CN111125384B - Multimedia answer generation method and device, terminal equipment and storage medium - Google Patents

Multimedia answer generation method and device, terminal equipment and storage medium Download PDF

Info

Publication number
CN111125384B
CN111125384B CN201811295847.1A CN201811295847A CN111125384B CN 111125384 B CN111125384 B CN 111125384B CN 201811295847 A CN201811295847 A CN 201811295847A CN 111125384 B CN111125384 B CN 111125384B
Authority
CN
China
Prior art keywords
data
answer
content
information
multimedia
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811295847.1A
Other languages
Chinese (zh)
Other versions
CN111125384A (en
Inventor
高雪
陈喆
姜毅
莫智慧
陈志宇
毛书宇
王亚军
杨茜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alibaba Group Holding Ltd
Original Assignee
Alibaba Group Holding Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alibaba Group Holding Ltd filed Critical Alibaba Group Holding Ltd
Priority to CN201811295847.1A priority Critical patent/CN111125384B/en
Publication of CN111125384A publication Critical patent/CN111125384A/en
Application granted granted Critical
Publication of CN111125384B publication Critical patent/CN111125384B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B5/00Electrically-operated educational appliances
    • G09B5/06Electrically-operated educational appliances with both visual and audible presentation of the material to be studied

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a multimedia answer generating method, a device, terminal equipment and a storage medium, wherein the method comprises the following steps: analyzing content data input by a user to obtain answer content information and answer characteristic information corresponding to the content data; searching according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information; and combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information. According to the method and the device, a user can quickly obtain the material data and/or the template data according to the content data only by inputting a small amount of content data, and automatically generate the multimedia answer by using the material data and/or the template data, so that the operation is simple and convenient, and the data required by the multimedia answer is not required to be searched and edited by spending more time and energy.

Description

Multimedia answer generation method and device, terminal equipment and storage medium
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for generating multimedia answers, a terminal device, and a storage medium.
Background
With the continuous development of internet technology, more and more users are biased to obtain answers to some questions in work or life in internet products with social attributes such as forums, microblogs, question and answer communities and the like. At present, in internet products with a question and answer function, users who answer questions mainly write answers to the questions through characters, in order to improve the visual effect of the answers, part of the internet products also support inserting multimedia materials such as pictures, animations, audios and videos into the characters, and finally generated answers are only to simply arrange various materials, and materials with different data types are not synthesized into one multimedia answer, for example, a video answer file is synthesized.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: when a user makes a multimedia answer, the user needs to spend much time and energy to search and obtain materials from other channels, and then edits and synthesizes the materials by himself, so that the whole process is complicated to operate. In a long term, the enthusiasm of the user for making better visual answers can be influenced by complicated operation, the overall quality of answers of internet products with the question answering function is reduced, and the scale of active users is reduced.
Disclosure of Invention
In view of this, one of the technical problems to be solved by the embodiments of the present invention is to provide a method, an apparatus, a terminal device and a storage medium for generating multimedia answers, so as to overcome the defect of tedious operations in editing and generating multimedia answers in the prior art, and achieve the effect of quickly and conveniently generating multimedia answers with better visualization effect.
The embodiment of the invention provides a multimedia answer generating method, which comprises the following steps:
analyzing content data input by a user to obtain answer content information and answer characteristic information corresponding to the content data;
retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information;
and combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information.
Optionally, in an embodiment of the present invention, the analyzing the content data input by the user to obtain answer content information and answer feature information corresponding to the content data includes at least one of the following steps:
analyzing the content data to obtain answer format information and answer data information corresponding to the content data as answer content information corresponding to the content data;
and performing feature analysis on the content data to obtain material features matched with the multimedia answers and the content data, and taking the material features as answer feature information corresponding to the input content data.
Optionally, in an embodiment of the present invention, the analyzing the content data input by the user to obtain answer content information and answer feature information corresponding to the content data includes:
analyzing the content data and the question data corresponding to the content data to obtain the answer content information and/or the answer characteristic information corresponding to the content data and the question data.
Optionally, in an embodiment of the present invention, the retrieving according to the answer feature information to obtain material data and/or template data matched with the answer feature information includes at least one of the following steps:
sorting and/or selecting the material data according to the correlation degree of the answer characteristic information and the material data;
and sequencing and/or selecting the template data according to the correlation degree of the answer characteristic information and the template data.
Optionally, in a specific embodiment of the present invention, the template data includes at least one of insertion information, processing information, and guidance information, where:
the insertion information is used for inserting the answer content information and/or the material data into a preset data insertion position in the template data;
the processing information is used for carrying out preset data processing on answer content information and/or material data;
the guide information is used for guiding the user operation how to combine the answer content information with the material data and/or the template data.
According to still another aspect of embodiments of the present application, there is also provided a multimedia answer generating apparatus including:
the analysis module is used for analyzing the content data input by the user to obtain answer content information and answer characteristic information corresponding to the content data;
the retrieval module is used for retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information;
and the answer generating module is used for combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information.
Optionally, in an embodiment of the present invention, the parsing module includes at least one of a content parsing unit and a feature parsing unit, where:
the content analysis unit is used for carrying out content analysis on the content data to obtain answer format information and answer data information corresponding to the content data as answer content information corresponding to the content data;
the feature analysis unit is used for carrying out feature analysis on the content data to obtain material features matched with the multimedia answers and the content data, and the material features are used as answer feature information corresponding to the input content data.
Optionally, in an embodiment of the present invention, the parsing module further includes: and the question analysis unit is used for analyzing the content data and the question data corresponding to the content data to obtain the answer content information and/or the answer characteristic information corresponding to the content data and the question data.
Optionally, in an embodiment of the present invention, the retrieving module includes at least one of a material retrieving unit and a template retrieving unit, where:
the material retrieval unit is used for sorting and/or selecting the material data according to the correlation degree of the answer characteristic information and the material data;
the template retrieval unit is used for sorting and/or selecting the template data according to the correlation degree of the answer characteristic information and the template data.
Optionally, in an embodiment of the present invention, the template data includes at least one of insertion information, processing information, and guiding information, where:
the insertion information is used for inserting the answer content information and/or the material data into a preset data insertion position in the template data;
and the processing information is used for carrying out preset data processing on the answer content information and/or the material data.
The guide information is used for guiding the user operation how to combine the answer content information with the material data and/or the template data.
According to another aspect of the embodiments of the present application, there is also provided a terminal device, including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the multimedia answer generation method.
According to still another aspect of embodiments of the present application, there is also provided a storage medium having a computer program stored thereon, where the computer program is executed by a processor to implement the corresponding operations of the multimedia answer generation method as described above.
As can be seen from the above technical solutions, in the multimedia answer generation method, apparatus, terminal device and storage medium provided in the embodiments of the present invention, content data input by a user is analyzed to obtain answer content information and answer feature information corresponding to the content data; then, retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information; and combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information. Therefore, the user can quickly obtain the material data and/or the template data according to the content data by only inputting a small amount of content data, and automatically generate the multimedia answer by using the material data and/or the template data, so that the operation is simple and convenient, and the data required by the multimedia answer is not required to be searched and edited by spending more time and energy.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present invention, and it is also possible for a person skilled in the art to obtain other drawings based on the drawings.
Fig. 1 is a flowchart illustrating a method for generating multimedia answers according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for generating multimedia answers according to another embodiment of the present invention;
FIG. 3 is a block diagram of a multimedia answer generating device according to an embodiment of the present invention;
FIG. 4 is a block diagram of a multimedia answer generating device according to another embodiment of the present invention;
fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments obtained by a person skilled in the art based on the embodiments of the present invention shall fall within the scope of the protection of the embodiments of the present invention.
Fig. 1 is a schematic flowchart of a multimedia answer generation method according to an embodiment of the present invention, which can be applied to terminal devices such as a computer, a mobile phone, a projector, a video camera, a VR device, and an AR device. As shown in fig. 1, a multimedia answer generating method includes:
step S101, analyzing the content data input by the user to obtain answer content information and answer characteristic information corresponding to the content data.
In this embodiment, the content data is data input by the user in the local terminal device to answer a specific question, and the data format, the data size, and the input mode of the content data are not limited, and can be set by the user according to the requirement in the actual application.
Alternatively, the data format of the content data may include at least one of text, picture, animation, audio, and video. For example, to answer a question, a user may input a text and a plurality of pictures on the answer editing interface.
In this embodiment, the answer content information is used to present all or part of the content included in the content data in the generated multimedia answer.
Optionally, the answer content information may include all or part of content data input by the user, and/or data obtained by processing the content data input by the user using a preset content analysis model. For example, after a text segment input by a user is analyzed by using a semantic analysis model, a content summary corresponding to the text segment can be obtained, and the content summary is used as answer content information.
In this embodiment, the answer feature information is used to identify conditions that need to be satisfied by other data that can be used to generate the multimedia answer, except for the answer content information, and specific conditions may be set by those skilled in the art according to the requirements in practical application.
In this embodiment, the main body of the analysis processing of the content data is not limited. For example, the parsing may be performed by the local terminal device; or the local terminal device uploads the content data to a network server through a network, and the network server analyzes the content data.
In this embodiment, in order to enable the multimedia answer to more accurately solve the corresponding question, step S101 may further include: analyzing the content data input by the user and the question data corresponding to the content data to obtain answer content information and/or answer characteristic information corresponding to the content data and the question data.
For example, when the question data includes "who are your favorite sports stars? "when the content data that the user has input includes" lina and sunun ", the answer content information and/or the answer feature information obtained only from the content data may include" lina "and" sunun ", and since" sunun "does not belong to" sports stars "and occurs inaccurately in the answer, it may be further determined that the answer content information and/or the answer feature information includes only" lina "in conjunction with the question data.
In this embodiment, the parsing of the content data input by the user may be implemented by any appropriate manner according to actual needs by those skilled in the art. For example, a service of NLP new version of chinese proper name recognition (nlpc _ nerl _ plus) may be invoked, a semantic analysis technique in Natural Language Processing (NLP) technology is used, keywords included in content data in a text format are extracted, and answer content information and/or answer feature information are obtained from the keywords.
And S102, retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information.
In this embodiment, the material data may be used to present, in the generated multimedia answer, content other than all or part of the content included in the content data, that is, the content included in the content data and the material data may be used together to answer a specific question.
The data format of the material data is not limited, and the material data may include at least one of text, picture, animation, audio, and video. For example, the text material data may be classical speech lines, the audio material data may be songs or voice-overs, the picture material data may be photos or stickers, the animation material may be special-effect animations, and the video material data may be shot short videos or movie video clips.
In this embodiment, the template data may be used to determine a presentation manner of the answer content information and/or the material data in the generated multimedia answer.
Optionally, at least one template data may be generated in advance according to the data type of the multimedia answer, so that after the content information and/or the material data are combined with the template data, the multimedia answer corresponding to the data type may be generated. For example, when the template data is a video editing template, the content information and/or the material data may be added to the video editing template as a material required for video editing, and the multimedia answer in the video format is generated after being synthesized with the template data.
In this embodiment, the storage location, the obtaining manner, and the number of the material data and/or the template data are not limited. For example, the material data and/or the template data may be obtained directly from the local terminal device, or may be obtained by data transmission with other terminal devices and/or a network server.
In this embodiment, the search according to the answer feature information may be implemented by those skilled in the art in any appropriate manner according to actual needs. For example, all material data and/or template data meeting answer feature information can be obtained in a tag screening manner; a preset amount of optimal material data and/or template data can be obtained through the recommendation algorithm model.
And step S103, combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information.
In this embodiment, all or part of the answer content information may be used to combine with all or part of the material data and/or the template data obtained in step 102, and the data format of the media answer is not limited, and may be set according to the requirement in the actual application.
In this embodiment, generating the multimedia answer may be implemented by those skilled in the art in any appropriate manner according to actual needs.
For example, adaptive parameters such as text display duration, audio switching duration, text fonts, picture display style, background music and the like can be dynamically calculated by using template data for generating video multimedia answers, and then an AI and FFMPEG video editing Software Development Kit (SDK) is called to fuse material data including information such as pictures, audio and text with answer content information to generate a multimedia answer in a video format.
For another example, when the format of the multimedia answer selected by the user is audio and the content information of the answer and the material data each include a segment of text, the two segments of text may be merged first, and then the text is converted into the corresponding audio by using the speech synthesis technology to generate the multimedia answer in the audio format.
As can be seen from the above embodiments of the present invention, in the present invention, first, content data input by a user is analyzed to obtain answer content information and answer feature information corresponding to the content data; then, retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information; and combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information. Therefore, the user can quickly obtain the material data and/or the template data according to the content data by inputting a small amount of content data, and automatically generate the multimedia answer by using the material data and/or the template data, so that the operation is simple and convenient, and the data required by the multimedia answer is not required to be searched and edited by spending more time and energy.
Fig. 2 is a schematic flowchart of a multimedia answer generation method according to another embodiment of the present invention, which can be applied to terminal devices such as a computer, a mobile phone, a projector, a video camera, a VR device, and an AR device. As shown in fig. 2, a multimedia answer generating method includes:
step S201, content analysis is carried out on content data input by a user, and answer format information and answer data information corresponding to the content data are obtained and serve as answer content information corresponding to the content data; and performing feature analysis on the content data to obtain material features matched with the multimedia answer to be generated and the content data, and taking the material features as answer feature information corresponding to the input content data.
In this embodiment, since data processing is performed on the content information of the answer when the multimedia answer is generated, and the processing used for data with different format attributes is different, for example, a voice processing technology is used for generating the multimedia answer in an audio format, and an image processing technology is used for generating the multimedia answer in a video format, for convenience of subsequent data processing, when the content data is analyzed, the corresponding answer format information and answer data information can be obtained at the same time.
Specifically, the answer format information may be used to identify format-related attributes of the answer data information. Such as data type, data size, picture size, play duration, etc.
Specifically, the answer data information is data that can be combined with the material data and/or the template data, that is, the content of the content data presented in the multimedia answer can be determined according to the answer data information.
In this embodiment, since the user may pre-select some characteristics of the multimedia answer in addition to the content data before generating the multimedia answer, for example, the data format of the multimedia answer is determined to be video or audio, and there may be a difference in the data required for generating the multimedia answer including different characteristics and the data processing technology, in order to obtain the material data and/or the template data more suitable for the user's requirement, the answer characteristic information may be obtained according to the multimedia answer and the content data.
In particular, the material characteristics are used to identify attributes of material data and/or template data that may be used to generate the multimedia answer. For example, a "rural style" and "European style" may be used to identify style attributes; the format-related attributes are identified using "video", "picture", "audio".
And step S202, retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information.
In this embodiment, in order to reduce the machine computation amount in the retrieval process, the corresponding material characteristics may be labeled and stored in advance according to the attribute of each piece of material data and/or template data, so that when the retrieval is performed according to the answer characteristic information, the retrieval matching may be performed on the piece of material data and/or template data according to the multimedia answer and the material characteristics matched with the content data.
In this embodiment, in order to facilitate the user to check or select the material data and/or the template data according to the search result, step S202 may include: sorting and/or selecting the material data according to the correlation degree of the answer characteristic information and the material data; and/or sorting and/or selecting the template data according to the correlation degree of the answer characteristic information and the template data.
Specifically, the relevance values corresponding to the answer feature information and the material data and/or the template data can be calculated according to a preset relevance value calculation rule; and then sorting and/or selecting the material data and/or the template data according to the relevance value.
Optionally, when the material data and/or the template data are/is selected according to the correlation value, the selection number or the correlation threshold range may be preset according to actual needs.
For example, picture data and corresponding text description data in the internet can be mined in advance, and a correlation numerical calculation rule is constructed; when the material data in the picture format is retrieved, the text description corresponding to the answer characteristic information can be obtained firstly; then, respectively calculating correlation values between the plurality of picture data and the answer characteristic information text description by using a correlation value calculation rule, and comparing the calculated correlation values with a preset threshold value; if the relevance value of the material data is greater than or equal to the predetermined threshold, the material data can be used as the material data matched with the answer feature information.
Optionally, the correlation value calculation rule may be subjected to machine learning, that is, as the calculation amount is accumulated, part of parameters in the correlation value calculation rule may be continuously optimized to obtain a more accurate search result.
Step S203, combining the answer content information with the material data and/or the template data, and generating a multimedia answer including the answer content information.
In this embodiment, in order to determine the combination position of the data, the template data may include insertion data, and the insertion information is used to insert the answer content information and/or the material data into a preset data insertion position in the template data.
Optionally, the insertion information may include at least one preset data insertion position and corresponding data insertion conditions, and when the answer content information and/or the material data satisfy the insertion data condition, the answer content information and/or the material data may be synthesized to the data insertion position of the template data, so as to generate the multimedia answer by combining with the template data.
For example, if the template data is a picture, and the lower portion of the picture includes a preset position into which text can be inserted, text included in the answer content information can be inserted into the preset position, and image synthesis is performed to generate a multimedia answer.
In this embodiment, in order to determine the data presentation manner in the multimedia answer, the template data may further include processing information, and the processing information is used to perform preset data processing on the answer content information and/or the material data.
Optionally, the processing information may include at least one data processing rule, and the data processing rule may be used to perform corresponding data processing on the answer content information and/or the material data, and generate the multimedia answer. Wherein, the data processing may comprise: at least one of a play order, a play speed, a play duration, a play start time, a play end time, a volume, a tone, a timbre, a visual special effect, a position in an image area, a filter, a size, a color, a font, and a rotation angle of the answer content information and/or the material data is determined.
For example, pictures included in the answer content information may be processed into an animation of fading in and out using a data processing rule of processing picture data into a fading in and out effect in the template data.
Optionally, in order to control the size of the template data and perform diversified processing, the processing information may include at least one service invocation interface, which is used to perform corresponding data processing on the answer content information and/or the material data in an interface invocation manner and generate the multimedia answer.
For example, when the answer content information includes a text, the template data may be used to call a speech synthesis technology of an Artificial Intelligence (AI) open platform to perform speech synthesis on the text, so as to obtain a corresponding audio, and convert the text into a real-person-like speech rich in emotional colors.
In this embodiment, in order to facilitate the user to perform a better custom editing operation, the template data may further include guiding information, where the guiding information is used to guide the user to operate how to combine the answer content information with the material data and/or the template data.
Specifically, the corresponding guiding information can be obtained and presented to the user according to the detection result of the user operation, so as to prompt the user to perform the relevant operation of generating the multimedia answer. The guidance information may be presented to the user by at least one of voice guidance, text guidance, image guidance, video guidance. The setting of the guidance information corresponding to the operation detection result may be set by any appropriate setting by those skilled in the art according to actual requirements, and the embodiment of the present invention is not limited thereto.
The guidance information corresponding to different material data, template data and answer content information may be different, for example, only video data with a playing time of 20 seconds may be inserted into the template data, and if it is detected that the normal playing time of the video material data is 30 seconds, guidance information "shorten the playing time to 20 seconds" may be given; if it is detected that the normal play time of the video material data is 10 seconds, the guidance information "the video material data with the play time of 10 seconds can be inserted" may be given.
It can be seen from the above embodiments of the present invention that, the present invention can obtain answer feature information according to multimedia answers and content data to obtain material data and/or template data that better meet user requirements; when the content data is analyzed, the corresponding answer format information and the corresponding answer data information can be obtained at the same time, so that the data processing efficiency during the subsequent data synthesis is facilitated; through sorting and/or selection, the user can conveniently view or select the material data and/or the template data.
Fig. 3 is a block diagram of a multimedia answer generating device according to an embodiment of the present invention, where the multimedia answer generating device of the embodiment may include:
the parsing module 301 is configured to parse content data input by a user to obtain answer content information and answer feature information corresponding to the content data.
And the retrieval module 302 is configured to perform retrieval according to the answer feature information to obtain material data and/or template data matched with the answer feature information.
The answer generating module 303 is configured to combine the answer content information with the material data and/or the template data to generate a multimedia answer including the answer content information.
The multimedia answer generating device of this embodiment is used to implement the corresponding multimedia answer generating method in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.
Fig. 4 is a block diagram of a multimedia answer generating device according to another embodiment of the present invention, where the multimedia answer generating device of this embodiment may include:
the parsing module 401 is configured to parse content data input by a user to obtain answer content information and answer feature information corresponding to the content data.
In this embodiment, the parsing module includes at least one of a content parsing unit 401a and a feature parsing unit 401b, where:
the content analysis unit 401a is configured to perform content analysis on the content data, and obtain answer format information and answer data information corresponding to the content data as answer content information corresponding to the content data.
The feature analysis unit 401b is configured to perform feature analysis on the content data, obtain material features matched with the multimedia answers and the content data, and use the material features as answer feature information corresponding to the input content data.
In this embodiment, the parsing module 401 may further include a question parsing unit 401c, configured to parse the content data and the question data corresponding to the content data to obtain answer content information and/or answer feature information corresponding to the content data and the question data.
And the retrieval module 402 is configured to perform retrieval according to the answer feature information to obtain material data and/or template data matched with the answer feature information.
In this embodiment, the retrieving module 402 may further include at least one of a material retrieving unit 402a and a template retrieving unit 402b, where:
the material retrieval unit 402a is configured to sort and/or select the material data according to the degree of correlation between the answer feature information and the material data.
The template retrieving unit 402b is configured to sort and/or select the template data according to the degree of correlation between the answer feature information and the template data.
In this embodiment, the template data includes at least one of insertion information, processing information, and guidance information, where:
the insertion information is used for inserting the answer content information and/or the material data into a preset data insertion position in the template data;
the processing information is used for carrying out preset data processing on answer content information and/or material data;
the guide information is used to guide the user operation on how to combine the answer content information with the material data and/or the template data.
And an answer generating module 403, configured to combine the answer content information with the material data and/or the template data, and generate a multimedia answer including the answer content information.
The multimedia answer generating device of this embodiment is used to implement the corresponding multimedia answer generating method in the foregoing multiple method embodiments, and has the beneficial effects of the corresponding method embodiments, which are not described herein again.
Referring to fig. 5, a schematic structural diagram of a terminal device according to an embodiment of the present invention is shown, and the specific embodiment of the present invention does not limit the specific implementation of the terminal device.
As shown in fig. 5, the terminal device may include: a processor (processor) 502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein:
the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508.
A communication interface 504 for communicating with network elements of other devices, such as other terminals or servers.
The processor 502 is configured to execute the program 510, and may specifically execute relevant steps in the foregoing graphical user interface display method embodiment.
In particular, program 510 may include program code comprising computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the invention. The terminal device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 506 for storing a program 510. The memory 506 may include high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 may specifically be used to cause the processor 502 to perform the following operations:
analyzing content data input by a user to obtain answer content information and answer characteristic information corresponding to the content data;
searching according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information;
and combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information.
In an alternative embodiment, the program 510 is further configured to cause the processor 502 to perform at least one of the following operations:
analyzing the content data to obtain answer format information and answer data information corresponding to the content data as answer content information corresponding to the content data;
and performing characteristic analysis on the content data to obtain material characteristics matched with the multimedia answers and the content data, and taking the material characteristics as answer characteristic information corresponding to the input content data.
In an alternative embodiment, the program 510 is further configured to cause the processor 502 to perform: and analyzing the content data and the question data corresponding to the content data to obtain answer content information and/or answer characteristic information corresponding to the content data and the question data.
In an alternative embodiment, the program 510 is further configured to cause the processor 502 to perform at least one of the following operations:
sorting and/or selecting the material data according to the correlation degree of the answer characteristic information and the material data;
and sorting and/or selecting the template data according to the correlation degree of the answer characteristic information and the template data.
In an alternative embodiment, the template data includes at least one of:
inserting information, which is used for inserting answer content information and/or material data into a preset data inserting position in the template data;
the processing information is used for carrying out preset data processing on the answer content information and/or the material data;
and guiding information for guiding a user operation how to combine the answer content information with the material data and/or the template data.
For specific implementation of each step in the program 510, reference may be made to corresponding steps and corresponding descriptions in units in the foregoing content display method embodiments, which are not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus (device), or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the embodiments of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

Claims (12)

1. A method for generating multimedia answers, the method comprising:
analyzing content data input by a user to obtain answer content information and answer characteristic information corresponding to the content data;
retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information;
and combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information.
2. The method of claim 1, wherein the parsing the content data inputted by the user to obtain the answer content information and the answer feature information corresponding to the content data comprises at least one of the following steps:
analyzing the content data to obtain answer format information and answer data information corresponding to the content data as answer content information corresponding to the content data;
and performing feature analysis on the content data to obtain material features matched with the multimedia answer and the content data, and taking the material features as answer feature information corresponding to the input content data.
3. The method of claim 1, wherein the parsing the content data input by the user to obtain answer content information and answer feature information corresponding to the content data comprises:
analyzing the content data and the question data corresponding to the content data to obtain the answer content information and/or the answer characteristic information corresponding to the content data and the question data.
4. The method according to claim 1, wherein the retrieving according to the answer feature information to obtain material data and/or template data matching with the answer feature information comprises at least one of:
sorting and/or selecting the material data according to the correlation degree of the answer characteristic information and the material data;
and sorting and/or selecting the template data according to the correlation degree of the answer characteristic information and the template data.
5. The method of generating multimedia answers according to claim 1, wherein said template data includes at least one of insertion information, processing information, and guidance information, wherein:
the insertion information is used for inserting the answer content information and/or the material data into a preset data insertion position in the template data;
the processing information is used for carrying out preset data processing on answer content information and/or material data;
the guide information is used for guiding the user operation how to combine the answer content information with the material data and/or the template data.
6. A multimedia answer generating apparatus, characterized in that the apparatus comprises:
the analysis module is used for analyzing the content data input by the user to obtain answer content information and answer characteristic information corresponding to the content data;
the retrieval module is used for retrieving according to the answer characteristic information to obtain material data and/or template data matched with the answer characteristic information;
and the answer generation module is used for combining the answer content information with the material data and/or the template data to generate a multimedia answer comprising the answer content information.
7. The multimedia answer generating apparatus of claim 6, wherein the parsing module comprises at least one of a content parsing unit and a feature parsing unit, wherein:
the content analysis unit is used for carrying out content analysis on the content data to obtain answer format information and answer data information corresponding to the content data as answer content information corresponding to the content data;
the feature analysis unit is used for carrying out feature analysis on the content data to obtain material features matched with the multimedia answers and the content data, and the material features are used as answer feature information corresponding to the input content data.
8. The multimedia answer generating apparatus of claim 6, wherein the parsing module further comprises:
and the question analysis unit is used for analyzing the content data and the question data corresponding to the content data to obtain the answer content information and/or the answer characteristic information corresponding to the content data and the question data.
9. The multimedia answer generating apparatus of claim 6, wherein the retrieving module comprises at least one of a material retrieving unit and a template retrieving unit, wherein:
the material retrieval unit is used for sorting and/or selecting the material data according to the correlation degree of the answer characteristic information and the material data;
the template retrieval unit is used for sorting and/or selecting the template data according to the correlation degree of the answer characteristic information and the template data.
10. The apparatus of claim 6, wherein the template data comprises at least one of insertion information, processing information, and guidance information, wherein:
the insertion information is used for inserting the answer content information and/or the material data into a preset data insertion position in the template data;
the processing information is used for carrying out preset data processing on answer content information and/or material data;
the guide information is used for guiding the user operation how to combine the answer content information with the material data and/or the template data.
11. A terminal device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the multimedia answer generation method according to any one of claims 1-5.
12. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-5.
CN201811295847.1A 2018-11-01 2018-11-01 Multimedia answer generation method and device, terminal equipment and storage medium Active CN111125384B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811295847.1A CN111125384B (en) 2018-11-01 2018-11-01 Multimedia answer generation method and device, terminal equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811295847.1A CN111125384B (en) 2018-11-01 2018-11-01 Multimedia answer generation method and device, terminal equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111125384A CN111125384A (en) 2020-05-08
CN111125384B true CN111125384B (en) 2023-04-07

Family

ID=70494122

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811295847.1A Active CN111125384B (en) 2018-11-01 2018-11-01 Multimedia answer generation method and device, terminal equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111125384B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112115282A (en) * 2020-09-17 2020-12-22 北京达佳互联信息技术有限公司 Question answering method, device, equipment and storage medium based on search
CN112367308A (en) * 2020-10-27 2021-02-12 广州朗国电子科技有限公司 Automatic making method, device and storage medium of multimedia playing content
CN113296653B (en) * 2021-07-27 2021-10-22 阿里云计算有限公司 Simulation interaction model construction method, interaction method and related equipment

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1466367A (en) * 2002-07-03 2004-01-07 中国科学院计算技术研究所 Universal mobile human interactive system and method
CN101178924A (en) * 2006-11-09 2008-05-14 国际商业机器公司 System and method for inserting a description of images intoaudio recordings
CN103425640A (en) * 2012-05-14 2013-12-04 华为技术有限公司 Multimedia questioning-answering system and method
CN105792003A (en) * 2014-12-19 2016-07-20 张鸿勋 Interactive multimedia production system and method
CN106022704A (en) * 2016-05-06 2016-10-12 长沙市麓智信息科技有限公司 Inspection opinion reply auxiliary system and auxiliary method thereof
CN106409283A (en) * 2016-08-31 2017-02-15 上海交通大学 Audio frequency-based man-machine mixed interaction system and method
CN106649752A (en) * 2016-12-26 2017-05-10 北京云知声信息技术有限公司 Answer acquisition method and device
CN106802941A (en) * 2016-12-30 2017-06-06 网易(杭州)网络有限公司 The generation method and equipment of a kind of reply message
CN106847279A (en) * 2017-01-10 2017-06-13 西安电子科技大学 Man-machine interaction method based on robot operating system ROS
CN108399169A (en) * 2017-02-06 2018-08-14 阿里巴巴集团控股有限公司 Dialog process methods, devices and systems based on question answering system and mobile device

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10068016B2 (en) * 2013-10-17 2018-09-04 Wolfram Alpha Llc Method and system for providing answers to queries
CN104598445B (en) * 2013-11-01 2019-05-10 腾讯科技(深圳)有限公司 Automatically request-answering system and method
US11182681B2 (en) * 2017-03-15 2021-11-23 International Business Machines Corporation Generating natural language answers automatically

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1466367A (en) * 2002-07-03 2004-01-07 中国科学院计算技术研究所 Universal mobile human interactive system and method
CN101178924A (en) * 2006-11-09 2008-05-14 国际商业机器公司 System and method for inserting a description of images intoaudio recordings
CN103425640A (en) * 2012-05-14 2013-12-04 华为技术有限公司 Multimedia questioning-answering system and method
CN105792003A (en) * 2014-12-19 2016-07-20 张鸿勋 Interactive multimedia production system and method
CN106022704A (en) * 2016-05-06 2016-10-12 长沙市麓智信息科技有限公司 Inspection opinion reply auxiliary system and auxiliary method thereof
CN106409283A (en) * 2016-08-31 2017-02-15 上海交通大学 Audio frequency-based man-machine mixed interaction system and method
CN106649752A (en) * 2016-12-26 2017-05-10 北京云知声信息技术有限公司 Answer acquisition method and device
CN106802941A (en) * 2016-12-30 2017-06-06 网易(杭州)网络有限公司 The generation method and equipment of a kind of reply message
CN106847279A (en) * 2017-01-10 2017-06-13 西安电子科技大学 Man-machine interaction method based on robot operating system ROS
CN108399169A (en) * 2017-02-06 2018-08-14 阿里巴巴集团控股有限公司 Dialog process methods, devices and systems based on question answering system and mobile device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李佳 ; 杨婷婷 ; 刘伟 ; .数字多媒体旅游咨询信息智能问答系统设计.现代电子技术.2017,(12),74-76+79. *

Also Published As

Publication number Publication date
CN111125384A (en) 2020-05-08

Similar Documents

Publication Publication Date Title
US10811013B1 (en) Intent-specific automatic speech recognition result generation
WO2019114516A1 (en) Media information display method and apparatus, storage medium, and electronic apparatus
WO2021178379A1 (en) Systems and methods for automating video editing
CN107193792A (en) The method and apparatus of generation article based on artificial intelligence
CN111125384B (en) Multimedia answer generation method and device, terminal equipment and storage medium
CN110164435A (en) Audio recognition method, device, equipment and computer readable storage medium
WO2020232796A1 (en) Multimedia data matching method and device, and storage medium
US20140172419A1 (en) System and method for generating personalized tag recommendations for tagging audio content
CN109977255A (en) Model generating method, audio-frequency processing method, device, terminal and storage medium
CN113641859B (en) Script generation method, system, computer storage medium and computer program product
CN108460122B (en) Video searching method, storage medium, device and system based on deep learning
CN111626049A (en) Title correction method and device for multimedia information, electronic equipment and storage medium
CN107665188B (en) Semantic understanding method and device
CN112163560A (en) Video information processing method and device, electronic equipment and storage medium
CN111681678B (en) Method, system, device and storage medium for automatically generating sound effects and matching videos
CN104994000A (en) Method and device for dynamic presentation of image
CN112199932A (en) PPT generation method, device, computer-readable storage medium and processor
CN114173067A (en) Video generation method, device, equipment and storage medium
CN113660526B (en) Script generation method, system, computer storage medium and computer program product
CN115052201A (en) Video editing method and electronic equipment
CN114339076A (en) Video shooting method and device, electronic equipment and storage medium
CN113676772A (en) Video generation method and device
CN113556484A (en) Video processing method and device, electronic equipment and computer readable storage medium
CN115129806A (en) Data processing method and device, electronic equipment and computer storage medium
CN112732951A (en) Man-machine interaction method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant