Copy configuration method and apparatus, and device and storage medium

Abstract

The present application relates to the technical field of computers. Disclosed are a copy configuration method and apparatus, and a device and a storage medium. The method comprises: acquiring prompt information, wherein the prompt information is used for indicating a copy configuration requirement (220); on the basis of the prompt information and a historical configuration record, obtaining at least one first copy type, wherein the historical configuration record is used for indicating copy types which have been configured within a historical time period (240); determining a proportion corresponding to the at least one first copy type, wherein the proportion corresponding to the first copy type is used for representing the probability of the first copy type being configured (260); and according to the proportion corresponding to the at least one first copy type, selecting a target copy from a copy library, wherein the target copy is used for generating, in combination with a selected copy timbre, audio corresponding to the target copy (280). By means of combining with prompt information and a historical configuration record, the present application increases selectable copy types for a target copy, and ensures the conformity between the target copy and the prompt information.

Description

Copywriting configuration method and device, equipment and storage medium

[0001] The present application claims priority from the Chinese patent application No. 202410724738.6 filed on June 5, 2024 and entitled "Copywriting configuration method and device, equipment and storage medium", the whole content of which is incorporated herein by reference. TECHNICAL FIELD

[0002] The present application relates to the technical field of computer, in particular to a copywriting configuration method, device, equipment and storage medium. BACKGROUND

[0003] Music DJs (Disc Jockey) add unique story commentary to each song in the form of AI (Artificial Intelligence) intelligent voice broadcast, allowing users to enjoy personalized listening experience similar to local radio.

[0004] In related technologies, after starting the "music DJ", a special commentary audio will be automatically played before playing any song, and a selected "DJ" will tell the user the story behind the song and its singer. In addition, based on the user's personalized listening habits, the system can intelligently generate and provide a variety of audio interactive content for the user, from song creation background to music style analysis, from lyrics depth interpretation to song meaning interesting commentary, allowing different users to experience different customized commentary content, and providing users with a comprehensive and in-depth music appreciation experience.

[0005] However, the above method is based on the user's listening scenario and generates song copywriting for the user in real time, resulting in a single type of generated copywriting. SUMMARY

[0006] The present application provides a copywriting configuration method, device, equipment and storage medium. The technical scheme provided by the present application is as follows:

[0007] According to an aspect of the present application, a copywriting configuration method is provided, which is executed by a computer device, and the method comprises:

[0008] Obtaining prompt information, the prompt information being used to indicate copywriting configuration requirements;

[0009] Obtaining at least one first copywriting type according to the prompt information and historical configuration records, the historical configuration records being used to indicate copywriting types configured in a historical time period;

[0010] determine the proportion corresponding to each of the at least one first script type, the proportion corresponding to the first script type being used to represent the probability of the first script type being configured;

[0011] select a target script from a script library according to the proportion corresponding to each of the at least one first script type, the target script being used to generate audio corresponding to the target script in combination with a selected script tone.

[0012] According to an aspect of an embodiment of the present application, a script configuration device is provided, and the device comprises:

[0013] an information obtaining module, configured to obtain prompt information, the prompt information being used to indicate a script configuration requirement;

[0014] a type determining module, configured to obtain at least one first script type according to the prompt information and historical configuration records, the historical configuration records being used to indicate script types configured in a historical time period;

[0015] a proportion determining module, configured to determine the proportion corresponding to each of the at least one first script type, the proportion corresponding to the first script type being used to represent the probability of the first script type being configured;

[0016] a script selecting module, configured to select a target script from a script library according to the proportion corresponding to each of the at least one first script type, the target script being used to generate audio corresponding to the target script in combination with a selected script tone.

[0017] According to an aspect of an embodiment of the present application, a computer device is provided, and the computer device comprises a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the script configuration method.

[0018] According to an aspect of an embodiment of the present application, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program, the computer program being loaded and executed by a processor to implement the script configuration method.

[0019] According to an aspect of an embodiment of the present application, a computer program product is provided, and the computer program product comprises a computer program, the computer program being loaded and executed by a processor to implement the script configuration method.

[0020] The technical solution provided by the embodiments of the present application can bring the following beneficial effects:

[0021] According to the prompt information input by the user and the historical configuration record, at least one first script label is obtained, and a proportion corresponding to each first script type is determined to obtain a probability of each first script type being configured, and a target script is selected from the script library according to the proportion corresponding to each first script type. Compared with the method for obtaining a target script based on a user's song listening scene in the related art, the present application obtains at least one first script label by combining the prompt information and the historical configuration record, increases the script types available for the target script, broadens the selection range of the target script, and avoids the single script type affecting the user's song listening experience. In addition, by proportionally analyzing the at least one first script label, the probability of each first script type being configured is obtained, so that the selected target script can meet the user's script configuration demand as much as possible, the coincidence degree of the target script and the prompt information is ensured, and the accuracy of script configuration is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0022] FIG. 1 is a schematic diagram of a computer system according to an embodiment of the present application;

[0023] FIG. 2 is a flowchart of a script configuration method according to an embodiment of the present application;

[0024] FIG. 3 is a flowchart of a script configuration method according to an embodiment of the present application;

[0025] FIG. 4 is a block diagram of a script configuration device according to an embodiment of the present application;

[0026] FIG. 5 is a structural block diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] To make the purpose, technical scheme and advantages of the present application clearer, the embodiments of the present application will be described in further detail below with reference to the drawings.

[0028] Please refer to FIG. 1, which shows a schematic diagram of a computer system according to an embodiment of the present application. The computer system can include a terminal device 10 and a server 20.

[0029] The number of terminal devices 10 can be one or more. The terminal device 10 can be an electronic device such as a mobile phone, a tablet computer, a notebook computer, a desktop computer, a game console, an e-book reader, a multimedia playback device, a wearable device, a smart television, a vehicle-mounted terminal, etc. The terminal device 10 can be installed with a client of a music application program, and the music application program has a function of playing a song. In the embodiments of the present application, the music application program has a function of playing an explanation audio before playing a song. Optionally, the music application program described above can be an application program that needs to be downloaded and installed, or an application program that can be used immediately after being clicked, which is not limited in the present application.

[0030] The server 20 is configured to provide background service for the client of the music application installed and running in the terminal device 10. For example, the server 20 can be a background server of the application. The server 20 can be a single server, a server cluster composed of multiple servers, or a cloud computing service center. Alternatively, the server 20 provides background service for the clients of the music application in multiple terminal devices 10. The terminal device 10 and the server 20 can communicate with each other through a network.

[0031] The server 20 stores a song library and a script library. The song library stores multiple songs, and the script library stores multiple scripts configured for the multiple songs respectively.

[0032] In the embodiment of the present application, the user inputs prompt information on the client of the music application in the terminal device 10 to indicate the user's script configuration requirement. The computer device obtains at least one first script type according to the prompt information input by the user and the historical configuration record of the user, filters the script library according to the first script type to obtain a script library containing only scripts corresponding to the first script type, and removes scripts in the script library that do not conform to the script style label contained in the prompt information to obtain a removed script library. The proportion corresponding to each of the at least one first script type is determined, and a target script is selected from the removed script library according to the proportion (probability). If the computer device is a server, the server returns the target script and the song corresponding to the target script to the client of the music application. After the user selects the script tone on the client, the server generates an audio corresponding to the selected script tone, and then returns the audio corresponding to the target script to the client. The client first plays the audio corresponding to the target script to introduce the song, and then plays the song corresponding to the target script. If the computer device is a terminal device, the terminal device directly generates an audio corresponding to the selected script tone, and then first plays the audio corresponding to the target script to introduce the song, and then plays the song corresponding to the target script.

[0033] Please refer to FIG. 2, which shows a flowchart of a script configuration method according to an embodiment of the present application. The execution subject of each step of the method can be a computer device. The method can include at least one of the following steps 220-280:

[0034] Step 220: Obtain prompt information input by a user, the prompt information being used to indicate a script configuration requirement.

[0035] The script refers to a song introduction script. One script is used to introduce one dimension of a song. The dimensions of the song include, but are not limited to, the creation experience of the song, the singing experience of the singer singing the song, the release time of the song, the song listening evaluation, the song cover experience, and the like. Exemplarily, if the script is used to introduce the creation experience of the song, the script can include the introduction of the songwriting experience of the songwriter, the composition experience of the song composer, the creation experience of other staff of the song, and the like. If the script is used to introduce the song release time, the script can include the elaboration of the specific song release time, the introduction of the reason for the song release time, and the like.

[0036] Before playing the song, the audio corresponding to the script is played, so that the user understands the related information of the song. After playing the audio corresponding to the script, the song corresponding to the script is played, so that the user can more fully enjoy the song and improve the song listening experience of the user. In the embodiment of the present application, the target script is selected from the script library according to the prompt information input by the user, the script configuration requirement of the user is met, and then the client on the terminal device can play the audio corresponding to the target script and play the song corresponding to the target script.

[0037] The prompt information includes script type information and script style information. The script type information is used to indicate the type requirement of the user for the target script, and the script style information is used to indicate the style requirement of the user for the target script.

[0038] The script type information is used to indicate at least one script type. The script type refers to the dimension type of the song introduced by the script, that is, one script type corresponds to one dimension of the song. The script type includes, but is not limited to, the script about the creation experience of the song, the script about the singing experience of the singer singing the song, the script about the release time of the song, the script about the song listening evaluation, the script about the song cover experience, and the like.

[0039] The script style information is used to indicate at least one script style, and the script style refers to a narrative style of a script. The script style includes, but is not limited to, a soothing script style, a calm script style, an exuberant script style, a heavy script style, a sentimental script style, and the like. The script style information can be information about a script style. For example, the script style information can be a "soothing script", and it can be determined that the script style indicated by the script style information is "soothing". The script style information can also be information about a song style. In this case, the information about a song style needs to be used to obtain a song style corresponding to the information about a song style, and a script style matched with the song style is obtained based on the song style corresponding to the information about a song style. For example, the script style information can be "suitable for listening quietly at night alone", and the song style is "quiet". In this case, the script style matched with the song style is "quiet". The script style information can also include information about a script style and information about a song style. In this case, a script style corresponding to the information about a script style and a script style matched with the song style are determined as the at least one script style. For example, the script style information can be "suitable for listening quietly at night alone, soothing script", and the at least one script style indicated by the script style information includes two script styles of "quiet" and "soothing".

[0040] For example, the prompt information input by the user can be "like to listen to a song creation story, when the song is released, suitable for listening briskly alone in the morning". In this case, the script type information is "like to listen to a song creation story, when the song is released", and the at least one script type indicated by the script type information includes a script about a creation experience of a song and a script about a release time of a song. The script style information is "suitable for listening briskly alone in the morning", and the script style information is information about a song style. According to the script style information, a song style corresponding to the information about a song style is obtained, and a script style matched with the song style is obtained. The at least one script style indicated by the script style information includes a "brisk" script style.

[0041] In step 240, at least one first script type is obtained according to the prompt information and a historical configuration record. The historical configuration record is used to indicate a script type configured in a historical time period.

[0042] The historical configuration record includes script information configured in a historical time period and listening records corresponding to the script configured in the historical time period. The script information configured in the historical time period is used to indicate at least one script configured in the historical time period, and the script type and script style of the at least one script configured in the historical time period can be obtained according to the at least one script configured in the historical time period. The listening records corresponding to the script configured in the historical time period include song information of at least one song corresponding to the script configured in the historical time period, listening time lengths respectively corresponding to the at least one song corresponding to the script configured in the historical time period, and song cutting conditions corresponding to the at least one song corresponding to the script configured in the historical time period.

[0043] The end moment of the historical time period is the current moment, which can be one week before the current moment, one month before the current moment, or half a year before the current moment, etc. The application does not limit the start moment of the historical time period, that is, the length of time of the historical time period is not limited.

[0044] According to the prompt information, at least one script type indicated by the extraction information is obtained; at least one historical script type is extracted according to the historical configuration record; and at least one first script type is obtained according to the at least one script type contained in the prompt information and the at least one historical script type. The at least one first script type includes the at least one script type contained in the prompt information and the at least one historical script type.

[0045] In some embodiments, the at least one first script type is obtained by the large language model according to the prompt information and the historical configuration record.

[0046] The specific steps of obtaining the first script type can refer to the following embodiments.

[0047] In some embodiments, step 240 further includes step 250 for screening and removing the script library according to the first script type and the prompt information to obtain a removed script library. Step 250 includes at least one of sub-steps 251-254 (not shown in the figure).

[0048] Sub-step 251: screening the script library according to the at least one first script type to obtain a screened script library, and the screened script library contains scripts corresponding to the at least one first script type.

[0049] According to the at least one song contained in the song library, a plurality of scripts corresponding to different script types are respectively configured for each song. The scripts configured for each song can be written and generated by technical personnel, or can be generated by a large language model, which is not limited by the application.

[0050] The multiple scripts corresponding to at least one song in the song library are stored in the script library. If a new song is added to the song library, multiple scripts corresponding to the new song are generated according to the new song, and the multiple scripts corresponding to the new song are stored in the script library.

[0051] After obtaining at least one first script type, the script library is screened to retain scripts corresponding to at least one first script type in the script library and remove scripts corresponding to script types other than at least one first script type in the script library, thereby obtaining a screened script library. Therefore, the screened script library only contains scripts corresponding to at least one first script type.

[0052] In sub-step 252, at least one script style label included in the prompt information and at least one script style label of at least one script included in the screened script library are obtained.

[0053] The script style information included in the prompt information is obtained, and at least one script style indicated by the script style information included in the prompt information is obtained according to the script style information included in the prompt information, so that a label corresponding to the at least one script style is generated, and at least one script style label is obtained.

[0054] As described above, if the script style information includes information about the script style, at least one script style corresponding to the information about the script style can be obtained according to the information about the script style. If the script style information includes information about the song style, at least one song style corresponding to the information about the song style can be obtained according to the information about the song style, and at least one script style matching the at least one song style can be obtained based on the at least one song style corresponding to the information about the song style.

[0055] According to the narrative style of at least one script included in the screened script library, at least one script style label of at least one script included in the screened script library is obtained.

[0056] In some embodiments, at least one script style label included in the prompt information and at least one script style label of at least one script included in the screened script library are obtained by a large language model.

[0057] In sub-step 253, the similarity between at least one script style label of at least one script included in the screened script library and at least one script style label included in the prompt information is calculated respectively, and at least one similarity score corresponding to at least one script included in the screened script library is obtained.

[0058] Optionally, the similarity between the text style label of the at least one text in the screened text library and the at least one text style label included in the prompt information is calculated by a cosine similarity calculation to obtain a similarity score corresponding to the at least one text in the screened text library.

[0059] In sub-step 254, the texts with similarity scores less than or equal to the second threshold value are removed from the screened text library to obtain a removed text library.

[0060] According to the similarity scores corresponding to the at least one text in the screened text library, the at least one text in the screened text library is sorted in descending order to obtain a sorted at least one text.

[0061] In some embodiments, the texts with similarity scores less than or equal to the second threshold value are removed from the screened text library among the sorted at least one text to obtain a removed text library. The removed text library includes at least one text with a similarity score greater than or equal to the second threshold value. The application does not limit the specific value of the second threshold value, which can be set to a default value by the technician or can be flexibly set according to the user's text configuration requirements. For example, if the number of texts corresponding to the text style indicated in the user's text configuration requirements is small, the second threshold value can be set to be small. If the number of texts corresponding to the text style indicated in the user's text configuration requirements is large, the second threshold value can be set to be large.

[0062] In some embodiments, the first number of texts at the back of the sorting are removed from the screened text library among the sorted at least one text to obtain a removed text library. The application does not limit the specific value of the first number, which can be set to a default value by the technician or can be flexibly set according to the user's text configuration requirements. For example, if the number of texts corresponding to the text style indicated in the user's text configuration requirements is small, the first number can be set to be small. If the number of texts corresponding to the text style indicated in the user's text configuration requirements is large, the first number can be set to be large.

[0063] In some embodiments, the first proportion of texts at the back of the sorting are removed from the text library among the sorted at least one text to obtain a removed text library. The application does not limit the specific value of the second threshold value, which can be set to a default value by the technician or can be flexibly set according to the user's text configuration requirements. For example, if the number of texts corresponding to the text style indicated in the user's text configuration requirements is small, the first proportion can be set to be small. If the number of texts corresponding to the text style indicated in the user's text configuration requirements is large, the first proportion can be set to be large.

[0064] By screening the copywriting library according to the first copywriting type, the screened copywriting library only contains the copywriting corresponding to the at least one first copywriting type, so that the configured target copywriting does not belong to the at least one first copywriting type and does not meet the copywriting configuration requirements of the user. According to the similarity between the at least one copywriting style label in the prompt information and the at least one copywriting style label in the prompt information, the screened copywriting library is screened again, so that the copywriting contained in the eliminated copywriting library is the copywriting with a higher association degree with the copywriting style label in the prompt information, and the configured target copywriting does not meet the copywriting configuration requirements of the user, thereby improving the compliance and accuracy of copywriting configuration.

[0065] In step 260, the proportion corresponding to the at least one first copywriting type is determined, and the proportion corresponding to the first copywriting type is used to represent the probability of the first copywriting type being configured.

[0066] For the at least one first copywriting type, a proportion is configured for each first copywriting type, and the proportion corresponding to each first copywriting type is used to represent the probability of the first copywriting type being configured. It can also be understood that the proportion corresponding to each first copywriting type is used to represent the probability of the first copywriting type being selected when selecting the target copywriting from the copywriting library.

[0067] For example, if the at least one first copywriting type includes copywriting type a, copywriting type b and copywriting type c, the proportion corresponding to the copywriting type a is 20%, the proportion corresponding to the copywriting type b is 50%, and the proportion corresponding to the copywriting type c is 30%, which means that the probability of selecting the copywriting type a is 20%, the probability of selecting the copywriting type b is 50%, and the probability of selecting the copywriting type c is 30%.

[0068] In step 280, the target copywriting is selected from the copywriting library according to the proportion corresponding to the at least one first copywriting type, and the target copywriting is used to generate the audio corresponding to the target copywriting in combination with the selected copywriting tone.

[0069] In some embodiments, the target copywriting is selected from the eliminated copywriting library according to the proportion corresponding to the at least one first copywriting type. The target copywriting refers to the copywriting selected by the probability.

[0070] By selecting the target copywriting from the eliminated copywriting library, the target copywriting is the copywriting with a higher association degree with the copywriting style label in the prompt information, so that the configured target copywriting can meet the copywriting configuration requirements of the user as much as possible, thereby improving the compliance and accuracy of copywriting configuration.

[0071] After obtaining the target script, the user can select a script tone suitable for the target script based on the target script, and then the computer device generates an audio corresponding to the target script according to the script tone selected by the user, and plays the audio corresponding to the target script. Then, a song corresponding to the target script is obtained, and the song corresponding to the target script is played.

[0072] The selected script tone here is any one of at least one pre-configured script tone, which can be a tone generated based on real human voice or a mechanical tone generated based on AI, and the present application does not limit this. The script tone can include tones of females and males of different age groups, such as tones of young males and females, tones of middle-aged males and females, tones of old males and females, etc. The script tone can also configure different tones for the tones of females and males of different age groups, such as configuring a gentle tone, a serious tone, a light tone, etc. for the tone of a middle-aged female. The script tone can also configure different emotions for the tones of females and males of different age groups, such as configuring an excited emotion, a calm emotion, a sad emotion, etc. for the tone of a middle-aged female.

[0073] The technical solution provided by the embodiments of the present application obtains at least one first script label according to the prompt information and the historical configuration record input by the user, and determines the proportion corresponding to each first script type, to obtain the probability of each first script type being configured, and selects a target script from the script library according to the proportion corresponding to each first script type. Compared with the method of obtaining a target script based on a user's listening scene in the related art, the present application increases the script types available for the target script by combining the prompt information and the historical configuration record to obtain at least one first script label, broadens the selection range of the target script, and avoids the single script type affecting the user's listening experience. Moreover, by analyzing the proportion of the at least one first script label, the probability of each first script type being configured is obtained, so that the selected target script can meet the script configuration needs of the user as much as possible, ensuring the compliance of the target script and the prompt information, and ensuring the accuracy of the script configuration.

[0074] In some embodiments, step 240 includes at least one of sub-steps 241-243 (not shown in the figure).

[0075] In sub-step 241, at least one script type contained in the prompt information is obtained.

[0076] According to the prompt information, script type information contained in the prompt information is obtained, and at least one script type indicated by the script type information is obtained according to the script type information.

[0077] In sub-step 242, at least one historical script type is extracted according to the historical configuration record. The historical script type refers to a script type configured in the historical time period and having reference significance.

[0078] The historical configuration record includes script information configured in the historical time period and listening record corresponding to the script configured in the historical time period. According to the script information configured in the historical time period, the script type of at least one script configured in the historical time period is obtained. Here, the script types corresponding to the at least one script configured in the historical time period can be repeated. Then, the script types corresponding to the at least one script configured in the historical time period are integrated to obtain the script type of the at least one script configured in the historical time period.

[0079] According to the script type of the at least one script configured in the historical time period, at least one historical script type is obtained. The historical script type refers to a script type configured in the historical time period and having reference significance, specifically, a script type in the script type configured in the historical time period and having reference significance for current script configuration.

[0080] In some embodiments, the script type configured in the historical time period is determined as the historical script type.

[0081] That is, all script types of scripts configured in the historical time period have reference significance for current script configuration. Then, all script types of scripts configured in the historical time period can be determined as the historical script type.

[0082] In some embodiments, according to the configuration times of the at least one script type configured in the historical time period, a script type with a configuration time greater than or equal to a first threshold value is determined as the historical script type.

[0083] Since the at least one script type configured in the historical time period is repeatedly configured, it is indicated that, among all script types of scripts configured in the historical time period, the script type with the configuration time greater than or equal to the first threshold value has reference significance for current script configuration, and the script type with the configuration time less than the first threshold value does not have reference significance for current script configuration.

[0084] According to the configuration times of the at least one script type configured in the historical time period, the at least one script type is sorted in descending order to obtain the sorted at least one script type.

[0085] Optionally, the template type with a configuration number greater than or equal to the first threshold value in the ranked at least one template type can be determined as the historical template type. The application does not limit the specific value of the first threshold value, which can be set to a default value by the technical personnel, or can be flexibly set according to the number of template types configured in the historical time period. For example, if the number of template types configured in the historical time period is small, the first threshold value can be set to be larger, and if the number of template types configured in the historical time period is large, the first threshold value can be set to be smaller.

[0086] Optionally, the second number of template types with high ranking in the ranked at least one template type can also be determined as the historical template type. The application does not limit the specific value of the second number, which can be set to a default value by the technical personnel, or can be flexibly set according to the number of template types configured in the historical time period. For example, if the number of template types configured in the historical time period is small, the second number can be set to be larger, and if the number of template types configured in the historical time period is large, the second number can be set to be smaller.

[0087] Optionally, the second proportion of template types with high ranking in the ranked at least one template type can also be determined as the historical template type. The application does not limit the specific value of the second proportion, which can be set to a default value by the technical personnel, or can be flexibly set according to the number of template types configured in the historical time period. For example, if the number of template types configured in the historical time period is small, the second proportion can be set to be larger, and if the number of template types configured in the historical time period is large, the second proportion can be set to be smaller.

[0088] In some embodiments, if the time length of the historical time period is less than or equal to the first time length, the template types configured in the historical time period are determined as the historical template type; if the time length of the historical time period is greater than the first time length, the template type with a configuration number greater than or equal to the first threshold value is determined as the historical template type.

[0089] That is, in the case where the length of the historical configuration record is short, the template types of all templates configured in the historical time period have reference significance for the current template configuration, and in the case where the length of the historical configuration record is short, a part of the template types of all templates configured in the historical time period have reference significance for the current template configuration.

[0090] Optionally, if the time length of the historical time period is greater than the first time length, the second number of template types with high ranking in the configuration number can also be determined as the historical template type. Or, the second proportion of template types with high ranking in the configuration number can also be determined as the historical template type.

[0091] The first time length is not limited in the present application, and a default value can be set by the technician, or the number of configured text types in the historical time period can be flexibly set. For example, if the number of configured text types in the historical time period is small, the first time length can be set to be large, and if the number of configured text types in the historical time period is large, the first time length can be set to be small.

[0092] By providing different schemes for determining historical text types, the historical text types are text types with configuration significance, and the corresponding determination scheme of the historical text types can be selected according to the time length of the historical time period, so that the determined historical text types can meet the configuration preferences of the user, thereby improving the accuracy of the configured target text and enhancing the listening experience of the user.

[0093] In substep 243, at least one first text type is obtained according to the at least one text type and the at least one historical text type contained in the prompt information.

[0094] Since there can be repeated text types in the at least one text type and the at least one historical text type contained in the prompt information, the at least one text type and the at least one historical text type contained in the prompt information need to be integrated to obtain at least one first text type.

[0095] The above method combines the prompt information and the historical configuration record to obtain at least one first text label, which not only increases the text types available for the target text and widens the selection range of the target text, but also ensures that the configured target text can meet the configuration preferences of the user and improve the compliance and accuracy of the target text.

[0096] In some embodiments, step 260 includes at least one of substeps 261-263 (not shown in the figure).

[0097] In substep 261, a first proportion is configured for each of the at least one text type contained in the prompt information.

[0098] The first proportion can be a proportion set by the user or a proportion set by the technician, and the present application is not limited in this regard.

[0099] The prompt information includes at least one script type, and a first proportion is configured for each script type included in the prompt information, that is, the proportion corresponding to each of the at least one script type included in the prompt information is the first proportion. Alternatively, a total proportion that the at least one script type included in the prompt information needs to be configured can be set by the user or the technician in advance, and then the proportion that each script type included in the prompt information needs to be configured can be obtained according to the number of the at least one script type included in the prompt information.

[0100] For example, if the user or the technician sets the total proportion that the at least one script type included in the prompt information needs to be configured as 50%, and the at least one script type included in the prompt information includes a script type a and a script type b, the first proportion is 25%, and the proportions corresponding to the script type a and the script type b are both 25%.

[0101] In substep 262, the initial proportions corresponding to the at least one historical script type are determined according to the song playing information corresponding to the at least one historical script type in the historical configuration record, and the sum of the initial proportions corresponding to the at least one historical script type is 1.

[0102] Each historical script type corresponds to at least one song, and the song playing information corresponding to the at least one historical script type refers to the song playing information of the at least one song corresponding to the at least one historical script type. The historical configuration record includes script information configured in a historical time period and listening records corresponding to scripts configured in the historical time period. The song playing information of the at least one song corresponding to the at least one historical script type is obtained according to the listening records corresponding to the scripts configured in the historical time period.

[0103] In some embodiments, the song playing information corresponding to the at least one historical script type includes at least one of the following: a playing time of the at least one song corresponding to the at least one historical script type; a number of times of song switching of the at least one song corresponding to the at least one historical script type; and a number of songs corresponding to the at least one historical script type.

[0104] Alternatively, if the song playing information corresponding to the at least one historical script type only includes the playing time of the at least one song corresponding to the at least one historical script type, the total playing time of all songs corresponding to the at least one historical script type and the sum of the playing times of the at least one song corresponding to each historical script type can be obtained according to the playing time of the at least one song corresponding to the at least one historical script type in the historical configuration record. The proportion of the sum of the playing times of the at least one song corresponding to each historical script type relative to the total playing time is used to obtain the initial proportion corresponding to each historical script type.

[0105] Optionally, if the song play information corresponding to the at least one historical script type only includes the number of times of song switching of at least one song corresponding to the at least one historical script type respectively, the total number of times of song switching of all songs corresponding to the at least one historical script type and the sum of the number of times of song switching of at least one song corresponding to each historical script type can be obtained according to the number of times of song switching of at least one song corresponding to the at least one historical script type in the historical configuration record respectively. The proportion of the sum of the number of times of song switching of at least one song corresponding to each historical script type to the total number of times of song switching is obtained to obtain the initial proportion corresponding to each historical script type.

[0106] Optionally, if the song play information corresponding to the at least one historical script type only includes the number of songs corresponding to the at least one historical script type respectively, the total number of songs corresponding to the at least one historical script type and the number of songs corresponding to each historical script type can be obtained according to the number of songs corresponding to the at least one historical script type in the historical configuration record respectively. The proportion of the number of songs corresponding to each historical script type to the total number of songs is obtained to obtain the initial proportion corresponding to each historical script type.

[0107] Optionally, if the song play information corresponding to the at least one historical script type includes at least two song play information, after obtaining the initial proportion corresponding to each historical script type corresponding to each song play information based on each song play information, the final initial proportion corresponding to the at least one historical script type can be calculated according to the weight corresponding to the at least two song play information. The sum of the final initial proportion corresponding to the at least one historical script type is 1.

[0108] Illustratively, if the song play information corresponding to the at least one historical script type includes the play duration of at least one song corresponding to the at least one historical script type respectively and the number of times of song switching of at least one song corresponding to the at least one historical script type respectively, the at least one historical script type includes script type c and script type d, the initial proportion corresponding to the script type c is 20% and the initial proportion corresponding to the script type d is 80% based on the play duration of at least one song corresponding to the at least one historical script type respectively, and the initial proportion corresponding to the script type c is 40% and the initial proportion corresponding to the script type d is 60% based on the number of times of song switching of at least one song corresponding to the at least one historical script type respectively. If the weight corresponding to the play duration is 0.2 and the weight corresponding to the number of times of song switching is 0.8, the final initial proportion corresponding to the script type c is 36% and the final initial proportion corresponding to the script type d is 64%. The sum of the final initial proportion corresponding to the script type c and the script type d is 1.

[0109] The application does not limit the weight corresponding to each song playing information, which can be set to a default value by a technician, and the sum of the weights corresponding to at least two song playing information is 1.

[0110] By considering multiple song playing information of the song, the initial proportion corresponding to each historical script type is determined, the preference of the user for different historical script types is considered, the probability of the historical script type with shorter song playing time, more song switching times, or fewer song numbers being configured is reduced, and the satisfaction of the user for the target script is improved.

[0111] In substep 263, the proportion corresponding to each historical script type is obtained according to the initial proportion corresponding to each historical script type, and the sum of the proportion corresponding to each historical script type and the at least one first proportion is 1.

[0112] According to the total proportion of at least one script type configured in the prompt information, the total proportion of at least one historical script type is obtained; the initial proportion corresponding to each historical script type is multiplied by the total proportion of at least one historical script type to obtain the proportion corresponding to each historical script type.

[0113] For example, if the total proportion of at least one script type is 50%, the proportion corresponding to script type a and script type b is 25%. Then the total proportion of at least one historical script type is 50%, the initial proportion corresponding to script type c is 40%, and the initial proportion corresponding to script type d is 60%. The proportion corresponding to script type c is 20%, and the initial proportion corresponding to script type d is 30%. The sum of the proportions corresponding to script type a, script type b, script type c and script type d is 1.

[0114] By configuring the proportion of at least one script type and at least one historical script type in the prompt information, the target script can be selected from the script library according to the proportion corresponding to each first script type, which provides a selection basis for the selection of the target script and ensures the accuracy of the target script.

[0115] In some embodiments, the above method further includes step 290 for generating an adjusted target script corresponding to audio according to user input adjustment information, and obtaining an adjusted target script corresponding to a song. Step 290 includes at least one of substeps 291-293 (not shown in the figure).

[0116] In substep 291, adjustment information is obtained, and the adjustment information is used to adjust the script configuration requirement.

[0117] The adjustment information is prompt information input by the user again after inputting the prompt information, and is used to adjust the script configuration requirement in the prompt information.

[0118] The adjustment information can increase the script configuration requirement in the prompt information, or modify the script configuration requirement in the prompt information, which is not limited in the application.

[0119] In substep 292, the prompt information and the adjustment information are integrated to obtain adjusted prompt information.

[0120] For example, if the prompt information is "like to listen to song creation story, when the song is released, and is suitable for listening to in the morning alone", and the adjustment information is "like to listen to the evaluation of the song", the adjusted prompt information is "like to listen to song creation story, like to listen to the evaluation of the song, when the song is released, and is suitable for listening to in the morning alone".

[0121] For example, if the prompt information is "like to listen to song creation story, when the song is released, and is suitable for listening to in the morning alone", and the adjustment information is "suitable for listening to in the evening alone", the adjusted prompt information is "like to listen to song creation story, when the song is released, and is suitable for listening to in the evening alone".

[0122] In substep 293, the adjusted target script is selected from the script library according to the adjusted prompt information, and the adjusted target script is used to combine the selected script timbre to generate an audio corresponding to the adjusted target script.

[0123] The adjusted target script can be obtained by referring to the above embodiments, and the specific process will not be described again.

[0124] In some embodiments, if the user still needs to adjust the script configuration requirement, the user can continue to input adjustment information to generate a target script adjusted again.

[0125] Through multiple rounds of prompt information input by the user, the script configuration requirement is updated, and the adjusted target script is generated according to the adjusted prompt information, so that the script meeting the user's requirement can be continuously obtained, and the user's satisfaction with the script configuration is improved.

[0126] FIG. 3 shows a flowchart of the script configuration. According to the prompt information input by the user, the computer device obtains at least one script type and at least one script style label contained in the prompt information through the large language model according to the prompt information. At least one historical script type is obtained through the large language model according to the historical configuration record. The at least one script type contained in the prompt information and the at least one historical script type are fused to obtain at least one first script type. The proportion of the at least one first script type is analyzed to obtain the proportion corresponding to each of the at least one script type.

[0127] In addition, according to the first script type, other types in the script library except the first script type are removed to obtain a screened script library. According to the similarity between the script style label of at least one script contained in the screened script library and the at least one script style label contained in the prompt information, the scripts with a similarity not meeting the requirement are removed to obtain a removed script library. According to the proportion corresponding to each of the at least one first script type, the target script is selected from the removed script library.

[0128] If the user is satisfied with the selected target script, the target script corresponding audio is generated according to the script tone selected by the user and played, and the script configuration process is ended. Subsequently, the terminal device plays the song corresponding to the target script. If the user is not satisfied with the selected target script, the user can input adjustment information again for adjusting the script configuration requirement. The prompt information and the adjustment information are integrated to obtain adjusted prompt information. According to the adjusted prompt information, the above script configuration process is experienced again to generate an adjusted target script. Until the adjusted target script is satisfied, the adjusted target script corresponding audio is generated according to the script tone selected by the user and played, thereby ending the script configuration process.

[0129] The following is an embodiment of the device of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0130] Please refer to FIG. 4, which shows a block diagram of a script configuration device according to an embodiment of the present application. The device has the functions of implementing the above script configuration method, which can be realized by hardware or corresponding software executed by hardware. The device can be the computer device introduced above or can be arranged in the computer device. As shown in FIG. 4, the device 400 can include an information acquisition module 410, a type determination module 420, a proportion determination module 430, and a script selection module 440.

[0131] The information acquisition module 410 is configured to acquire prompt information, wherein the prompt information is used to indicate script configuration requirements.

[0132] The type determination module 420 is configured to obtain at least one first script type according to the prompt information and historical configuration records, the historical configuration records being used to indicate script types configured in a historical time period.

[0133] The proportion determination module 430 is configured to determine proportions corresponding to the at least one first script type respectively, the proportions corresponding to the first script types being used to represent probabilities of the first script types being configured.

[0134] The script selection module 440 is configured to select a target script from a script library according to the proportions corresponding to the at least one first script type respectively, the target script being used to generate audio corresponding to the target script in combination with a selected script tone.

[0135] In some embodiments, the type determination module 420 is configured to:

[0136] obtain at least one script type contained in the prompt information;

[0137] extract at least one historical script type according to the historical configuration records, the historical script type being a script type configured in the historical time period and having reference significance;

[0138] obtain the at least one first script type according to the at least one script type contained in the prompt information and the at least one historical script type.

[0139] In some embodiments, the type determination module 420 is configured to:

[0140] determine script types configured in the historical time period as the historical script types;

[0141] alternatively,

[0142] determine, according to configuration times of at least one script type configured in the historical time period, script types with configuration times greater than or equal to a first threshold value as the historical script types;

[0143] alternatively,

[0144] if a time length of the historical time period is less than or equal to a first time length, determine script types configured in the historical time period as the historical script types; and if the time length of the historical time period is greater than the first time length, determine script types with configuration times greater than or equal to the first threshold value as the historical script types.

[0145] In some embodiments, the proportion determination module 430 is configured to:

[0146] configure a first proportion for each of the at least one script type contained in the prompt information respectively;

[0147] determine an initial proportion corresponding to each of the at least one historical script type according to the song playing information corresponding to the at least one historical script type in the historical configuration record, and the sum of the initial proportions corresponding to the at least one historical script type is 1;

[0148] obtain a proportion corresponding to each of the at least one historical script type according to the initial proportion corresponding to each of the at least one historical script type, and the sum of the proportion corresponding to each of the at least one historical script type and at least one first proportion is 1.

[0149] In some embodiments, the song playing information corresponding to the at least one historical script type comprises at least one of the following:

[0150] the playing time of at least one song corresponding to each of the at least one historical script type;

[0151] the number of song switching of at least one song corresponding to each of the at least one historical script type;

[0152] the number of songs corresponding to each of the at least one historical script type.

[0153] In some embodiments, the device 400 further comprises a script library screening module (not shown in the figure), which is configured to:

[0154] screen the script library according to the at least one first script type to obtain a screened script library, and the screened script library contains scripts corresponding to each of the at least one first script type;

[0155] obtain at least one script style label contained in the prompt information and at least one script style label contained in the screened script library;

[0156] respectively calculate the similarity between the script style label of at least one script contained in the screened script library and the at least one script style label contained in the prompt information to obtain a similarity score corresponding to each of the at least one script contained in the screened script library;

[0157] eliminate scripts with a similarity score less than or equal to a second threshold from the screened script library to obtain an eliminated script library.

[0158] In some embodiments, the script selection module 440 is configured to:

[0159] According to the proportion corresponding to the at least one first script type, the target script is selected from the script library after the elimination.

[0160] In some embodiments, the apparatus 400 further comprises a script adjustment module (not shown in the figure), configured to:

[0161] obtain adjustment information, the adjustment information being used for adjusting the script configuration requirement;

[0162] integrate the prompt information and the adjustment information to obtain adjusted prompt information;

[0163] select an adjusted target script from the script library according to the adjusted prompt information, the adjusted target script being used for generating audio corresponding to the adjusted target script in combination with the selected script tone.

[0164] It should be noted that the apparatus provided in the above embodiments, in realizing its functions, is only exemplified by the above division of functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the content structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be described here.

[0165] Please refer to FIG. 5, which shows a structural block diagram of a computer device 500 provided in an embodiment of the present application. The computer device 500 can be any electronic device with data computing, processing and storage functions. The computer device 500 can be used to implement the script configuration method provided in the above embodiments.

[0166] Generally, the computer device 500 comprises a processor 501 and a memory 502.

[0167] The processor 501 can include one or more processing cores, such as a 4-core processor, an 8-core processor, and the like. The processor 501 can be implemented in at least one of a hardware form of a DSP (Digital Signal Processing), an FPGA (Field Programmable Gate Array), a PLA (Programmable Logic Array). The processor 501 can also include a main processor and a co-processor, the main processor being a processor for processing data in an awake state, also referred to as a CPU (Central Processing Unit), and the co-processor being a low-power processor for processing data in a standby state. In some embodiments, the processor 501 can be integrated with a GPU (Graphics Processing Unit) for rendering and drawing content required to be displayed by the display screen. In some embodiments, the processor 501 can further include an AI processor for processing computing operations related to machine learning.

[0168] The memory 502 can include one or more computer-readable storage media, which can be non-transitory. The memory 502 can also include a high-speed random access memory, and a nonvolatile memory such as one or more disk storage devices, flash storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 502 is configured to store a computer program configured to be executed by one or more processors to implement the above-described text configuration method.

[0169] Those skilled in the art can understand that the structure shown in FIG. 5 does not constitute a limitation on the computer device 500, and can include more or fewer components than illustrated, or combine certain components, or adopt different component arrangements.

[0170] In an illustrative embodiment, a computer-readable storage medium is also provided, the storage medium storing a computer program, the computer program being configured to implement the above-described text configuration method when executed by a processor of a computer device. Optionally, the above-described computer-readable storage medium can be a ROM (Read-Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0171] In an example embodiment, a computer program product is also provided, which includes a computer program stored in a computer readable storage medium. A processor of a computer device reads the computer program from the computer readable storage medium, and the processor executes the computer program, so that the computer device performs the above-mentioned script configuration method.

[0172] It should be understood that "multiple" mentioned herein refers to two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A existing alone, A and B existing together, and B existing alone. The character " / " generally represents that the associated objects before and after it are in an "or" relationship. In addition, the step numbers described herein only exemplarily show a possible execution order between steps. In some other embodiments, the above steps can also be executed in a non-numbered order, such as two steps with different numbers being executed at the same time, or two steps with different numbers being executed in an order opposite to that shown in the figure, and the embodiments of the present application are not limited in this regard.

[0173] The above only describes example embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A script configuration method, the method being executed by a computer device, the method comprising: obtaining prompt information, the prompt information being used to indicate a script configuration requirement; obtaining at least one first script type according to the prompt information and historical configuration records, the historical configuration records being used to indicate script types configured in a historical time period; determining proportions respectively corresponding to the at least one first script type, the proportions respectively corresponding to the first script types being used to represent probabilities of the first script types being configured; selecting target scripts from a script library according to the proportions respectively corresponding to the at least one first script type, the target scripts being used to generate audios corresponding to the target scripts in combination with selected script tones.

2. The method of claim 1, wherein, The obtaining at least one first script type according to the prompt information and historical configuration records comprises: obtaining at least one script type contained in the prompt information; extracting at least one historical script type according to the historical configuration records, the historical script type being a script type configured in the historical time period and having reference significance; obtaining the at least one first script type according to the at least one script type contained in the prompt information and the at least one historical script type.

3. The method of claim 2, wherein, The extracting at least one historical script type according to the historical configuration records comprises: determining script types configured in the historical time period as the historical script types; or, determining script types with configuration times greater than or equal to a first threshold value as the historical script types according to the configuration times of at least one script type configured in the historical time period; or, if a time length of the historical time period is less than or equal to a first time length, determining script types configured in the historical time period as the historical script types; if the time length of the historical time period is greater than the first time length, determining script types with configuration times greater than or equal to the first threshold value as the historical script types.

4. The method of claim 2 or 3, wherein, The determining proportions respectively corresponding to the at least one first script type comprises: configuring first proportions respectively for the at least one script type contained in the prompt information; determining initial proportions respectively corresponding to the at least one historical script type according to song playing information corresponding to the at least one historical script type in the historical configuration records, the sum of the initial proportions respectively corresponding to the at least one historical script type being 1; obtaining proportions respectively corresponding to the at least one historical script type according to the initial proportions respectively corresponding to the at least one historical script type, the sum of the proportions respectively corresponding to the at least one historical script type and at least one first proportion being 1.

5. The method of claim 4, wherein, The song playing information corresponding to the at least one historical script type comprises at least one of the following: playing time lengths of at least one song corresponding to the at least one historical script type; song switching times of the at least one song corresponding to the at least one historical script type; numbers of songs corresponding to the at least one historical script type.

6. The method according to any one of claims 1 to 5, wherein, After the obtaining at least one first script type according to the prompt information and historical configuration records, the method further comprises: screen the script library according to the at least one first script type, to obtain a screened script library, the screened script library containing scripts corresponding to the at least one first script type respectively; obtain at least one script style label contained in the prompt information and at least one script style label contained in the screened script library; calculate similarity between the at least one script style label contained in the prompt information and the at least one script style label contained in the screened script library respectively, to obtain a similarity score corresponding to at least one script contained in the screened script library respectively; eliminate scripts with a similarity score less than or equal to a second threshold from the screened script library, to obtain an eliminated script library.

7. The method of claim 6, wherein, The selecting target scripts from the script library according to the proportion corresponding to the at least one first script type comprises: selecting the target scripts from the eliminated script library according to the proportion corresponding to the at least one first script type.

8. The method according to any one of claims 1 to 7, wherein, The method further comprises: obtaining adjustment information, the adjustment information being used to adjust the script configuration requirement; integrating the prompt information and the adjustment information, to obtain adjusted prompt information; selecting an adjusted target script from the script library according to the adjusted prompt information, the adjusted target script being used to generate audio corresponding to the adjusted target script in combination with a selected script tone. 9.A script configuration device, the device comprising: an information obtaining module, configured to obtain prompt information, the prompt information being used to indicate a script configuration requirement; a type determining module, configured to obtain at least one first script type according to the prompt information and historical configuration records, the historical configuration records being used to indicate script types configured in a historical time period; a proportion determining module, configured to determine a proportion corresponding to the at least one first script type respectively, the proportion corresponding to the first script type being used to represent a probability of the first script type being configured; a script selecting module, configured to select target scripts from a script library according to the proportion corresponding to the at least one first script type respectively, the target scripts being used to generate audio corresponding to the target scripts in combination with selected script tones. 10.A computer device, comprising a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the script configuration method according to any one of claims 1 to 8. 11.A computer readable storage medium, storing a computer program, the computer program being loaded and executed by a processor to implement the script configuration method according to any one of claims 1 to 8. 12.A computer program product, comprising a computer program, the computer program being loaded and executed by a processor to implement the script configuration method according to any one of claims 1 to 8.

Images