Ssummary generation method and device, equipment and storage medium

Abstract

The invention provides a summary generation method and device, equipment and a storage medium, and relates to the field of data processing, in particular to the field of artificial intelligence. According to the specific implementation scheme, an audio file uploaded by a user is acquired, and an audio scene corresponding to the audio file is determined; in response to the monitored summary generation instruction for the audio file, judging whether the audio file has a corresponding transcription text or not; in response to a transcriptional text corresponding to the audio file, determining a first summary generation model corresponding to the transcriptional text according to the audio scene and a preset summary template corresponding to the audio scene; inputting the transcriptional text into a first summary generation model, and obtaining a first summary text output by the first summary generation model according to a preset summary template; and displaying the first summary text on a display screen of the user.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, in particular to the field of artificial intelligence, and specifically to a method, device, equipment and storage medium for generating minutes. Background Art

[0002] In the era of rapid development of informatization and mobile Internet, recording equipment has become an indispensable tool for people's work and life. From early voice recorders to the recording function on modern smartphones, users' demand for recording technology has been growing. These recording devices and applications can record audio information, but often have certain deficiencies in post-recording processing and organization.

[0003] Traditional audio transcription can only provide the original text transcription, and cannot fully understand the context of the audio content, nor can it automatically extract key information and summarize the main points. Therefore, in many cases, users still need to spend a lot of time screening and editing the transcribed text to form a readable and practical minutes, often facing the problem of cumbersome information organization and low efficiency. Summary of the invention

[0004] The present disclosure provides a method, device, equipment and storage medium for generating minutes.

[0005] According to one aspect of the present disclosure, a method for generating minutes is provided, including: obtaining an audio file uploaded by a user, and determining an audio scene corresponding to the audio file; in response to monitoring a minutes generation instruction for the audio file, determining whether the audio file already has a corresponding transcribed text; in response to the audio file already having a corresponding transcribed text, determining a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene; inputting the transcribed text into the first minutes generation model, obtaining a first minutes text output by the first minutes generation model according to the preset minutes template; and displaying the first minutes text on the user's display screen.

[0006] This application can effectively realize automated audio transcription and minutes generation, significantly reducing the time required for users to manually organize audio records, improving work efficiency, reducing human intervention and errors, and improving the accuracy of information extraction and presentation.

[0007] According to one embodiment of the present application, in response to monitoring a minutes generation instruction for an audio file, determining whether the audio file already has a corresponding transcribed text includes: in response to receiving a minutes generation instruction for an audio file, determining whether the user has artificial intelligence generated content AIGC authority; in response to the user having AIGC authority, determining whether the audio file already has a corresponding transcribed text.

[0008] According to one embodiment of the present application, the method for generating minutes also includes: in response to the user not having AIGC authority, displaying a first prompt box on the display screen, the first prompt box being used to remind the user to perform AIGC authorization.

[0009] According to one embodiment of the present application, the method for generating minutes also includes: in response to the audio file having no corresponding transcribed text, displaying a second prompt box on the display screen, the second prompt box being used to remind the user to transcribe the audio file into the corresponding transcribed text; in response to detecting a user's click operation on the second prompt box, transcribing the audio file into text to obtain the transcribed text corresponding to the audio file; displaying the transcribed text on the display screen, and displaying a third prompt box on the display screen, the third prompt box being used to remind the user to generate a corresponding minutes text based on the transcribed text; in response to detecting a user's click operation on the third prompt box, executing a first minutes generation model and subsequent steps corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene.

[0010] According to one embodiment of the present application, after displaying the first minutes text on the user's display screen, it also includes: in response to monitoring the user's click operation on the text content contained in the first minutes text, obtaining the text position corresponding to the text content in the transcribed text, highlighting the corresponding text position in the transcribed text, and positioning the audio file to the audio position corresponding to the text position and starting to play the audio file from the audio position.

[0011] According to one embodiment of the present application, after displaying the first minutes text on the user's display screen, it also includes: in response to monitoring the user's click operation on the minutes template switching box on the display screen, displaying multiple candidate minutes templates on the display screen; in response to monitoring the user's selection and confirmation operation on any candidate minutes template, using the candidate minutes template as the target minutes template; calling the corresponding second minutes generation model according to the audio scene and the target minutes template to re-generate minutes for the transcribed text and obtain the generated second minutes text; replacing the first minutes text based on the second minutes text and displaying it on the display screen.

[0012] According to an embodiment of the present application, the method for generating minutes further includes: for any text among the transcribed text, the first minutes text and the second minutes text, in response to monitoring the user's editing operation on any text, updating any text based on the editing operation.

[0013] According to one embodiment of the present application, the method for generating minutes also includes: for any text among the transcribed text, the first minutes text and the second minutes text, in response to monitoring the user's export operation on any text, generating a text file based on any text, wherein the name of the text file is the same as that of the audio file; obtaining the storage location of the audio file, and storing the text file in the storage location.

[0014] According to one embodiment of the present application, text-transcribe an audio file to obtain a transcribed text corresponding to the audio file, including: determining whether a user has subscribed to an audio transcription service; in response to the user having subscribed to the audio transcription service, transcribing the audio file to obtain a transcribed text corresponding to the audio file; in response to the user not subscribing to the audio transcription service, displaying a fourth prompt box on the display screen, the fourth prompt box being used to remind the user to subscribe to the audio transcription service.

[0015] According to one embodiment of the present application, determining a first minutes generation model corresponding to a transcribed text according to an audio scene and a preset minutes template corresponding to the audio scene includes: determining whether a user has subscribed to a minutes generation service; in response to the user having subscribed to the minutes generation service, determining a first minutes generation model corresponding to the transcribed text according to the audio scene and the preset minutes template corresponding to the audio scene; in response to the user not having subscribed to the minutes generation service, displaying a fifth prompt box on a display screen, the fifth prompt box being used to remind the user to subscribe to the minutes generation service.

[0016] According to another aspect of the present disclosure, a device for generating minutes is provided, including: an audio acquisition module, used to acquire an audio file uploaded by a user, and to determine an audio scene corresponding to the audio file; a transcription judgment module, used to determine whether the audio file already has a corresponding transcription text in response to monitoring a minutes generation instruction for the audio file; a model determination module, used to determine a first minutes generation model corresponding to the transcription text according to the audio scene and a preset minutes template corresponding to the audio scene in response to the audio file already having a corresponding transcription text; a minutes generation module, used to input the transcription text into the first minutes generation model, and obtain a first minutes text output by the first minutes generation model according to the preset minutes template; and a minutes display module, used to display the first minutes text on the user's display screen.

[0017] According to one embodiment of the present application, the transcription judgment module is also used to: in response to receiving an instruction to generate a minutes for an audio file, determine whether the user has artificial intelligence generated content AIGC authority; in response to the user having AIGC authority, determine whether the audio file already has a corresponding transcription text.

[0018] According to one embodiment of the present application, the transcription judgment module is also used to: in response to the user not having AIGC authority, display a first prompt box on the display screen, and the first prompt box is used to remind the user to perform AIGC authorization.

[0019] According to one embodiment of the present application, the model determination module is also used to: in response to the audio file having no corresponding transcribed text, display a second prompt box on the display screen, the second prompt box being used to remind the user to transcribe the audio file into the corresponding transcribed text; in response to detecting a user's click operation on the second prompt box, perform text transcription on the audio file to obtain the transcribed text corresponding to the audio file; display the transcribed text on the display screen, and display a third prompt box on the display screen, the third prompt box being used to remind the user to generate a corresponding minutes text based on the transcribed text; in response to detecting a user's click operation on the third prompt box, determine a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene.

[0020] According to one embodiment of the present application, the minutes generation device also includes: a text positioning module, which is used to respond to monitoring the user's click operation on the text content contained in the first minutes text, and obtain the text position corresponding to the text content in the transcribed text; an audio positioning module, which is used to highlight the corresponding text position in the transcribed text, and position the audio file to the audio position corresponding to the text position and start playing the audio file from the audio position.

[0021] According to one embodiment of the present application, the minutes generation device also includes a minutes template switching module, which is used to: in response to monitoring the user's click operation on the minutes template switching box on the display screen, display multiple candidate minutes templates on the display screen; in response to monitoring the user's selection and confirmation operation on any candidate minutes template, use the candidate minutes template as the target minutes template; call the corresponding second minutes generation model according to the audio scene and the target minutes template to re-generate minutes for the transcribed text, and obtain the generated second minutes text; replace the first minutes text based on the second minutes text and display it on the display screen.

[0022] According to one embodiment of the present application, the minutes generation device also includes a text editing module, which is used to: for any text among the transcribed text, the first minutes text and the second minutes text, in response to monitoring the user's editing operation on any text, update any text based on the editing operation.

[0023] According to one embodiment of the present application, the minutes generation device also includes a text export module, which is used to: for any text among the transcribed text, the first minutes text and the second minutes text, in response to monitoring the user's export operation on any text, generate a text file based on any text, wherein the name of the text file is the same as that of the audio file; obtain the storage location of the audio file, and store the text file in the storage location.

[0024] According to one embodiment of the present application, the model determination module is also used to: determine whether the user has subscribed to the audio transcription service; in response to the user having subscribed to the audio transcription service, transcribe the audio file into text to obtain a transcribed text corresponding to the audio file; in response to the user not subscribing to the audio transcription service, display a fourth prompt box on the display screen, and the fourth prompt box is used to remind the user to subscribe to the audio transcription service.

[0025] According to one embodiment of the present application, the model determination module is also used to: determine whether the user has subscribed to the minutes generation service; in response to the user having subscribed to the minutes generation service, determine the first minutes generation model corresponding to the transcribed text according to the audio scene and the preset minutes template corresponding to the audio scene; in response to the user not subscribing to the minutes generation service, display a fifth prompt box on the display screen, and the fifth prompt box is used to remind the user to subscribe to the minutes generation service.

[0026] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method for generating minutes.

[0027] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above-mentioned method for generating minutes.

[0028] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, wherein the computer program implements the above-mentioned method for generating minutes when executed by a processor.

[0029] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0031] Figure 1 It is a schematic diagram of an exemplary implementation of a method for generating minutes according to an exemplary embodiment of the present disclosure.

[0032] Figure 2 is a schematic diagram of an audio selection interface according to an exemplary embodiment of the present disclosure.

[0033] Figure 3 It is a schematic diagram after a minutes text is loaded successfully according to an exemplary embodiment of the present disclosure.

[0034] Figure 4 It is a schematic diagram after a minutes text fails to load according to an exemplary embodiment of the present disclosure.

[0035] Figure 5 It is a schematic diagram after a transcribed text is loaded successfully according to an exemplary embodiment of the present disclosure.

[0036] Figure 6 It is a schematic diagram of an exemplary implementation of a method for generating minutes according to an exemplary embodiment of the present disclosure.

[0037] Figure 7 It is a schematic diagram of an exemplary implementation of a method for generating minutes according to an exemplary embodiment of the present disclosure.

[0038] Figure 8 It is a schematic diagram of a minutes template switching interface according to an exemplary embodiment of the present disclosure.

[0039] Fig. 9 It is a preview schematic diagram of a selected candidate minutes template according to an exemplary embodiment of the present disclosure.

[0040] Fig.10 It is a schematic diagram of a device for generating minutes according to an exemplary embodiment of the present disclosure.

[0041] Fig.11 is a schematic diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0043] Artificial Intelligence (AI) is a discipline that studies how computers can simulate certain thought processes and intelligent behaviors of human beings (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level technologies and software-level technologies. AI hardware technologies generally include computer vision technology, speech recognition technology, natural language processing technology, as well as learning / deep learning, big data processing technology, knowledge graph technology, and other aspects.

[0044] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0045] Figure 1 is a schematic diagram of an exemplary implementation of a method for generating minutes shown in the present application, such as Figure 1 As shown, the method for generating the minutes includes the following steps:

[0046] S101, obtaining an audio file uploaded by a user, and determining an audio scene corresponding to the audio file.

[0047] Optionally, the audio file may be a real-time recording file of the user.

[0048] Optionally, the audio file may be a file uploaded by the user, such as an interview file, a classroom file, a music file, etc.

[0049] For ease of understanding, Figure 2 is a schematic diagram of an audio selection interface shown in this application, such as Figure 2 As shown, the user can click on the interface to select real-time recording to generate an audio file, or click to select an audio file that has been selected.

[0050] Among them, different audio files can correspond to different audio scenes, such as interview scenes, telephone scenes, classroom scenes, meeting scenes, etc.

[0051] S102, in response to detecting a minutes generation instruction for an audio file, determining whether the audio file already has a corresponding transcription text.

[0052] If a minutes generation instruction issued by the user to an audio file is detected, the audio file is used as the audio file to be generated for minutes. In this application, it is considered that the user may have previously transcribed the audio file to be generated for minutes, that is, the transcribed text corresponding to the audio file to be generated for minutes already exists. In order to reduce computing resources, it is necessary to determine whether the audio file to be generated for minutes already has a corresponding transcribed text.

[0053] S103: In response to the audio file having a corresponding transcribed text, a first minutes generation model corresponding to the transcribed text is determined according to the audio scene and a preset minutes template corresponding to the audio scene.

[0054] Each audio scene may correspond to multiple minutes templates, and different minutes templates may include different modules. For convenience, a preset minutes template is generally set for each audio scene.

[0055] Among them, a classroom focus module can be added to the minutes template of the classroom scene to introduce the key points of knowledge corresponding to the classroom audio file.

[0056] Among them, a question review module can be added to the interview scenario and telephone scenario to display the corresponding key points of the audio file based on a question-and-answer method.

[0057] Optionally, different audio scenes combined with different minutes templates may correspond to different minutes generation models. For example, if an interview scene corresponds to 5 candidate minutes templates, then the interview scene combined with different minutes templates corresponds to 5 minutes generation models in total, and the minutes generation model may adopt a natural language processing model.

[0058] In the present application, a corresponding minutes generation model is determined from a minutes generation model library according to the audio scene and the preset minutes template corresponding to the audio scene as the first minutes generation model.

[0059] Among them, for any audio scene combined with any minutes template, a training sample set is collected in advance for training to obtain a minutes generation model, and stored in a minutes generation model library.

[0060] S104, inputting the transcribed text into the first minutes generation model, and obtaining the first minutes text output by the first minutes generation model according to the preset minutes template.

[0061] S105, displaying the first minutes text on the user's display screen.

[0062] Optionally, after the first minutes text is generated, it can be uniformly displayed on the user's display screen.

[0063] Optionally, during the generation process of the first minutes text, the first minutes text can be generated and loaded on the user's display screen at the same time.

[0064] For ease of understanding, Figure 3 This is a schematic diagram of a minutes text after it is successfully loaded. Figure 3As shown, the minutes text may include multiple modules, such as a basic meeting information module (meeting time and participants), a meeting theme module, a meeting to-do module (user interaction may be performed in the to-do selection box, and the selection box may be checked or unchecked to mark whether the to-do item has been completed), and various meeting topic modules.

[0065] In addition, there will generally be a situation where the minutes text fails to load. Figure 4 This is a schematic diagram of a failure to load a minutes text shown in this application, such as Figure 4 As shown, if the minutes text fails to load, a loading failure reminder will appear on the screen and the user can choose to reload it.

[0066] In addition, the user can freely choose whether to display the minutes content, the transcription text, or the intelligent summary content on the display screen (unlike the minutes content, the intelligent summary content is a summary of the key points of the audio file). Figure 5 is a schematic diagram of a transcribed text after it is successfully loaded, as shown in the present application. Figure 5 As shown, when the user chooses to display the transcribed text, the transcribed text will be displayed in the relevant area, and during the playback of the audio file, the segment being played will be highlighted.

[0067] The embodiment of the present application provides a method for generating minutes, including: obtaining an audio file uploaded by a user, and determining an audio scene corresponding to the audio file; in response to monitoring a minutes generation instruction for an audio file, determining whether the audio file already has a corresponding transcription text; in response to the audio file already having a corresponding transcription text, determining a first minutes generation model corresponding to the transcription text according to the audio scene and a preset minutes template corresponding to the audio scene; inputting the transcription text into the first minutes generation model, obtaining the first minutes text output by the first minutes generation model according to the preset minutes template; and displaying the first minutes text on the user's display screen. The present application can effectively realize automated audio transcription and minutes generation, greatly reduce the time required for users to manually organize audio records, improve work efficiency, reduce manual intervention and errors, and improve the accuracy of information extraction and presentation.

[0068] Optionally, different from the above implementation, different audio scenarios combined with different minutes templates can correspond to the same minutes generation model. When training the model, prompt tuning needs to be performed for different scenarios.

[0069] In the related technology, considering that the user's artificial intelligence generated content (AIGC) authorization is required, the related application can perform AI processing based on the user's instructions. Figure 6is a schematic diagram of an exemplary implementation of a method for generating minutes shown in the present application, such as Figure 6 As shown, the method for generating the minutes includes the following steps:

[0070] S601, obtaining an audio file uploaded by a user, and determining an audio scene corresponding to the audio file.

[0071] S602, in response to receiving an instruction to generate a minutes for an audio file, determining whether the user has AIGC authority to generate artificial intelligence content.

[0072] Among them, determining whether the user has AIGC authority can also be understood as determining whether the user has ever checked the agreement to allow related applications to perform AI-related behaviors.

[0073] S603: In response to the user having the AIGC authority, determine whether the audio file already has a corresponding transcription text.

[0074] S604: In response to the user not having the AIGC authority, a first prompt box is displayed on the display screen, where the first prompt box is used to remind the user to perform AIGC authorization.

[0075] S605: In response to the audio file having a corresponding transcribed text, a first minutes generation model corresponding to the transcribed text is determined according to the audio scene and a preset minutes template corresponding to the audio scene.

[0076] As a feasible method, if all users can perform the minutes generation service by default, then if the audio file already has a corresponding transcribed text, the first minutes generation model corresponding to the transcribed text is directly executed based on the audio scene and the preset minutes template corresponding to the audio scene.

[0077] As another feasible method, since in most scenarios, the relevant application only provides minutes generation service to some users (for example, minutes generation service is only provided to users who purchase membership rights or users who receive minutes generation service rights for free), in this case, if the audio file already has a corresponding transcription text, it is necessary to determine whether the user has subscribed to the minutes generation service; if the user has subscribed to the minutes generation service, the first minutes generation model corresponding to the transcription text is determined according to the audio scene and the preset minutes template corresponding to the audio scene; if the user has not subscribed to the minutes generation service, the fifth prompt box is displayed on the display screen, and the fifth prompt box is used to remind the user to subscribe to the minutes generation service. In this way, it can be ensured that only subscribed users can use this function. This targeted service provision helps to improve user satisfaction and reduce unnecessary waste of resources; and for unsubscribed users, by displaying a prompt box to remind them to subscribe to the service, it can effectively promote user subscriptions, thereby increasing the coverage and revenue of the service.

[0078] S606: Input the transcribed text into the first minutes generation model to obtain the first minutes text output by the first minutes generation model according to the preset minutes template.

[0079] S607, displaying the first minutes text on the user's display screen.

[0080] The embodiment of the present application confirms the user's AIGC authority to ensure that only authorized users can use the AI-generated content function, thereby protecting user privacy and data security; after confirming that the audio file has a transcribed text, minutes are automatically generated and displayed, reducing the user's manual operations and waiting time and improving work efficiency; by displaying a prompt box to remind the user to authorize AIGC, it ensures that the user is aware of and agrees to the relevant terms, thereby improving transparency and user experience.

[0081] Figure 7 is a schematic diagram of an exemplary implementation of a method for generating minutes shown in the present application, such as Figure 7 As shown, the method for generating the minutes includes the following steps:

[0082] S701, obtaining an audio file uploaded by a user, and determining an audio scene corresponding to the audio file.

[0083] S702, in response to receiving an instruction to generate a minutes for an audio file, determining whether the user has AIGC authority to generate artificial intelligence content.

[0084] S703: In response to the user having the AIGC authority, determine whether the audio file already has a corresponding transcription text.

[0085] S704: In response to the user not having the AIGC authority, a first prompt box is displayed on the display screen, where the first prompt box is used to remind the user to perform AIGC authorization.

[0086] S705: In response to the audio file having a corresponding transcribed text, a first minutes generation model corresponding to the transcribed text is determined according to the audio scene and a preset minutes template corresponding to the audio scene.

[0087] S706, inputting the transcribed text into the first minutes generation model, and obtaining the first minutes text output by the first minutes generation model according to the preset minutes template.

[0088] S707, displaying the first minutes text on the user's display screen.

[0089] Regarding the specific implementation of steps S701 to S707, reference may be made to the specific introduction of the relevant parts in the above embodiments, which will not be elaborated here.

[0090] S708: In response to the audio file not having a corresponding transcription text, displaying a second prompt box on the display screen, the second prompt box being used to remind the user to transcribe the audio file into a corresponding transcription text.

[0091] S709, in response to detecting a click operation of the user on the second prompt box, transcribing the audio file to obtain a transcribed text corresponding to the audio file.

[0092] As a feasible method, if all users can perform the audio transcription service by default, then if a user click operation on the second prompt box is detected, the audio file is directly transcribed to obtain the transcribed text corresponding to the audio file.

[0093] As another feasible method, since in most scenarios, the relevant application only provides audio transcription services to some users (for example, only provides audio transcription services to users who purchase membership rights or users who receive audio transcription service rights for free), in this case, if the user's click operation on the second prompt box is monitored, it is necessary to determine whether the user has subscribed to the audio transcription service; if the user has subscribed to the audio transcription service, the audio file is transcribed into text to obtain the transcribed text corresponding to the audio file; if the user has not subscribed to the audio transcription service, a fourth prompt box is displayed on the display screen, and the fourth prompt box is used to remind the user to subscribe to the audio transcription service. In this way, by checking the user's subscription status, it is ensured that only users who have subscribed to the audio transcription service can perform text transcription, which avoids waste of resources and ensures the compliance use of the service; for users who have not subscribed to the audio transcription service, by displaying the fourth prompt box to remind them to subscribe to the service, it is helpful to guide users to understand and subscribe to related services, thereby improving the user coverage and potential revenue of the service.

[0094] S710, displaying the transcribed text on the display screen, and displaying a third prompt box on the display screen, the third prompt box being used to remind the user to generate a corresponding minutes text based on the transcribed text.

[0095] S711, in response to monitoring a click operation of the user on the third prompt box, executing a first minutes generation model and subsequent steps corresponding to the transcription text according to the audio scene and a preset minutes template corresponding to the audio scene.

[0096] If a user click operation on the third prompt box is monitored, the first minutes generation model corresponding to the transcribed text is determined according to the audio scene and the preset minutes template corresponding to the audio scene, the transcribed text is input into the first minutes generation model, the first minutes text output by the first minutes generation model according to the preset minutes template is obtained, and the first minutes text is displayed on the user's display screen.

[0097] The embodiment of the present application confirms the user's AIGC authority to ensure that only authorized users can use the AI-generated content function, thereby protecting user privacy and data security; after confirming that the audio file has transcribed text, minutes are directly generated and displayed based on the transcribed text; and after confirming that the audio file does not have transcribed text, a corresponding prompt box is provided to guide the user to make a choice to generate and display minutes; by displaying a prompt box to remind the user to authorize AIGC, it is ensured that the user is aware of and agrees to the relevant terms, thereby improving transparency and user experience.

[0098] Furthermore, after displaying the first minutes text on the user's display screen, it also includes: if the user's click operation on the text content contained in the first minutes text is monitored, the text position corresponding to the text content in the transcribed text is obtained, and the corresponding text position in the transcribed text is highlighted, or in other words, a dynamic effect can also be added, such as flashing the corresponding text position in the transcribed text twice, and locating the audio file to the audio position corresponding to the text position and playing the audio file from the audio position. In this way, a more intuitive and interactive experience is provided, allowing users to more conveniently view and understand the transcribed content; through highlighting or dynamic effects, users can quickly identify and focus on key content, improving the efficiency of information retrieval; locating the audio file to the corresponding text position and playing it allows users to directly hear the relevant part, enhancing the coherence and understanding of the information.

[0099] Furthermore, after displaying the first minutes text on the user's display screen, it also includes: if the user clicks on the minutes template switching box on the display screen, multiple candidate minutes templates are displayed on the display screen; in response to the user's selection and confirmation operation on any candidate minutes template, the candidate minutes template is used as the target minutes template; according to the audio scene and the target minutes template, the corresponding second minutes generation model is called to regenerate the transcript text to obtain the generated second minutes text; based on the second minutes text, the first minutes text is replaced and displayed on the display screen. In this way, users are allowed to select different minutes templates, providing services customized according to personal needs or preferences, and improving user satisfaction and usage experience.

[0100] For ease of understanding, Figure 8 This is a schematic diagram of the minutes template switching interface, such as Figure 8 As shown, after the user clicks the minutes template switching box, multiple candidate minutes templates corresponding to the audio scene are displayed on the display screen, and the user can select to switch the template.

[0101] For ease of understanding, Fig. 9 It is a preview diagram of the selected candidate minutes template, such as Fig. 9As shown, the user can click the candidate minutes template selected again to enter the preview interface. Multiple pages of candidate minutes templates support sliding viewing.

[0102] Among them, if the template switch fails, the user is supported to switch the minutes template and try again.

[0103] Further, for the transcribed text, if the user's editing operation on the transcribed text is monitored, such as inserting, deleting, replacing, etc., the transcribed text is updated based on the editing operation. Optionally, the edit button is grayed out and cannot be edited before the transcribed text is generated, and can be edited after it is generated.

[0104] Further, for the first minutes text, if the user's editing operation on the first minutes text is monitored, such as inserting, deleting, replacing, etc., the first minutes text is updated based on the editing operation. Optionally, the edit button is grayed out and cannot be edited before the first minutes text is generated, and can be edited after it is generated.

[0105] Further, for the second minutes text, if the user's editing operation on the second minutes text is monitored, such as inserting, deleting, replacing, etc., the second minutes text is updated based on the editing operation. Optionally, the edit button is grayed out and cannot be edited before the second minutes text is generated, and can be edited after it is generated.

[0106] This design ensures the accuracy and completeness of the text before it is generated, and avoids errors introduced by editing during the generation process. At the same time, the post-generation editing function allows users to make corrections as needed, thereby improving the quality and accuracy of the final text.

[0107] Furthermore, for the transcribed text, if the user's export operation on the transcribed text is monitored, a text file is generated based on the transcribed text, wherein the name of the text file is the same as that of the audio file; the storage location of the audio file is obtained, and the text file is stored in the storage location.

[0108] Furthermore, for the first minutes text, if the user's export operation on the first minutes text is monitored, a text file is generated based on the first minutes text, wherein the name of the text file is the same as that of the audio file; the storage location of the audio file is obtained, and the text file is stored in the storage location.

[0109] Furthermore, for the second minutes text, if the user's export operation on the second minutes text is monitored, a text file is generated based on the second minutes text, wherein the name of the text file is the same as that of the audio file; the storage location of the audio file is obtained, and the text file is stored in the storage location.

[0110] The format of the exported text file can be word format, pdf format, etc., and users can choose freely.

[0111] For any of the transcripts, first minutes text, and second minutes text, this design ensures that the text file has the same name as the audio file, allowing users to more easily associate and manage these files. This consistency makes file organization clearer and reduces confusion for users when looking for related files.

[0112] Furthermore, during the generation process of any of the above-mentioned transcription text, the first minutes text and the second minutes text, a sweeping light effect can be added to the corresponding position of the screen to indicate that the text is being generated.

[0113] Furthermore, during the generation process of any of the above-mentioned transcription text, first minutes text and second minutes text, if the generation fails, the user is supported to retry the generation, and push notification (PushNotification, PUSH) notification and / or instant messaging notification (Instant Messaging Notification, IM) notification of the failure message is supported.

[0114] Fig.10 is a schematic diagram of a device for generating minutes shown in the present application, such as Fig.10 As shown, the minutes generation device 1000 includes an audio acquisition module 1001, a transcription judgment module 1002, a model determination module 1003, a minutes generation module 1004 and a minutes display module 1005, wherein:

[0115] The audio acquisition module 1001 is used to acquire the audio file uploaded by the user and determine the audio scene corresponding to the audio file.

[0116] The transcription determination module 1002 is used to determine whether the audio file has a corresponding transcription text in response to detecting a minutes generation instruction for the audio file.

[0117] The model determination module 1003 is used to determine, in response to the audio file having a corresponding transcribed text, a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene.

[0118] The minutes generation module 1004 is used to input the transcribed text into the first minutes generation model, and obtain the first minutes text output by the first minutes generation model according to the preset minutes template.

[0119] The minutes display module 1005 is used to display the first minutes text on the user's display screen.

[0120] This device can effectively realize automatic audio transcription and minutes generation, greatly reducing the time required for users to manually organize audio records, improving work efficiency, reducing human intervention and errors, and improving the accuracy of information extraction and presentation.

[0121] Furthermore, the transcription judgment module 1002 is also used to: in response to receiving an instruction to generate a minutes for an audio file, determine whether the user has the artificial intelligence generated content AIGC authority; in response to the user having the AIGC authority, determine whether the audio file already has a corresponding transcription text.

[0122] Furthermore, the transcription judgment module 1002 is also used to: in response to the user not having the AIGC authority, display a first prompt box on the display screen, where the first prompt box is used to remind the user to perform AIGC authorization.

[0123] Furthermore, the model determination module 1003 is also used to: in response to the audio file having no corresponding transcribed text, display a second prompt box on the display screen, the second prompt box being used to remind the user to transcribe the audio file into the corresponding transcribed text; in response to detecting a user's click operation on the second prompt box, transcribe the audio file into text to obtain the transcribed text corresponding to the audio file; display the transcribed text on the display screen, and display a third prompt box on the display screen, the third prompt box being used to remind the user to generate a corresponding minutes text based on the transcribed text; in response to detecting a user's click operation on the third prompt box, determine a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene.

[0124] Furthermore, the minutes generating device 1000 also includes: a text positioning module, which is used to respond to monitoring the user's click operation on the text content contained in the first minutes text, and obtain the text position corresponding to the text content in the transcribed text; an audio positioning module, which is used to highlight the corresponding text position in the transcribed text, and to position the audio file to the audio position corresponding to the text position and start playing the audio file from the audio position.

[0125] Furthermore, the minutes generation device 1000 also includes a minutes template switching module, which is used to: in response to monitoring the user's click operation on the minutes template switching box on the display screen, display multiple candidate minutes templates on the display screen; in response to monitoring the user's selection and confirmation operation on any candidate minutes template, use the candidate minutes template as the target minutes template; call the corresponding second minutes generation model according to the audio scene and the target minutes template to re-generate minutes for the transcribed text and obtain the generated second minutes text; replace the first minutes text based on the second minutes text and display it on the display screen.

[0126] Furthermore, the minutes generating device 1000 also includes a text editing module, which is used to: for any text among the transcription text, the first minutes text and the second minutes text, in response to monitoring the user's editing operation on any text, update any text based on the editing operation.

[0127] Furthermore, the minutes generating device 1000 also includes a text export module, which is used to: for any text among the transcribed text, the first minutes text and the second minutes text, in response to monitoring the user's export operation on any text, generate a text file based on any text, wherein the name of the text file is the same as that of the audio file; obtain the storage location of the audio file, and store the text file in the storage location.

[0128] Furthermore, the model determination module 1003 is also used to: determine whether the user has subscribed to the audio transcription service; in response to the user having subscribed to the audio transcription service, transcribe the audio file into text to obtain a transcribed text corresponding to the audio file; in response to the user not subscribing to the audio transcription service, display a fourth prompt box on the display screen, and the fourth prompt box is used to remind the user to subscribe to the audio transcription service.

[0129] Furthermore, the model determination module 1003 is also used to: determine whether the user has subscribed to the minutes generation service; in response to the user having subscribed to the minutes generation service, determine the first minutes generation model corresponding to the transcribed text according to the audio scene and the preset minutes template corresponding to the audio scene; in response to the user not subscribing to the minutes generation service, display a fifth prompt box on the display screen, and the fifth prompt box is used to remind the user to subscribe to the minutes generation service.

[0130] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0131] Fig.11 A schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0132] like Fig.11As shown, the device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0133] A number of components in the device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0134] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1101 performs the various methods and processes described above, such as the method for generating minutes. For example, in some embodiments, the method for generating minutes may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the method for generating minutes described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to execute the method for generating a summary in any other appropriate manner (eg, by means of firmware).

[0135] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0136] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0137] 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.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0139] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by 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), and the Internet.

[0140] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0141] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0142] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for generating minutes, characterized in that: include: Obtaining an audio file uploaded by a user, and determining an audio scene corresponding to the audio file; In response to detecting a minutes generation instruction for the audio file, determining whether the audio file already has a corresponding transcription text; In response to the audio file having a corresponding transcribed text, determining a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene; Inputting the transcribed text into the first minutes generation model to obtain the first minutes text output by the first minutes generation model according to the preset minutes template; The first minutes text is displayed on the display screen of the user.

2. The method according to claim 1, characterized in that In response to monitoring the instruction to generate a minutes for the audio file, determining whether the audio file has a corresponding transcription text includes: In response to receiving an instruction to generate a minutes of the audio file, determining whether the user has AIGC authority; In response to the user having the AIGC authority, it is determined whether the audio file already has a corresponding transcription text.

3. The method according to claim 2, characterized in that The method further comprises: In response to the user not having AIGC authority, a first prompt box is displayed on the display screen, where the first prompt box is used to remind the user to perform AIGC authorization.

4. The method according to claim 1 or 3, characterized in that: The method further comprises: In response to the audio file not having a corresponding transcription text, displaying a second prompt box on the display screen, the second prompt box being used to remind the user to transcribe the audio file into a corresponding transcription text; In response to detecting a click operation of the user on the second prompt box, transcribing the audio file to obtain a transcribed text corresponding to the audio file; Displaying the transcribed text on the display screen, and displaying a third prompt box on the display screen, wherein the third prompt box is used to remind the user to generate a corresponding minutes text based on the transcribed text; In response to monitoring a click operation of the user on the third prompt box, a first minutes generation model corresponding to the transcription text and subsequent steps are determined according to the audio scene and a preset minutes template corresponding to the audio scene.

5. The method according to claim 4, characterized in that After displaying the first minutes text on the user's display screen, the method further includes: In response to monitoring a click operation of the user on the text content contained in the first minutes text, obtaining a text position corresponding to the text content in the transcription text, The corresponding text position in the transcribed text is highlighted, and the audio file is positioned to the audio position corresponding to the text position and the audio file is played from the audio position.

6. The method according to claim 5, characterized in that After displaying the first minutes text on the user's display screen, the method further includes: In response to monitoring a click operation of the user on a minutes template switching box on the display screen, displaying a plurality of candidate minutes templates on the display screen; In response to monitoring the user's selection and confirmation operation on any of the candidate minutes templates, the candidate minutes template is used as a target minutes template; According to the audio scene and the target minutes template, a corresponding second minutes generation model is retrieved to regenerate the minutes for the transcribed text to obtain a generated second minutes text; The first minute text is replaced based on the second minute text and displayed on the display screen.

7. The method according to claim 6, characterized in that The method further comprises: With respect to any one of the transcription text, the first minutes text and the second minutes text, in response to monitoring an editing operation of the user on the any one of the texts, the any one of the texts is updated based on the editing operation.

8. The method according to claim 7, characterized in that The method further comprises: For any one of the transcription text, the first minutes text, and the second minutes text, in response to monitoring the user's export operation on any one of the texts, generating a text file based on the any one of the texts, wherein the text file has the same name as the audio file; The storage location of the audio file is obtained, and the text file is stored in the storage location.

9. The method according to claim 4, wherein: The step of transcribing the audio file to obtain a transcribed text corresponding to the audio file includes: Determining whether the user has subscribed to an audio transcription service; In response to the user having subscribed to the audio transcription service, transcribing the audio file into text to obtain a transcribed text corresponding to the audio file; In response to the user not having subscribed to the audio transcription service, a fourth prompt box is displayed on the display screen, wherein the fourth prompt box is used to remind the user to subscribe to the audio transcription service.

10. The method according to claim 4, wherein: The step of determining a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene includes: Determining whether the user has subscribed to the minutes generation service; In response to the user having subscribed to the minutes generation service, determining a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene; In response to the user not subscribing to the minutes generating service, a fifth prompt box is displayed on the display screen, wherein the fifth prompt box is used to remind the user to subscribe to the minutes generating service.

11. A device for generating minutes, characterized in that: include: An audio acquisition module, used to acquire an audio file uploaded by a user, and to determine an audio scene corresponding to the audio file; A transcription determination module, configured to determine whether the audio file has a corresponding transcription text in response to detecting a minutes generation instruction for the audio file; A model determination module, configured to determine, in response to the audio file having a corresponding transcribed text, a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene; A minutes generation module, used for inputting the transcribed text into the first minutes generation model, and obtaining the first minutes text output by the first minutes generation model according to the preset minutes template; The minutes display module is used to display the first minutes text on the display screen of the user.

12. The device according to claim 11, characterized in that The transcription judgment module is also used for: In response to receiving an instruction to generate a minutes of the audio file, determining whether the user has AIGC authority; In response to the user having the AIGC authority, it is determined whether the audio file already has a corresponding transcription text.

13. The device according to claim 12, characterized in that The transcription judgment module is also used for: In response to the user not having AIGC authority, a first prompt box is displayed on the display screen, where the first prompt box is used to remind the user to perform AIGC authorization.

14. The device according to claim 11 or 13, characterized in that The model determination module is also used for: In response to the audio file not having a corresponding transcription text, displaying a second prompt box on the display screen, the second prompt box being used to remind the user to transcribe the audio file into a corresponding transcription text; In response to detecting a click operation of the user on the second prompt box, transcribing the audio file to obtain a transcribed text corresponding to the audio file; Displaying the transcribed text on the display screen, and displaying a third prompt box on the display screen, wherein the third prompt box is used to remind the user to generate a corresponding minutes text based on the transcribed text; In response to detecting a click operation of the user on the third prompt box, a first minutes generation model corresponding to the transcribed text is determined according to the audio scene and a preset minutes template corresponding to the audio scene.

15. The device according to claim 14, characterized in that The device further comprises: a text positioning module, configured to obtain a text position corresponding to the text content in the transcribed text in response to monitoring a click operation of the user on the text content contained in the first minutes text, The audio positioning module is used to highlight the corresponding text position in the transcribed text, and to position the audio file to the audio position corresponding to the text position and start playing the audio file from the audio position.

16. The device according to claim 15, characterized in that The device further includes a minutes template switching module, and the minutes template switching module is used to: In response to monitoring a click operation of the user on a minutes template switching box on the display screen, displaying a plurality of candidate minutes templates on the display screen; In response to monitoring the user's selection and confirmation operation on any of the candidate minutes templates, the candidate minutes template is used as a target minutes template; According to the audio scene and the target minutes template, a corresponding second minutes generation model is retrieved to regenerate the minutes for the transcribed text to obtain a generated second minutes text; The first minute text is replaced based on the second minute text and displayed on the display screen.

17. The device according to claim 16, characterized in that The device also includes a text editing module, which is used to: With respect to any one of the transcription text, the first minutes text and the second minutes text, in response to monitoring an editing operation of the user on the any one of the texts, the any one of the texts is updated based on the editing operation.

18. The device according to claim 16, characterized in that The device further comprises a text export module, wherein the text export module is used for: For any one of the transcription text, the first minutes text, and the second minutes text, in response to monitoring the user's export operation on any one of the texts, generating a text file based on the any one of the texts, wherein the text file has the same name as the audio file; The storage location of the audio file is obtained, and the text file is stored in the storage location.

19. The device according to claim 14, characterized in that The model determination module is also used for: Determining whether the user has subscribed to an audio transcription service; In response to the user having subscribed to the audio transcription service, transcribing the audio file into text to obtain a transcribed text corresponding to the audio file; In response to the user not having subscribed to the audio transcription service, a fourth prompt box is displayed on the display screen, wherein the fourth prompt box is used to remind the user to subscribe to the audio transcription service.

20. The device according to claim 14, characterized in that The model determination module is also used for: Determining whether the user has subscribed to the minutes generation service; In response to the user having subscribed to the minutes generation service, determining a first minutes generation model corresponding to the transcribed text according to the audio scene and a preset minutes template corresponding to the audio scene; In response to the user not subscribing to the minutes generating service, a fifth prompt box is displayed on the display screen, wherein the fifth prompt box is used to remind the user to subscribe to the minutes generating service.

21. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 10.

Images