can be acquired first, and then the slice analysis is performed on the text information based on the second Prompt text, so that a slice analysis result is obtained.
In some embodiments of the present invention, in some embodiments,
the playing target may include a video to be played, and the preset analysis platform may perform slice analysis on the video.
In this embodiment, a large number of video data sets including various video contents such as movies, tv shows, and animations may be collected first while training the preset analysis platform. And then, carrying out slice level analysis on the target scenario by utilizing the target scenario corresponding to the video and combining with the Prompt and GPT technologies, and dividing slices from aspects of characters, scenes, scenario development, scenario classification and the like to obtain scenario understanding of different slices so as to realize scenario analysis on the video.
In this embodiment, when the preset analysis platform is used later, the target scenario corresponding to the video to be played may be obtained first, and the second promt text corresponding to the playing requirement information may be input into the preset analysis platform, and the preset analysis platform may perform slice analysis on the scenario based on the second promt text, so as to obtain a slice analysis result corresponding to the playing requirement information. For example, when the playing requirement information includes information of skipping the specific actor a, 1.5 times of the non-suspense scenario, and the like, the slice analysis result may include at least the information of the slice corresponding to the specific actor a, the slice corresponding to the non-suspense scenario, and the like.
The present invention is not limited to the above-described method, and may be used to obtain a slice analysis result.
In the method, the preset analysis platform can carry out slice analysis on the playing target based on the second Prompt text corresponding to the playing requirement information, so that a slice analysis result corresponding to the playing requirement information can be obtained more accurately, targeted playing control can be carried out conveniently, and the playing experience is improved.
In one exemplary embodiment, a play control method is provided, which is applicable to an electronic device. The method may include:
S410, responding to a setting operation for a video to be played, and popping up an interactive interface; the interactive interface comprises an information input inlet for inputting playing requirement information;
s420, receiving playing requirement information based on an information input inlet;
s430, generating a second Prompt text according to the playing requirement information;
s440, acquiring a target script corresponding to the video to be played;
s450, inputting the second promt text into a preset analysis platform, so that the preset analysis platform performs slice analysis on the target scenario based on the second promt text to determine a slice analysis result;
s460, generating a first Prompt text based on the slice analysis result and the play requirement information;
s470, inputting the first promt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first promt text;
s480, controlling the playing of the playing target based on the playing strategy.
The electronic device may include a playing module, a Prompt module, a preset analysis platform, and a preset natural language processing model (e.g., LLM, large language model), the playing module may include a player module and a user interaction module, and the user interaction module may include a feedback module and a selection module.
In the method, after a user inputs setting operation for a video to be played to the electronic equipment, the user interaction module can pop up an interaction interface on a playing interface of the video to be played based on the setting operation. The interactive interface may include a demand information input box and a demand information option.
The demand information input box may correspond to the feedback module, and the demand information option may correspond to the selection module. After the user inputs the personalized demand through the demand information input box, the feedback module of the electronic equipment can receive the personalized demand. After the user selects the corresponding requirement information through the requirement information option, the selection module of the electronic equipment can receive the requirement information selected by the user.
After the electronic device obtains the user input and the selected playing requirement information, the user interaction module can transmit the requirement information to the Prompt module. The promt module may generate a corresponding second promt text based on the playing requirement information, and transmit the second promt text to a preset analysis platform.
In addition, the preset analysis platform can also acquire a target scenario corresponding to the video to be played, then the target scenario can be subjected to slice analysis based on the second Prompt text, so that a slice analysis result corresponding to the second Prompt text, namely a slice analysis result corresponding to the playing requirement information, is obtained, and then the slice analysis result is returned to the Prompt module.
After the promt module obtains the slice analysis result, the play requirement information and the slice analysis result can be combined to generate a corresponding first promt text, and then the corresponding first promt text is transmitted to a preset natural language processing model.
After the preset natural language processing model receives the first Prompt text, determining a corresponding playing strategy based on the first Prompt text, wherein the playing strategy is the playing strategy meeting the playing requirement information. That is, the preset natural language processing model may generate a play policy suitable for the viewing requirement of the user according to the input first Prompt text. These strategies may include adjusting the play speed over a particular period of time to focus on character conversations, important episodes, or portions of interest to the user.
After the preset natural language processing model determines the playing strategy, the determined playing strategy can be transmitted to the player module, so that the generated playing strategy is applied to the video player to realize self-adaptive viewing experience. The player module can automatically adjust the playing speed of the corresponding video segment in the video to be played according to the playing strategy guidance, so that the user can better understand the scenario and role interaction, and the quality of the watching experience is improved.
The player module can divide the video according to different time periods according to the playing strategy and correlate the video with the corresponding playing speed. The player module automatically adjusts the play speed within a time period of a key scene, a character dialogue, or a user preference according to the direction of the play policy.
In addition, the user interaction module of the playing module can monitor feedback and selection of a user in real time, and dynamically adjust the video to be played according to the playing requirement information input and/or selected by the user so as to provide more optimized watching experience.
Among other things, the play policy may include, for example, the following information:
wherein,
strategy (plural form strategies): a play strategy array comprising a plurality of time periods and corresponding play strategies;
time: a time period range, representing a play strategy within a specific time range, defines a time period with a start time and an end time of a minute level.
playbackspeed: play speed, which means the play speed applied during the period, is a floating point value, e.g., 1.0 means normal speed, 1.5 means 1.5 times speed;
subtitlelanguage: a caption language, which represents the caption language displayed in the period of time, may be a language code, such as "en" represents english, and "fr" represents french;
scene_labels: scene tags representing a specific type of scene, for example intro representing a pre-playing scene, dialog representing a dialog scene, action representing an action scene, intense representing a tension or stimulus scene, boring representing a boring scene, and violence representing a violence scene.
It should be noted that the above examples are for demonstration purposes only, and the actual playing strategy may be customized and extended according to the needs of the viewer and the video content, including adding more time periods and defining different scene types.
In some embodiments of the present invention, in some embodiments,
information input by the user based on the demand information input box may be denoted as feedback information (abc): movies like science fiction and action themes, and dramas like compact stimuli.
The information selected by the user based on the demand information option may be denoted as policy option (efg): it is desirable to adjust the play speed to a slower speed multiple when viewing at night.
That is, the play requirement information input by the user is exemplified as follows:
feedback information: movies like science fiction and action themes, drama like compact stimulus;
policy options: it is desirable to adjust the play speed to a slower speed multiple when viewing at night.
Based on the above-mentioned play requirement information (feedback information and policy options), a corresponding second promt text may be generated, examples of which are as follows:
User feedback information: movies like science fiction and action themes, drama like compact stimulus;
policy options: the playing speed is adjusted to be slower when watching at night.
Then, the second Prompt text is input to a preset analysis platform, so that a corresponding slice analysis result can be obtained, and the example is as follows:
slice 1: the science experiment accidentally causes huge explosion and the scenario is tense;
slice 2: the main angle is unfolded to fly high altitude, the scene is shocked, and the scenario is compact;
slice 3: terrorist alien organisms invade the earth and are in intense combat situations.
Then, the slice analysis result and the play requirement information are combined into a new first campt text, and the example is as follows:
slice 1: the science experiment accidentally causes huge explosion and the scenario is tense;
slice 2: the main angle is unfolded to fly high altitude, the scene is shocked, and the scenario is compact;
slice 3: terrorist alien organisms invade the earth, and strenuous combat situations;
user feedback information: movies like science fiction and action themes, drama like compact stimulus;
policy options: the playing speed is adjusted to be slower when watching at night.
Finally, the first promt text is input to a preset GPT model, and the preset GPT model can generate a corresponding play strategy according to the first promt text, for example, as follows:
Playing the slice 1, and keeping the normal playing speed;
playing the slice 2, and keeping the normal playing speed;
slice 3 is played, and the playing speed is adjusted to be slower at night.
Through the above example, the user's feedback information and policy options are incorporated into the Prompt to better generate a personalized play policy to meet the user's needs for viewing experience. In the whole process, the feedback information and the strategy options play a role in guiding the model to generate the playing strategy, so that more optimized viewing experience is provided.
The playback requirement information, the first Prompt text, the second Prompt text, the slice analysis result, and the playback policy may be other than the above-described configuration, and are not limited thereto.
In the method, the user interaction module can collect experience of user feedback about current playing experience, the feedback can be actively fed back by the user, and then the Prompt module, the preset analysis platform, the preset natural language processing model and the like can be optimized and improved based on the collected user feedback. In addition, the Prompt module, the preset analysis platform and the preset natural language processing model can continuously learn according to the playing requirement information input by the user, so that the understanding capability of the Prompt module, the preset analysis platform and the preset natural language processing model is continuously improved, and more accurate personalized playing strategies can be provided for the user. The method can periodically iterate and update the Prompt module, the preset analysis platform, the preset natural language processing model and the like so as to cope with the new video content and the change of the user demand.
According to the method, personalized playing strategies including playing speed, caption language, skipped scenes and the like can be generated according to user preference and feedback, so that user viewing experience is improved. The user can adjust the playing mode according to the own requirements and preferences, so that the watching content accords with the personal taste. In addition, the method encourages the user to participate and feed back actively by providing a real-time interactive interface, so that the user feels the opinion and the idea of the user to be valued. The user can express own demands through the interactive interface, the interactivity can increase the participation degree and satisfaction degree of the user, and the acceptance degree and loyalty degree of the user to company products or services are improved. In addition, the generation of the playing strategy in the method has flexibility and adaptability, and can be applied in different scenes. Whether an online video platform, a mobile application program, an intelligent television or other scenes for watching video content, the method can generate a proper playing strategy according to user requirements and large model calculation results, so that watching experience is more personalized and comfortable.
In addition, the method can better understand the watching preference and the like of the user by using the GPT technology, so that a company can provide more accurate content recommendation and customized service to recommend film and television works, roles or plot clues which accord with the like of the user, and the relevance and the attraction of the content are improved, thereby increasing the satisfaction degree and the loyalty of the user.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. The device can be used for implementing the playing control method. For example, referring to fig. 4, the apparatus may include a receiving module 10, a determining module 20, and a control module 30.
A receiving module 10, configured to receive the play requirement information;
the determining module 20 is configured to perform slice analysis on the play target according to the play requirement information, so as to determine a slice analysis result;
the method is also used for generating a first Prompt text based on the slice analysis result and the playing requirement information;
the method comprises the steps of inputting a first Prompt text into a preset natural language processing model, and enabling the preset natural language processing model to determine a playing strategy based on the first Prompt text;
a control module 30, configured to control playing of the playing target based on the playing policy.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. Referring to fig. 4, the apparatus may include a display module 40.
A display module 40, configured to pop up an interactive interface in response to a setting operation for a play target; the interactive interface comprises an information input inlet for inputting playing requirement information;
The receiving module 10 is configured to receive the playing requirement information based on the information input entry.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. In the apparatus, the information input portal includes at least one of:
and a demand information input box corresponding to the playing demand information, and demand information options corresponding to the playing demand information.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. Referring to fig. 4, in the apparatus,
a determining module 20, configured to generate a second campt text according to the play requirement information;
inputting the second promt text into a preset analysis platform, so that the preset analysis platform performs slice analysis on the playing target based on the second promt text to determine a slice analysis result.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. Referring to fig. 4, the apparatus may include an acquisition module 50.
The obtaining module 50 is configured to obtain text information corresponding to a playing target;
the determining module 20 may be configured to input the second promt text into the preset analysis platform, so that the preset analysis platform performs slice analysis on the text information based on the second promt text to determine a slice analysis result.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. In the device, the playing strategy comprises a corresponding relation between at least one time period and at least one sub-playing strategy, wherein the at least one time period corresponds to the at least one sub-playing strategy one by one, and the time period is a time period of a minute level.
In one exemplary embodiment, a play control device is provided, which is applicable to an electronic apparatus. In the device, the playing target comprises video to be played and/or audio to be played.
In one exemplary embodiment, an electronic device is provided. The electronic device may include, but is not limited to, a notebook computer, a desktop computer, a television, a mobile phone, and the like, which may play audio and/or video.
As shown with reference to fig. 5, the electronic device 100 includes: at least one processor 101, a memory 102, at least one network interface 104, and a user interface 103. The various components in the electronic device 100 are coupled together by a bus system 105. It is understood that the bus system 105 is used to enable connected communications between these components. The bus system 105 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled in the figures as bus system 105.
The user interface 103 may include, among other things, a display, a keyboard, or a pointing device (e.g., a mouse, a trackball), a touch pad, or a touch screen, etc.
It is to be appreciated that the memory 102 in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DRRAM). The memory 102 described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
In some implementations, the memory 102 stores the following elements, executable units or data structures, or a subset thereof, or an extended set thereof: an operating system 1021, and application programs 1022.
The operating system 1021 includes various system programs, such as a framework layer, a core library layer, a driver layer, and the like, for implementing various basic services and processing hardware-based tasks. The application programs 1022 include various application programs such as a Media Player (Media Player), a Browser (Browser), and the like for implementing various application services. A program for implementing the method of the embodiment of the present application may be included in the application program 1022.
In the present embodiment, the processor 101 is configured to execute the method steps provided in the method embodiments by calling a program or an instruction stored in the memory 102, specifically, a program or an instruction stored in the application 1022.
The method disclosed in the embodiments of the present application may be applied to the processor 101 or implemented by the processor 101. The processor 101 may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in the processor 101 or instructions in the form of software. The processor 101 described above may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software elements in a decoded processor. The software elements may be located in a random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 102, and the processor 101 reads information in the memory 102, and in combination with its hardware, performs the steps of the method described above.
It is to be understood that the embodiments described herein may be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For a hardware implementation, the processing units may be implemented within one or more application specific integrated circuits (Application Specific Integrated Circuits, ASIC), digital signal processors (Digital Signal Processing, DSP), digital signal processing devices (DSP devices, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field-Programmable Gate Array, FPGA), general purpose processors, controllers, microcontrollers, microprocessors, other electronic units configured to perform the functions described herein, or a combination thereof.
For a software implementation, the techniques herein may be implemented by means of units that perform the functions herein. The software codes may be stored in a memory and executed by a processor. The memory may be implemented within the processor or external to the processor.
The terminal provided in this embodiment may execute all steps of the data processing method, so as to achieve the technical effects of the data processing method, and refer to the related description of the data processing method specifically, and for brevity, description is omitted herein.
The embodiment of the application also provides a storage medium (computer readable storage medium). The storage medium here stores one or more programs. Wherein the storage medium may comprise volatile memory, such as random access memory; the memory may also include non-volatile memory, such as read-only memory, flash memory, hard disk, or solid state disk; the memory may also comprise a combination of the above types of memories.
When one or more programs in the storage medium are executable by one or more processors, the above-described data processing method performed on the electronic device side is implemented.
The processor is configured to execute a program stored in the memory to implement the steps of the method to be executed on the electronic device side.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of function in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present application, and are not meant to limit the scope of the invention, but to limit the scope of the invention.
Claims (10)
1. A play control method, characterized in that the play control method comprises:
receiving playing requirement information;
performing slice analysis on the playing target according to the playing requirement information to determine a slice analysis result;
generating a first Prompt text based on the slice analysis result and the play requirement information;
Inputting the first Prompt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first Prompt text;
and controlling the playing of the playing target based on the playing strategy.
2. The playback control method as recited in claim 1, wherein receiving playback demand information comprises:
responding to the setting operation for the playing target, and popping up an interactive interface; the interactive interface comprises an information input inlet for inputting the playing requirement information;
and receiving the playing requirement information based on the information input inlet.
3. The play control method according to claim 2, wherein the information input portal includes at least one of:
and a demand information input box corresponding to the playing demand information, wherein the demand information options corresponding to the playing demand information.
4. The playback control method of claim 1, wherein the performing a slice analysis on the playback target according to the playback requirement information to determine a slice analysis result comprises:
generating a second Prompt text according to the playing requirement information;
Inputting the second Prompt text into a preset analysis platform, so that the preset analysis platform performs slice analysis on the playing target based on the second Prompt text to determine the slice analysis result.
5. The playback control method of claim 4, wherein the inputting the second promt text into the preset analysis platform, such that the preset analysis platform performs a slice analysis on the playback target based on the second promt text to determine the slice analysis result, comprises:
acquiring text information corresponding to the playing target;
and inputting the second Prompt text into the preset analysis platform, so that the preset analysis platform performs slicing analysis on the text information based on the second Prompt text to determine the slicing analysis result.
6. The playback control method of claim 1, wherein the playback strategy comprises a correspondence of at least one time period to at least one sub-playback strategy, wherein at least one time period corresponds one-to-one to at least one sub-playback strategy, and wherein the time period is a minute-level time period.
7. The playback control method of any one of claims 1-6, wherein the playback target comprises video to be played and/or audio to be played.
8. A play control device, characterized in that the play control device comprises:
the receiving module is used for receiving the playing requirement information;
the determining module is used for carrying out slice analysis on the playing target according to the playing requirement information so as to determine a slice analysis result;
the method is also used for generating a first Prompt text based on the slice analysis result and the play requirement information;
the method further comprises the steps of inputting the first Prompt text into a preset natural language processing model, so that the preset natural language processing model determines a playing strategy based on the first Prompt text;
and the control module is used for controlling the playing of the playing target based on the playing strategy.
9. An electronic device, the electronic device comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to perform the play control method of any one of claims 1-7.
10. A non-transitory computer readable storage medium, wherein instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the play control method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311116832.5A CN117311839A (en) | 2023-08-31 | 2023-08-31 | Play control method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311116832.5A CN117311839A (en) | 2023-08-31 | 2023-08-31 | Play control method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117311839A true CN117311839A (en) | 2023-12-29 |
Family
ID=89254407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311116832.5A Pending CN117311839A (en) | 2023-08-31 | 2023-08-31 | Play control method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117311839A (en) |
-
2023
- 2023-08-31 CN CN202311116832.5A patent/CN117311839A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220138211A1 (en) | Approximate template matching for natural language queries | |
| US10127195B2 (en) | Selective content presentation engine | |
| US9852214B2 (en) | Systems and methods for automatic program recommendations based on user interactions | |
| US9288531B2 (en) | Methods and systems for compensating for disabilities when presenting a media asset | |
| US20180277132A1 (en) | Systems and methods for increasing language accessability of media content | |
| CN110085244B (en) | Live broadcast interaction method and device, electronic equipment and readable storage medium | |
| US20200007946A1 (en) | Selectively delivering a translation for a media asset based on user proficiency level in the foreign language and proficiency level required to comprehend the media asset | |
| CN106796496A (en) | Display device and its operating method | |
| US11153655B1 (en) | Content appeal prediction using machine learning | |
| US11375287B2 (en) | Systems and methods for gamification of real-time instructional commentating | |
| US11805295B2 (en) | Selective streaming based on dynamic parental rating of content | |
| US20200154123A1 (en) | Display apparatus and method of controlling the same | |
| US11687729B2 (en) | Systems and methods for training a model to determine whether a query with multiple segments comprises multiple distinct commands or a combined command | |
| US20230343320A1 (en) | Systems and methods for adjusting dubbed speech based on context of a scene | |
| US9832526B2 (en) | Smart playback method for TV programs and associated control device | |
| US20220248089A1 (en) | Selective streaming based on dynamic parental rating of content | |
| EP3256966B1 (en) | Relevance table aggregation in a database system | |
| CN114339285A (en) | Knowledge point processing method, video processing method and device and electronic equipment | |
| CN117311839A (en) | Play control method, device, equipment and storage medium | |
| KR20220135203A (en) | Automatic recommendation music support system in streaming broadcasting | |
| US20230196033A1 (en) | Methods and systems for responding to a natural language query | |
| US20230197067A1 (en) | Methods and systems for responding to a natural language query | |
| CN114022814A (en) | Video processing method and apparatus, electronic device, and computer-readable storage medium | |
| CN117376653A (en) | Live interaction abstract generation method and device, storage medium and electronic equipment |
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 |