Content generation method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses a content generation method and device, equipment and a storage medium, and relates to the technical field of computers. The method comprises the steps of obtaining a target text material from a target preset text resource library, obtaining a target audio material corresponding to the target text material from a target preset audio resource library, performing voice synthesis processing on the target text material to obtain a target voice audio corresponding to the target text material, and generating a target voice audio corresponding to the target text material by using a target preset generation template. And generating a target audio content according to a target audio material corresponding to the target text material and the target voice audio. Through adoption of the technical scheme, the text material in the preset text resource library is subjected to speech synthesis processing to obtain the corresponding speech audio, and the template is utilized to automatically generate the corresponding audio content according to the audio resource in the preset audio resource library corresponding to the text material, so that the generation efficiency of the audio content is improved, manual recording is not needed, and the user experience is improved. And the labor cost is effectively saved.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular to a content generation method, apparatus, device, and storage medium. Background Art

[0002] Audio content in the form of broadcasting uses sound to transmit information and is an important way for people to obtain information in their daily lives. In traditional solutions, audio content is generated by manual recording and transmitted to audiences in a certain area using radio waves or other means. Summary of the invention

[0003] The embodiments of the present disclosure provide a content generation method, apparatus, storage medium, and device, which can optimize existing audio content generation solutions.

[0004] In a first aspect, an embodiment of the present disclosure provides a content generation method, including:

[0005] Acquire a target text material from a target preset text resource library, and acquire a target audio material corresponding to the target text material from a target preset audio resource library;

[0006] Performing speech synthesis processing on the target text material to obtain target speech audio corresponding to the target text material;

[0007] The target preset template is used to generate the target audio content according to the target audio material corresponding to the target text material and the target voice audio.

[0008] In a second aspect, the present disclosure also provides a content generation device, including:

[0009] A material acquisition module, used to acquire a target text material from a target preset text resource library, and to acquire a target audio material corresponding to the target text material from a target preset audio resource library;

[0010] A text material processing module, used to perform speech synthesis processing on the target text material to obtain a target speech audio corresponding to the target text material;

[0011] The content generation module is used to generate a target audio content according to the target audio material corresponding to the target text material and the target voice audio by using a target preset generation template.

[0012] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0013] one or more processors;

[0014] a storage device for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the content generating method provided by the embodiment of the present disclosure.

[0016] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium containing computer executable instructions, which, when executed by a computer processor, are used to execute the content generation method provided by the embodiment of the present disclosure.

[0017] The content generation scheme provided by the embodiment of the present disclosure obtains the target text material from the target preset text resource library, and obtains the target audio material corresponding to the target text material from the target preset audio resource library, performs speech synthesis processing on the target text material to obtain the target speech audio corresponding to the target text material, and uses the target preset generation template to generate the target audio content according to the target audio material and the target speech audio corresponding to the target text material. By adopting the above technical scheme, the text material in the preset text resource library is subjected to speech synthesis processing to obtain the corresponding speech audio, and the template is used to automatically generate the corresponding audio content according to the audio resources in the preset audio resource library corresponding to the text material, thereby improving the efficiency of audio content generation, eliminating the need for manual participation in recording, and effectively saving labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0019] Figure 1 A flowchart of a content generation method provided by an embodiment of the present disclosure;

[0020] Figure 2 A flowchart of another content generation method provided by an embodiment of the present disclosure;

[0021] Figure 3 A schematic diagram of the structure of a content generation device provided by an embodiment of the present disclosure;

[0022] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0023] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0024] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0025] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0026] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0027] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0028] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0029] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0030] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0031] As an optional but non-limiting implementation, in response to receiving an active request from the user, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0032] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0033] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0034] Figure 1 A flow chart of a content generation method provided in an embodiment of the present disclosure is applicable to the scenario of audio content generation. The method can be executed by a content generation device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal such as a mobile phone, a smart watch, a tablet computer, and a personal digital assistant, or a personal computer (PC), a car computer, or a server.

[0035] like Figure 1 As shown, the method includes:

[0036] Step 101: Acquire a target text material from a target preset text resource library, and acquire a target audio material corresponding to the target text material from a target preset audio resource library.

[0037] Exemplarily, a text resource library containing text resources can be pre-set, recorded as a preset text resource library, and the number of preset text resource libraries can be one or more. The target preset text resource library can be understood as a preset text resource library that currently needs to acquire text resources. The selection method of the target preset text resource library can be pre-set, such as system default, user self-selection, or dynamic selection based on the current scene (such as based on the current time, date, or region, etc.). The preset text resource library may contain text resources of one text resource type or multiple text resource types. Among them, the specific division method of text resource types is not limited, for example, it can include finance, technology, entertainment, education, travel, health, novels, and crosstalk, etc. The target text material can be understood as the text resource currently acquired from the target preset text resource library, and the specific quantity and acquisition method are not limited.

[0038] Exemplarily, an audio resource library containing audio resources can be pre-set, recorded as a preset audio resource library, and the number of preset audio resource libraries can be one or more. The target preset audio resource library can be understood as the preset audio resource library for which audio resources need to be currently acquired. The selection method of the target preset audio resource library can be pre-set, such as system default, user self-selection, or dynamic selection based on the current scene (such as based on the current time, date, or region, etc.). The preset audio resource library may contain audio resources of one audio resource type or multiple audio resource types. Among them, the specific division method of the audio resource type is not limited, for example, it can include music, lectures, and crosstalk, among which music can also be specifically divided into dynamic, rock, light, quiet, and stress relief, etc. according to dimensions such as music style. The target audio material can be understood as the audio resource corresponding to the target text material currently obtained from the target preset audio resource library, and the specific quantity and acquisition method are not limited.

[0039] It should be noted that the target text material and the target audio material correspond to each other, and there is no limitation on the order of obtaining the target text material and the target audio material. The target text material can be obtained first, and then the target audio material, or the target audio material can be obtained first, and then the target text material, or they can be obtained in parallel, etc.

[0040] Step 102: Perform speech synthesis processing on the target text material to obtain target speech audio corresponding to the target text material.

[0041] Exemplarily, the audio content to be generated needs to be played to the user in the form of sound, therefore, the target text material is subjected to speech synthesis processing, for example, the text content in the target text material can be converted into speech content, and the target speech audio corresponding to the target text material can be obtained. Optionally, a text-to-speech (TTS) technology can be used, such as using a TTS engine to convert the text content in the target text material into speech content.

[0042] Step 103: Generate target audio content according to the target audio material corresponding to the target text material and the target voice audio by using the target preset generation template.

[0043] Exemplarily, a template for synthesizing the target audio material and the target voice audio corresponding to the acquired target text material can be pre-set, which is recorded as a preset generation template. The target preset generation template can be understood as the preset generation template that needs to be used currently, and the selection method of the target preset generation template can be pre-set, such as system default, user self-selection, or dynamic selection according to the current scene (such as according to the current time, date, or region, etc.). The preset generation template may include relevant information for indicating the synthesis method of the audio material and the voice audio. Using the target preset generation template, the target audio content can be automatically generated according to the target audio material and the target voice audio corresponding to the target text material. Among them, the audio content can be the audio content of the target type, and the specific type is not limited. For example, the target type can be broadcast, that is, the audio content can be broadcast content. The preset text resource library, the preset audio resource library or the preset generation template can be determined according to the characteristics of the target type.

[0044] The content generation method of the disclosed embodiment obtains the target text material from the target preset text resource library, and obtains the target audio material corresponding to the target text material from the target preset audio resource library, performs speech synthesis processing on the target text material to obtain the target speech audio corresponding to the target text material, and uses the target preset generation template to generate the target audio content according to the target audio material and the target speech audio corresponding to the target text material. By adopting the above technical solution, the text material in the preset text resource library is subjected to speech synthesis processing to obtain the corresponding speech audio, and the template is used to automatically generate the corresponding audio content according to the audio resources in the preset audio resource library corresponding to the text material, thereby improving the efficiency of audio content generation, eliminating the need for manual recording, and effectively saving labor costs.

[0045] In some embodiments, the target preset generation template includes a plurality of template segments connected in a preset order, each of which is associated with a segment attribute; the segment attribute includes segment duration and / or segment content source type; the segment content source type includes at least one of an audio material, a voice audio corresponding to a text material, a voice audio and an audio material corresponding to a text material, and a preset audio in the target preset generation template; wherein, the target audio content is generated according to the target audio material corresponding to the target text material and the target voice audio using the target preset generation template, including: generating the target audio content according to the segment attributes associated with each of the template segments in the target preset generation template, the target audio material corresponding to the target text material, and the target voice audio. Thus, the preset generation template can be set more reasonably, and then the expected audio content can be automatically and quickly generated according to the segment attributes associated with each of the template segments in the target preset generation template.

[0046] Exemplarily, for each template segment in the target preset generated template, it can be determined whether it is necessary to fill in the material. If necessary, the corresponding material is filled into the current template segment according to the segment attributes of the current template segment. When the segment attributes of a template segment include the segment duration, the material to be filled can be adjusted according to the segment duration, such as editing or adjusting the speech speed, so that the duration of the material to be filled matches the segment duration; when the segment attributes of a template segment include the segment content source type, the material that matches the segment content source type can be filled into the template segment according to the segment content source type. Among them, when the segment content source type is the voice audio and audio material corresponding to the text material, the voice audio and audio material can be spliced, or the voice audio and audio material can be synthesized to achieve the effect of using the sound in the audio material as the background sound of the voice content in the voice audio.

[0047] Exemplarily, the target preset generation template includes preset audio, and the audio content in the preset audio can be the voice content of the template segments used to connect two other segment content source types. In this way, the appearance or transition of the voice audio corresponding to the audio material and the text material can be made more natural. Taking the broadcast content as an example, it is more in line with the characteristics of radio broadcasts, improves the authenticity of the audio content, and thus improves the user's listening experience.

[0048] Exemplarily, the voice content in the preset audio may include opening remarks, transitional remarks or closing remarks, etc. The opening remarks may be the voice content at the beginning of the audio content, that is, it may be the first template segment corresponding to the preset audio in the preset order, such as "Welcome to listen to XX radio station"; the transitional remarks may include the voice content between different template segments, such as "Let's listen to a song of XX"; the closing remarks may be understood as the voice content at the end of the audio content, that is, it may be the last template segment corresponding to the preset audio in the preset order, such as "Today's XX radio station is over, thank you for listening".

[0049] In some embodiments, before the target text material is obtained from the target preset text resource library, the method further includes: determining a target playback time period according to the current time; determining at least one of a corresponding target preset text resource library, a target preset audio resource library, and a target preset generation template according to the target playback time period; wherein the target audio content is used for the target terminal to play during the target playback time period. The advantage of such a setting is that at least one of a target preset text resource library, a target preset audio resource library, and a target preset generation template can be dynamically selected according to the target playback time period corresponding to the current time, thereby improving the flexibility of the audio content.

[0050] For example, a day can be divided into multiple broadcast time periods, such as morning period (5:00 to 12:00), afternoon period (12:00 to 17:00), evening period (17:00 to 22:00) and late night period (22:00 to 5:00), so that users can listen to different audio content in different time periods. Optionally, the current time can be the time that triggers the generation of audio content, and the broadcast time period after the current time and closest to the current time can be determined as the target playback time period, that is, before the target playback time period arrives, the target media content can be generated in advance.

[0051] Exemplarily, a mapping relationship table corresponding to different broadcast time periods can be preset, and the mapping relationship tables corresponding to different broadcast time periods can be the same or different, and the mapping relationship table includes the correspondence between the broadcast time period and at least one of the preset text resource library, the preset audio resource library, and the preset generation template. Optionally, at least one of the preset text resource library, the preset audio resource library, and the preset generation template corresponding to different broadcast time periods is different, and there is no limitation on which one or which ones are different. For example, the preset text resource library and the preset audio resource library are different, and the preset generation template is the same. Broadcast time period A can correspond to the preset text resource library a, the preset audio resource library b, and the preset generation template c; broadcast time period B can correspond to the preset text resource library d, the preset audio resource library e, and the preset generation template c.

[0052] Optionally, for different broadcast time periods, big data can be used to determine the preferences of users who listen to audio content, and then determine the mapping relationship table corresponding to different broadcast time periods. It should be noted that the collection and analysis of big data and other related operations are performed with the knowledge and authorization of the user.

[0053] Optionally, the target audio content is sent to the target terminal at the associated time of the target playback period. The associated time may be before the target playback period or within the target playback period, and may be determined specifically based on whether the target terminal is in a receivable state for the target audio content. For example, the range of the associated time is from the target moment before the start time of the target playback period (such as 10 minutes in advance) to the end time of the target playback period. The user turns on the audio content listening function of the target terminal, such as the radio function, within the range of the associated time, and can receive the target audio content. Optionally, the target terminal may also send a content acquisition request to the corresponding server within the range of the associated time. After receiving the content acquisition request, the server sends the target audio content to the target terminal.

[0054] In some embodiments, after generating the target audio content according to the target audio material corresponding to the target text material and the target voice audio by using the target preset generation template, it also includes: at the start time of the target playback period, and / or in response to the audio content acquisition request of the target terminal, the target audio content is sent to the target terminal. Wherein, the target terminal includes a car computer and / or a mobile terminal. In this way, the target terminal does not need to generate audio content by itself, and broadcasts according to the target audio content sent by the electronic device, thereby saving its own computing resources. Wherein, the electronic device in the embodiment of the present disclosure can be the same physical device as the target terminal, or it can be the server corresponding to the target terminal, without specific limitation.

[0055] For example, the target terminal may include a car computer, so that the car owner can listen to audio content in the car, so that the technical solution of the embodiment of the present disclosure can be applied to the application scenario of the car owner listening to radio broadcasts in the car. The target terminal may also include a mobile terminal such as a mobile phone, so that the user can listen to audio content anytime and anywhere.

[0056] In some embodiments, before the target text material is obtained from the target preset text resource library, it also includes: determining the target region according to the region where the target terminal is located; determining at least one of the corresponding target preset text resource library, target preset audio resource library and target preset generation template according to the target region; wherein the target audio content is used for playback by the target terminal. The advantage of such a setting is that at least one of the target preset text resource library, target preset audio resource library and target preset generation template can be dynamically selected according to the region where the target terminal is located, thereby improving the flexibility of the audio content. wherein, the region can be a province or a city, etc.

[0057] Exemplarily, mapping relationship tables corresponding to different regions may be preset, and the mapping relationship tables corresponding to different regions may be the same or different, and the mapping relationship tables include the correspondence between the region and at least one of the preset text resource library, the preset audio resource library, and the preset generation template. Optionally, at least one of the preset text resource library, the preset audio resource library, and the preset generation template corresponding to different regions is different, and the specific difference or differences is not limited.

[0058] Optionally, at least one of a target preset text resource library, a target preset audio resource library, and a target preset generation template may be determined in combination with the target playback period and the target region, so as to further enhance the flexibility and diversity of the audio content, meet the listening needs of users in different regions for different audio content in different time periods, and enhance the user experience.

[0059] In some embodiments, for the target preset text resource library, the target preset audio resource library and the target preset generation template, one of them can be determined first, and then the corresponding other two can be determined to ensure the degree of correlation among the three, and further ensure the quality of the audio content. Exemplarily, before obtaining the target text material from the target preset text resource library, it also includes: determining the target preset text resource library, and determining the corresponding target preset audio resource library and / or target preset generation template according to the target preset text resource library; or, determining the target preset audio resource library, and determining the corresponding target preset text resource library and / or target preset generation template according to the target preset text resource library; or, determining the target preset generation template, and determining the corresponding target preset audio resource library and / or target preset text resource library according to the target preset generation template.

[0060] In some embodiments, the division dimensions of at least one of different preset text resource libraries, different preset audio resource libraries and different preset generation templates include a target playback period and / or a target area, the target audio content is used for the target terminal to play during the target playback period, and the target area is determined based on the area where the target terminal is located.

[0061] In some embodiments, different preset text resource libraries correspond to different text resource types. For example, when different broadcast time periods correspond to different preset text resource libraries, users can listen to voice content corresponding to different types of text resources in different time periods, further enhancing the flexibility and diversity of audio content. Exemplarily, each preset text resource library corresponds to a text resource type set, and each text resource type set includes one or more text resource types. Different preset text resource libraries correspond to different text resource type sets, that is, there is at least one different text resource type in two text resource type sets. For example, the first text resource type set includes type A, type B, and type C; the second text resource type set includes type A, type D, and type E, or includes type D, type E, and type F.

[0062] In some embodiments, different preset audio resource libraries correspond to different audio resource types. For example, when different broadcast time periods correspond to different preset audio resource libraries, users can listen to different types of audio resources at different time periods, further improving the flexibility and diversity of audio content. Exemplarily, each preset audio resource library corresponds to an audio resource type set, and each audio resource type set includes one or more audio resource types. Different preset audio resource libraries correspond to different audio resource type sets, that is, two audio resource type sets have at least one different audio resource type.

[0063] In some embodiments, different preset generation templates correspond to at least one of different preset orders, different numbers of template segments, and different segment attributes. For example, when different broadcast time periods correspond to different preset generation templates, users can listen to content with different arrangements in different time periods, further improving the flexibility and diversity of audio content. For example, the opening remarks of the morning time period may include "Good morning", and the opening remarks of the evening time period may include "Good evening"; for another example, the voice audio corresponding to the text material is played first in the morning time period, and then the music is played, and the music is played first in the morning time period, and then the voice audio corresponding to the text material is played.

[0064] In some embodiments, the step of obtaining the target text material from the target preset text resource library includes: obtaining the target text material whose update time meets the first preset time requirement from the target preset text resource library, wherein the target preset text resource library includes a resource library for dynamically updated text resources, and the first preset time requirement is associated with the time of obtaining the target text material. Thus, different target text materials can be selected from the dynamically updated target preset text resource library according to the different times of obtaining the target text material, thereby enabling users to have the opportunity to listen to the voice audio corresponding to different text resources at different time periods. For broadcast content, this is more in line with the characteristics of radio broadcasts, improves the authenticity of the broadcast content, and thus improves the user's listening experience.

[0065] Exemplarily, the first preset time requirement may be that the update time is within a first preset time period before the time of acquiring the target text material, for example, text resources updated within the previous 24 hours, specifically news within the previous 24 hours.

[0066] In some embodiments, the step of obtaining the target audio material corresponding to the target text material from the target preset audio resource library includes: obtaining the target audio material corresponding to the target text material whose update time meets the second preset time requirement from the target preset audio resource library, wherein the target preset audio resource library includes a resource library for dynamically updated audio resources, and the second preset time requirement is associated with the time of obtaining the target audio material. Thus, according to the different times of obtaining the target audio material, different target audio materials can be selected from the dynamically updated target preset audio resource library, thereby allowing users to have the opportunity to listen to the sounds of different audio resources at different time periods. For broadcast content, it is more in line with the characteristics of radio broadcasts, improves the authenticity of the audio content, and thus improves the user's listening experience.

[0067] Exemplarily, the second preset time requirement may be that the update time is within a second preset time period before the time of acquiring the target audio material, for example, audio resources updated within the previous month, specifically songs published within the previous month.

[0068] In some embodiments, it also includes: extracting target text content from the target text material, wherein the target text content includes summary content of the target text material; wherein the performing speech synthesis processing on the target text material to obtain the target speech audio corresponding to the target text material includes: performing speech synthesis processing on the target text content to obtain the target speech audio corresponding to the target text material. Thus, the acquired text resources can be processed for the second time, and text content that is more in line with expectations can be extracted. Taking broadcast content as an example, text content that is more in line with the broadcast characteristics of a radio station can be extracted.

[0069] Exemplarily, summary content can be understood as the key content in the target text material. Taking news as an example, the key content in the news can be extracted, such as extracting the core content in the news title and the news text, and the extracted content can be controlled within a preset word count range, such as 450 words. Optionally, a machine learning model can be used to extract the target text content from the target text material, such as using a machine learning model to extract key information from the news text to generate summary content.

[0070] Optionally, the acquired target audio material may be further screened, for example, the integrity of the target audio material is detected, and audio resources that do not meet the integrity requirements are filtered out, such as song clips and background music. The screened target audio material participates in the generation of the target audio content.

[0071] Figure 2 This is a flow chart of another content generation method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is optimized based on the various optional solutions in the above embodiments. Specifically, taking the application scenario of listening to a radio station in a car as an example, the method includes the following steps:

[0072] Step 201: determine a target broadcast time period according to the current time, and determine a target area according to the area where the target terminal is located.

[0073] Exemplarily, in response to the audio content generation event being triggered, the target playback time period is determined according to the current time, and the target region is determined according to the region where the target terminal is located. It should be noted that the user needs to be informed and authorized before obtaining the region where the target terminal is located.

[0074] Exemplarily, the time of a day is divided into multiple broadcasting time periods, such as the morning time period (5 o'clock to 12 o'clock), the afternoon time period (12 o'clock to 17 o'clock), the evening time period (17 o'clock to 22 o'clock) and the late night time period (22 o'clock to 5 o'clock). The current time can be the time to trigger the generation of audio content, and the time of the preset duration (such as 30 minutes) before the start time of each broadcasting time period is triggered to generate audio content. For example, for the morning time period, it can be determined to trigger the audio content generation event 30 minutes before 5 o'clock, that is, 4:30, that is, the current time can be 4:30, and the corresponding target playback time period is the morning time period. If there is no corresponding playback time period at the current time, subsequent steps can be temporarily not performed. If the current time is 4:10, the current time is not the time of the preset duration (such as 30 minutes) before the start time of any broadcasting time period, then you can wait until 4:30 to perform subsequent steps.

[0075] Step 202: Determine a corresponding target preset text resource library, a target preset audio resource library and a target preset generation template according to the target playback period and the target region.

[0076] Exemplarily, for the target area, the text resource types in the preset text resource library corresponding to the morning period include finance and technology, and the corresponding audio resource types in the preset audio resource library include dynamic and rock; the text resource types in the preset text resource library corresponding to the afternoon and evening periods include entertainment, education and travel, and the corresponding audio resource types in the preset audio resource library include light-hearted; the text resource types in the preset text resource library corresponding to the late night period include health preservation, and the corresponding audio resource types in the preset audio resource library include tranquility and stress relief.

[0077] Step 203: Acquire a target text material whose update time meets a first preset time requirement from a target preset text resource library, and acquire a target audio material corresponding to the target text material from a target preset audio resource library.

[0078] For example, assuming that the target broadcast time period is the morning time period, the latest (e.g., within the last 24 hours) financial information and technology information are obtained from the corresponding target preset text resource library as target text materials. Dynamic music and rock music are obtained from the corresponding target preset audio resource library as target audio materials.

[0079] Step 204: extract the target text content from the target text material using a preset text extraction method.

[0080] Exemplarily, for the acquired financial information and scientific information, titles and abstracts are extracted as target text contents.

[0081] Step 205: Perform speech synthesis processing on the target text content to obtain target speech audio corresponding to the target text material.

[0082] Step 206: Generate target audio content according to the segment attributes associated with each template segment in the target preset generation template, the target audio material corresponding to the target text material, and the target voice audio.

[0083] Exemplarily, the target preset generation template corresponding to the morning time period is initialized, and the template includes preset audio corresponding to the preset template text content such as opening remarks, transition remarks and closing remarks. Table 1 is an example of a preset generation template.

[0084] Table 1. Examples of preset generation templates

[0085]

[0086] Exemplarily, five target text contents extracted from the acquired financial information and technology information are filled into the news part, and five acquired dynamic music and rock music are filled into the music part.

[0087] Step 207: Send the target audio content to the vehicle computer at the start time of the target playback period.

[0088] Exemplarily, at a time associated with the target playback period, such as the start time of the target playback period, the target audio content is sent to the vehicle computer, so that the vehicle computer can play the target audio content, which is convenient for users to listen to.

[0089] The content generation method provided by the embodiment of the present disclosure divides the whole day into multiple broadcast time periods, and dynamically determines the target broadcast time period according to the current time and the area where the vehicle is located. Different broadcast time periods and areas can correspond to resource libraries of different text types and / or different audio types and target preset generation templates. When obtaining text resources, text resources whose update time meets the requirements are obtained to ensure the freshness and timeliness of the audio content, and target text content is extracted therefrom, which is more in line with the characteristics of broadcasting. According to the fragment attributes associated with each template fragment in the target preset generation template, the target audio material corresponding to the target text material and the target voice audio, the target audio content is generated and sent to the car computer at the associated time of the target broadcast time period, thereby improving the generation efficiency of the broadcast content, eliminating the need for radio hosts to manually participate in recording, effectively saving labor costs, and meeting the full-time radio listening needs of car owners in the car.

[0090] Figure 3 A schematic diagram of the structure of a content generation device provided by an embodiment of the present disclosure is shown in FIG. Figure 3 As shown, the device comprises:

[0091] The material acquisition module 301 is used to acquire a target text material from a target preset text resource library, and to acquire a target audio material corresponding to the target text material from a target preset audio resource library;

[0092] The text material processing module 302 is used to perform speech synthesis processing on the target text material to obtain the target speech audio corresponding to the target text material;

[0093] The content generation module 303 is used to generate target audio content according to the target audio material corresponding to the target text material and the target voice audio by using the target preset generation template.

[0094] The content generation device provided by the embodiment of the present disclosure obtains the target text material from the target preset text resource library, and obtains the target audio material corresponding to the target text material from the target preset audio resource library, performs speech synthesis processing on the target text material to obtain the target speech audio corresponding to the target text material, and uses the target preset generation template to generate the target audio content according to the target audio material and the target speech audio corresponding to the target text material. By adopting the above technical solution, the text material in the preset text resource library is subjected to speech synthesis processing to obtain the corresponding speech audio, and the template is used to automatically generate the corresponding audio content according to the audio resources in the preset audio resource library corresponding to the text material, thereby improving the efficiency of audio content generation, eliminating the need for manual recording, and effectively saving labor costs.

[0095] Optionally, the target preset generation template includes a plurality of template segments connected in a preset order, each of the template segments is associated with a segment attribute; the segment attribute includes segment duration and / or segment content source type; the segment content source type includes at least one of an audio material, a voice audio corresponding to a text material, a voice audio and an audio material corresponding to a text material, and a preset audio in the target preset generation template;

[0096] The content generation module is specifically used to generate target audio content according to the segment attributes associated with each template segment in the target preset generation template, the target audio material corresponding to the target text material and the target voice audio.

[0097] Optionally, before acquiring the target text material from the target preset text resource library, the method further includes:

[0098] A determination module, configured to determine a target playback time period according to the current time, and / or determine a target region according to the region where the target terminal is located; and to determine at least one of a corresponding target preset text resource library, a target preset audio resource library, and a target preset generation template according to the target playback time period and / or the target region; wherein the target audio content is used for the target terminal to play during the target playback time period;

[0099] Alternatively, it is used to determine a target preset text resource library, and determine a corresponding target preset audio resource library and / or a target preset generation template according to the target preset text resource library;

[0100] Alternatively, it is used to determine a target preset audio resource library, and determine a corresponding target preset text resource library and / or a target preset generation template according to the target preset text resource library;

[0101] Alternatively, it is used to determine a target preset generation template, and determine a corresponding target preset audio resource library and / or a target preset text resource library according to the target preset generation template.

[0102] Optionally, the device satisfies at least one of the following: different preset text resource libraries correspond to different text resource types; different preset audio resource libraries correspond to different audio resource types; and different preset generation templates correspond to at least one of different preset orders, different numbers of template segments, and different segment attributes. The division dimension of at least one of the different preset text resource libraries, different preset audio resource libraries, and different preset generation templates includes a target playback time period and / or a target region, the target audio content is used for the target terminal to play during the target playback time period, and the target region is determined according to the region where the target terminal is located.

[0103] Optionally, when the material acquisition module acquires the target text material from the target preset text resource library, it is specifically used to: acquire the target text material whose update time satisfies a first preset time requirement from the target preset text resource library, wherein the target preset text resource library includes a resource library for dynamically updated text resources, and the first preset time requirement is associated with the time for acquiring the target text material; and / or, when the material acquisition module acquires the target audio material corresponding to the target text material from the target preset audio resource library, it is specifically used to: acquire the target audio material corresponding to the target text material whose update time satisfies a second preset time requirement from the target preset audio resource library, wherein the target preset audio resource library includes a resource library for dynamically updated audio resources, and the second preset time requirement is associated with the time for acquiring the target audio material.

[0104] Optionally, the device further comprises:

[0105] A content extraction module, used to extract target text content from the target text material, wherein the target text content includes summary content of the target text material;

[0106] The text material processing module is specifically used to perform speech synthesis processing on the target text content to obtain the target speech audio corresponding to the target text material.

[0107] Optionally, the audio content includes broadcast content.

[0108] Optionally, the device further comprises:

[0109] The content delivery module is used to generate the target audio content according to the target audio material corresponding to the target text material and the target voice audio by using the target preset generation template, and further includes:

[0110] At the start time of the target playback period, and / or in response to an audio content acquisition request from a target terminal, the target audio content is sent to the target terminal.

[0111] Optionally, the target terminal includes a vehicle computer and / or a mobile terminal.

[0112] The content generation device provided in the embodiments of the present disclosure can execute the content generation method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0113] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0114] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Figure 4 , which shows an electronic device (eg, Figure 4 The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0115] like Figure 4As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An edit / output (I / O) interface 405 is also connected to the bus 404.

[0116] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0117] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0118] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0119] The electronic device provided by the embodiment of the present disclosure and the content generation method provided by the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0120] The embodiments of the present disclosure provide a computer storage medium on which a computer program is stored. When the program is executed by a processor, the content generation method provided by the above embodiments is implemented.

[0121] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0122] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0123] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0124] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains target text material from a target preset text resource library, and obtains target audio material corresponding to the target text material from a target preset audio resource library; performs speech synthesis processing on the target text material to obtain target speech audio corresponding to the target text material; uses the target preset generation template to generate target audio content according to the target audio material corresponding to the target text material and the target speech audio.

[0125] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0126] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0127] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a module does not limit the module itself in some cases. For example, a content generation module may also be described as "a module that generates target audio content based on a target audio material and the target speech audio corresponding to the target text material using a target preset generation template".

[0128] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0129] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] According to one or more embodiments of the present disclosure, there is provided a content generation method, comprising:

[0131] Acquire a target text material from a target preset text resource library, and acquire a target audio material corresponding to the target text material from a target preset audio resource library;

[0132] Performing speech synthesis processing on the target text material to obtain target speech audio corresponding to the target text material;

[0133] The target preset template is used to generate the target audio content according to the target audio material corresponding to the target text material and the target voice audio.

[0134] According to one or more embodiments of the present disclosure, the target preset generation template includes a plurality of template segments connected in a preset order, each of the template segments is associated with a segment attribute; the segment attribute includes segment duration and / or segment content source type; the segment content source type includes at least one of an audio material, a voice audio corresponding to a text material, a voice audio and an audio material corresponding to a text material, and a preset audio in the target preset generation template;

[0135] The step of using a target preset template to generate target audio content according to the target audio material corresponding to the target text material and the target voice audio includes:

[0136] The target audio content is generated according to the segment attributes associated with each template segment in the target preset generation template, the target audio material corresponding to the target text material and the target voice audio.

[0137] According to one or more embodiments of the present disclosure, before acquiring the target text material from the target preset text resource library, the method further includes:

[0138] Determine a target playback time period according to the current time, and / or determine a target region according to the region where the target terminal is located; determine at least one of a corresponding target preset text resource library, a target preset audio resource library, and a target preset generation template according to the target playback time period and / or the target region; wherein the target audio content is used for the target terminal to play during the target playback time period;

[0139] or,

[0140] Determine a target preset text resource library, and determine a corresponding target preset audio resource library and / or a target preset generation template according to the target preset text resource library;

[0141] or,

[0142] Determine a target preset audio resource library, and determine a corresponding target preset text resource library and / or a target preset generation template according to the target preset text resource library;

[0143] or,

[0144] A target preset generation template is determined, and a corresponding target preset audio resource library and / or a target preset text resource library is determined according to the target preset generation template.

[0145] According to one or more embodiments of the present disclosure, the method satisfies at least one of the following:

[0146] Different preset text resource libraries correspond to different text resource types;

[0147] Different preset audio resource libraries correspond to different audio resource types; and

[0148] Different preset generation templates correspond to at least one of different preset orders, different numbers of template segments, and different segment attributes;

[0149] Among them, the division dimensions of at least one of the different preset text resource libraries, different preset audio resource libraries and different preset generation templates include target playback time period and / or target area, the target audio content is used for the target terminal to play during the target playback time period, and the target area is determined according to the area where the target terminal is located.

[0150] According to one or more embodiments of the present disclosure, the step of acquiring the target text material from the target preset text resource library includes: acquiring the target text material whose update time satisfies a first preset time requirement from the target preset text resource library, wherein the target preset text resource library includes a resource library for dynamically updating text resources, and the first preset time requirement is associated with the time of acquiring the target text material; and / or,

[0151] The method of obtaining the target audio material corresponding to the target text material from the target preset audio resource library includes: obtaining the target audio material corresponding to the target text material whose update time meets a second preset time requirement from the target preset audio resource library, wherein the target preset audio resource library includes a resource library for dynamically updated audio resources, and the second preset time requirement is associated with the time for obtaining the target audio material.

[0152] According to one or more embodiments of the present disclosure, the present invention further includes:

[0153] Extracting target text content from the target text material, wherein the target text content includes summary content of the target text material;

[0154] The step of performing speech synthesis processing on the target text material to obtain a target speech audio corresponding to the target text material includes:

[0155] The target text content is processed by speech synthesis to obtain the target speech audio corresponding to the target text material.

[0156] According to one or more embodiments of the present disclosure, the audio content includes broadcast content, and after generating the target audio content according to the target audio material corresponding to the target text material and the target voice audio using the target preset generation template, the method further includes:

[0157] At the start time of the target playback period, and / or in response to an audio content acquisition request from a target terminal, the target audio content is sent to the target terminal, wherein the target terminal includes a vehicle computer and / or a mobile terminal.

[0158] According to one or more embodiments of the present disclosure, there is provided a content generating device, including:

[0159] A material acquisition module, used to acquire a target text material from a target preset text resource library, and to acquire a target audio material corresponding to the target text material from a target preset audio resource library;

[0160] A text material processing module, used to perform speech synthesis processing on the target text material to obtain a target speech audio corresponding to the target text material;

[0161] The content generation module is used to generate a target audio content according to the target audio material corresponding to the target text material and the target voice audio by using a target preset generation template.

[0162] According to one or more embodiments of the present disclosure, an electronic device is provided, the electronic device comprising:

[0163] one or more processors;

[0164] a storage device for storing one or more programs,

[0165] When the one or more programs are executed by the one or more processors, the one or more processors implement the content generating method provided by the embodiment of the present disclosure.

[0166] According to one or more embodiments of the present disclosure, a storage medium containing computer executable instructions is provided. When the computer executable instructions are executed by a computer processor, the content generating method provided by the embodiment of the present disclosure is executed.

[0167] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other.

[0168] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0169] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A content generation method, characterized in that: include: Acquire a target text material from a target preset text resource library, and acquire a target audio material corresponding to the target text material from a target preset audio resource library; Performing speech synthesis processing on the target text material to obtain target speech audio corresponding to the target text material; The target preset template is used to generate the target audio content according to the target audio material corresponding to the target text material and the target voice audio.

2. The method according to claim 1, characterized in that: The target preset generation template includes a plurality of template segments connected in a preset order, each of the template segments is associated with a segment attribute; the segment attribute includes segment duration and / or segment content source type; the segment content source type includes at least one of an audio material, a voice audio corresponding to a text material, a voice audio and an audio material corresponding to a text material, and a preset audio in the target preset generation template; The step of using a target preset template to generate target audio content according to the target audio material corresponding to the target text material and the target voice audio includes: The target audio content is generated according to the segment attributes associated with each template segment in the target preset generation template, the target audio material corresponding to the target text material and the target voice audio.

3. The method according to claim 1, characterized in that Before acquiring the target text material from the target preset text resource library, the method further includes: Determine a target playback time period according to the current time, and / or determine a target region according to the region where the target terminal is located; determine at least one of a corresponding target preset text resource library, a target preset audio resource library, and a target preset generation template according to the target playback time period and / or the target region; wherein the target audio content is used for the target terminal to play during the target playback time period; or, Determine a target preset text resource library, and determine a corresponding target preset audio resource library and / or a target preset generation template according to the target preset text resource library; or, Determine a target preset audio resource library, and determine a corresponding target preset text resource library and / or a target preset generation template according to the target preset text resource library; or, A target preset generation template is determined, and a corresponding target preset audio resource library and / or a target preset text resource library is determined according to the target preset generation template.

4. The method according to claim 2, characterized in that: The method satisfies at least one of the following: Different preset text resource libraries correspond to different text resource types; Different preset audio resource libraries correspond to different audio resource types; and Different preset generation templates correspond to at least one of different preset orders, different numbers of template segments, and different segment attributes; Among them, the division dimensions of at least one of the different preset text resource libraries, different preset audio resource libraries and different preset generation templates include target playback time period and / or target area, the target audio content is used for the target terminal to play during the target playback time period, and the target area is determined according to the area where the target terminal is located.

5. The method according to claim 1, characterized in that The acquiring of the target text material from the target preset text resource library comprises: acquiring the target text material whose update time satisfies a first preset time requirement from the target preset text resource library, wherein the target preset text resource library comprises a resource library for dynamically updating text resources, and the first preset time requirement is associated with the time of acquiring the target text material; and / or, The method of obtaining the target audio material corresponding to the target text material from the target preset audio resource library includes: obtaining the target audio material corresponding to the target text material whose update time meets a second preset time requirement from the target preset audio resource library, wherein the target preset audio resource library includes a resource library for dynamically updated audio resources, and the second preset time requirement is associated with the time for obtaining the target audio material.

6. The method according to claim 1, characterized in that Also includes: Extracting target text content from the target text material, wherein the target text content includes summary content of the target text material; The step of performing speech synthesis processing on the target text material to obtain a target speech audio corresponding to the target text material includes: The target text content is processed by speech synthesis to obtain the target speech audio corresponding to the target text material.

7. The method according to claim 1, characterized in that The audio content includes broadcast content. After generating the target audio content according to the target audio material corresponding to the target text material and the target voice audio by using the target preset generation template, the method further includes: At the start time of the target playback period, and / or in response to an audio content acquisition request from a target terminal, the target audio content is sent to the target terminal, wherein the target terminal includes a vehicle computer and / or a mobile terminal.

8. A content generating device, characterized in that: include: A material acquisition module, used to acquire a target text material from a target preset text resource library, and to acquire a target audio material corresponding to the target text material from a target preset audio resource library; A text material processing module, used to perform speech synthesis processing on the target text material to obtain a target speech audio corresponding to the target text material; The content generation module is used to generate a target audio content according to the target audio material corresponding to the target text material and the target voice audio by using a target preset generation template.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the content generating method as described in any one of claims 1 to 7.

10. A storage medium containing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the content generation method according to any one of claims 1 to 7.

Images