Information display method and device

Abstract

The invention discloses an information display method and device. Belongs to the technical field of communication. The method comprises the steps that to-be-processed voice is input into a first model, a first text which is output by the first model and corresponds to the to-be-processed voice is obtained, and the first text comprises a plurality of paragraphs; determining at least one piece of key information in the first text and a paragraph associated with the at least one piece of key information in the first text through a second model; displaying at least one piece of key information on a display interface of the first text; and displaying a paragraph associated with the target key information in the first text under the condition that a first input of the user to the target key information in the at least one piece of key information is received.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and specifically to an information display method and device thereof. Background Art

[0002] Currently, when users use terminal devices to record meetings or important speeches, recording is a common method. However, when users need to review the content of the meeting or speech, they often need to play back the recording, which is inefficient, especially for long recordings.

[0003] In the prior art, recordings can be converted into text, and users can understand the information in the recordings by reading the text content. However, for longer recordings, the amount of information in the generated text is huge, and it is difficult for users to quickly and accurately extract the required information from the text. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an information display method and device thereof, which can improve the efficiency of obtaining information from audio and the accuracy of the obtained information.

[0005] In a first aspect, an embodiment of the present application provides an information display method, which includes: inputting a speech to be processed into a first model to obtain a first text corresponding to the speech to be processed output by the first model, wherein the first text includes multiple paragraphs; determining at least one key information in the first text and a paragraph in the first text associated with the at least one key information through a second model; displaying the at least one key information on a display interface of the first text; and upon receiving a first input from a user for target key information in the at least one key information, displaying the paragraph in the first text associated with the target key information.

[0006] In a second aspect, an embodiment of the present application provides an information display device, which includes: a speech recognition unit, used to input the speech to be processed into a first model, and obtain a first text corresponding to the speech to be processed output by the first model, wherein the first text includes multiple paragraphs; a processing unit, used to determine at least one key information in the first text and a paragraph in the first text associated with the at least one key information through a second model; a first display unit, used to display the at least one key information on a display interface of the first text; and a second display unit, used to display the paragraph in the first text associated with the target key information when receiving a first input from a user for the target key information in the at least one key information.

[0007] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the first aspect are implemented.

[0008] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in the first aspect above are implemented.

[0009] In a fifth aspect, an embodiment of the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect.

[0010] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the method described in the first aspect.

[0011] In an embodiment of the present application, the speech to be processed is first input into the first model to obtain the first text corresponding to the speech to be processed output by the first model, and the first text includes multiple paragraphs; then, at least one key information in the first text and the paragraphs associated with the at least one key information in the first text are determined by the second model; then, the at least one key information is displayed on the display interface of the first text; when the user receives the first input of the target key information in the at least one key information, the paragraphs associated with the target key information in the first text are displayed. On the one hand, at least one key information in the first text is extracted by the second model, and the paragraphs associated with each key information are identified, which saves the user from manually replaying the speech to understand the speech content, and saves the user from manually refining the key information in the speech by browsing the text. In the case of a long speech to be processed, the efficiency of obtaining information from the audio and the accuracy of the information obtained can be greatly improved. On the other hand, when the user receives the first input of the target key information, the paragraphs associated with the target key information in the first text are displayed, which can facilitate the user to quickly locate the paragraph corresponding to the target key information in the first text, further improving the efficiency of obtaining information from the audio. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a flow chart of an information display method provided by an embodiment of the present application;

[0013] Figure 2 is a schematic diagram of an application scenario of the information display method provided in an embodiment of the present application;

[0014] Figure 3 is a schematic diagram of an application scenario of the information display method provided in an embodiment of the present application;

[0015] Figure 4 is a schematic diagram of an application scenario of the information display method provided in an embodiment of the present application;

[0016] Figure 5 is a schematic diagram of an application scenario of the information display method provided in an embodiment of the present application;

[0017] Figure 6 is a schematic diagram of the structure of an information display device provided in an embodiment of the present application;

[0018] Figure 7 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0019] Figure 8 It is a schematic diagram of the hardware structure of an electronic device suitable for implementing the embodiments of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0021] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0022] The information display method and device provided by the embodiments of the present application are described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0023] Please refer to Figure 1 , which shows one of the flow charts of the information display method provided in the embodiment of the present application. The information display method provided in the embodiment of the present application can be applied to electronic devices. In practice, the above-mentioned electronic devices can be electronic devices such as smart phones, tablet computers, laptops, and wearable devices.

[0024] The process of the information display method provided in the embodiment of the present application includes the following steps:

[0025] Step 101: input the speech to be processed into the first model, and obtain the first text corresponding to the speech to be processed output by the first model, wherein the first text includes a plurality of paragraphs.

[0026] In this embodiment, the speech to be processed may include, but is not limited to, various types of speech such as conference recordings, speech recordings, real-time call voices, online course voices, and legal hearing recordings. The first model may be used to perform speech recognition and convert the speech into text. For example, the first model may include, but is not limited to, an automatic speech recognition model (Automatic Speech Recognition, ASR). The automatic speech recognition model is a model for converting speech into text. The automatic speech recognition model can convert speech to text and can automatically divide the text into paragraphs based on the text content.

[0027] In this embodiment, the speech to be processed can be input into the first model to obtain a text corresponding to the speech to be processed output by the first model, and the text can be recorded as the first text. The first text can include multiple paragraphs. In practical applications, a paragraph identifier can be added to each paragraph. The paragraph identifier is a unique identifier of the paragraph, which is used to identify and distinguish different paragraphs.

[0028] In some scenarios, the speech to be processed can be acquired in advance. As an example, in a meeting scenario, at the beginning of the meeting, the recording device in the electronic device can be started to start recording. After the meeting, the recording device is stopped to end the recording. After the recording is finished, the recording file is stored to obtain the speech to be processed. At this time, when it is necessary to review the content of the meeting, the speech to be processed can be input into the first model to obtain the first text corresponding to the speech to be processed.

[0029] In some scenarios, the speech to be processed can be obtained in real time. For example, in a meeting scenario, a recording device in an electronic device can be started at the beginning of the meeting to start recording. During the recording process, the audio collected by the recording device can be input into the first model in real time to obtain the first text converted by the first model in real time.

[0030] Step 102: Determine, by using a second model, at least one key information in the first text and a paragraph in the first text associated with the at least one key information.

[0031] In this embodiment, the second model may be a language model capable of natural language processing. For example, the second model may include, but is not limited to, a large language model (LLM). A large language model refers to a neural network model for natural language processing that contains ultra-large-scale parameters. The large language model has a huge scale, multi-task learning capabilities, powerful computing resources, and abundant training data. Large language models are widely used in the field of natural language processing and have the ability to perform well in various natural language processing tasks, such as text classification, sentiment analysis, summary generation, translation, etc. Large language models can be used in multiple application fields such as automatic writing, chatbots, virtual assistants, voice assistants, and automatic translation.

[0032] In this embodiment, the first text and the preset output requirements can be input into the second model, the first text and the output requirements are semantically understood by the large speech model, and the content that meets the above output requirements is output. The above output requirements can be used to instruct the second model to output at least one key information in the first text and output the paragraph identification of the paragraph associated with each key information in the first text. Based on the content output by the second model, a corresponding relationship can be established between each key information and the paragraph identification of the paragraph associated with it, so as to determine at least one key information in the first text and the paragraph associated with each key information in the first text. After determining at least one key information in the first text and the paragraph associated with each key information in the first text, each key information output by the second model can be displayed.

[0033] Among them, the key information can be the more important information in the text content of the first text. For example, if the speech to be processed is a meeting with the theme of "Summer Safety and Homework Requirements", the key information of the corresponding first text may include but is not limited to information about summer safety, information about summer homework arrangements, etc. The output requirements for the second model can be set as needed. For example, it can be set to "Please extract at least one key information in the following text, and output the paragraph identifier of the paragraph associated with each key information in the following text."

[0034] By using the second model to extract at least one key information in the first text and identify the paragraphs associated with each key information, the user is saved from manually playing back the voice to understand the voice content, and the user is saved from manually extracting key information from the voice by browsing the text. When the voice to be processed is long, the efficiency and accuracy of obtaining information from the audio can be greatly improved.

[0035] Step 103: display the at least one key information on the first text display interface.

[0036] In this embodiment, the at least one key information may be displayed in any form in the display interface of the first text, for example, in a floating window or in a specific area, etc., which is not specifically limited here.

[0037] In some optional implementations of this embodiment, the above-mentioned key information can be displayed in the following manner: display a first page, the first page includes at least a first area and a second area, the first area includes the above-mentioned at least one key information, and the second area includes the text content of the above-mentioned first text.

[0038] As an example, see Figure 2 , the first area is shown as label 201, and the second area is shown as label 202. In the first area, three key information may be included, namely "Point 1: The meeting emphasized safety issues during the summer vacation, including drowning prevention, traffic safety, home safety, food safety and mental health.", "Point 2: The meeting introduced the content of summer homework, including subject literacy, reading, calligraphy practice, labor practice, etc., and also emphasized the importance of reading and literacy skills.", "Point 3: The meeting mentioned the school's list of practical activities, including visiting museums, looking for bridges, watching documentaries, etc., and also emphasized the importance of morning reading and reading methods.". In the second area, the text content in the first text may be included. When the text content of the first text cannot be fully displayed in the second area, that is, when the second area includes part of the text content of the first text, the user can browse the text content of other parts of the first text through sliding gestures.

[0039] By displaying the key information in the first text and the original text content of the first text in different regions, the user can browse the original content of the first text without switching pages when browsing the key information in the first text, so as to further understand more content in the first text, thereby improving the efficiency of information acquisition. Through the intelligent user interaction interface, the user can easily jump between the key information and the related paragraphs, realizing the efficient browsing and processing of the text corresponding to the long voice content.

[0040] It should be noted that the first page may also include content such as recording identification. In addition to the above-mentioned first text and the above-mentioned output requirements, the content input to the second model may further increase output requirements. For example, a requirement may be added to instruct the large model to output the subject, summary, and other content of the first text. Figure 2In the first area of ​​the first page, in addition to the key information output by the large model, it can also include the theme "Theme: Summer safety and homework requirements explanation", summary "Summary: The main content of the meeting includes summer safety and summer homework release, as well as requirements and introductions for reading, calligraphy, mathematics, English and practical homework. The meeting emphasized the importance of safety and reading, and encouraged children to read more and accumulate more." This can further facilitate users to intuitively and conveniently understand the content of the speech to be processed.

[0041] Step 104 : upon receiving a first input of a user for target key information among the at least one key information, displaying a paragraph in the first text associated with the target key information.

[0042] In this embodiment, the first input can be used to select the target key information in the at least one key information mentioned above. The target key information can be any key information in the at least one key information mentioned above. In practice, the input in the embodiment of the present application can be a touch input, or a voice command, or a specific gesture input by the user, or other feasible input, which can be determined according to actual use requirements, and the embodiment of the present application is not limited. The specific gesture in the embodiment of the present application can be any one of a single-click gesture, a sliding gesture, a drag gesture, a pressure recognition gesture, a long press gesture, an area change gesture, a double-press gesture, and a double-click gesture. The click input in the embodiment of the present application can be a single-click input, a double-click input, or any number of click inputs, etc., and can also be a long press input or a short press input.

[0043] In this embodiment, in response to the first input, the paragraph associated with the target key information in the first text can be determined based on the correspondence between the target key information and the paragraph identifier of the paragraph associated with it, so as to display the paragraph. The display method of the paragraph is not limited, for example, the paragraph of the paragraph can be displayed in various ways such as a page, a floating window, etc.

[0044] By displaying the paragraphs associated with the target key information in the first text upon receiving the user's first input of the target key information, the user can quickly locate the original content and context information corresponding to the key information, thereby further improving the efficiency of information acquisition.

[0045] In some optional implementations of this embodiment, when a user first inputs a target key information in at least one key information, the following steps may be performed to display a paragraph in the first text associated with the target key information:

[0046] The first step is to switch the first page to the second page, where the second page includes the text content of the first text.

[0047] In the second step, the displayed text content of the first text is switched to a paragraph associated with the target key information.

[0048] Here, the text content of the displayed first text can be switched to the paragraph associated with the target key information by controlling the scrolling of the second page. The text content of the displayed first text can also be switched to the paragraph associated with the target key information by directly jumping. In practice, the area that the user can see in the second page is the window, also known as the viewport. In practice, the paragraph can be located based on the paragraph identification of the paragraph associated with the target key information, and the position of the paragraph in the second page can be determined, so as to control the scrolling or jumping of the second page to accurately display the paragraph in the window.

[0049] As an example, see Figure 3 , the first page is shown as label 301. In the first page, three key information can be displayed, namely "Point 1: The meeting emphasized safety issues during the summer vacation, including drowning prevention, traffic safety, home safety, food safety and mental health.", "Point 2: The meeting introduced the content of summer homework, including subject literacy, reading, calligraphy practice, labor practice, etc., and also emphasized the importance of reading and literacy skills.", "Point 3: The meeting mentioned the school's practical activity list, including visiting museums, looking for bridges, watching documentaries, etc., and also emphasized the importance of morning reading and reading methods.".

[0050] After the user clicks "Point 3", "Point 3: The meeting mentioned the school's list of practical activities, including visiting museums, looking for bridges, watching documentaries, etc., and also emphasized the importance of morning reading and reading methods." can be used as the target key information to jump to the second page as shown by label 302. Afterwards, the second page can be controlled to scroll or jump to display the paragraph associated with the target key information in the first text (see label 303) in the window. The above paragraphs associated with the target key information can be displayed separately from other content. For example, it can be displayed in bold, highlighted, displayed in different colors, etc., and its display style is not specifically limited here.

[0051] By switching to a second page including text content of a first text upon receiving a first input of target key information from a user, and switching the displayed text content of the first text to a paragraph associated with the target key information, the user can not only browse the content of the paragraph but also obtain contextual information of the paragraph, thereby improving the richness and convenience of information acquisition.

[0052] In some optional implementations of the present embodiment, in the above-mentioned second step, when the target key information is associated with at least two paragraphs, the display order of the at least two paragraphs can be determined based on the position of each paragraph in the first text of the at least two paragraphs. Then, based on the display order, the first paragraph is selected from the at least two paragraphs. After that, the text content of the displayed first text is switched to the determined first paragraph. When the user's second input to the second page is received, the next paragraph can be selected from the at least two paragraphs based on the display order. Then, the text content of the displayed first text can be switched to the next paragraph. Here, among the at least two paragraphs, the paragraph that is closer to the front in the first text has a closer display order. The second input can be used to trigger the scrolling of the second page and the display of another paragraph of the at least two paragraphs.

[0053] As an example, see Figure 4 . The second page is shown as label 401. The second page includes a control 402. There are 3 paragraphs associated with the target key information, and the first paragraph is currently displayed in the window. The above control 402 may include the display order of the paragraphs associated with the target key information currently displayed in the window, for example, "1" in "1 / 3 next original text". The above control 402 may also include the total number of paragraphs associated with the target key information, for example, "3" in "1 / 3". When the user clicks the control 402, the second page can be controlled to scroll or jump to the next paragraph associated with the target key information, so that the next paragraph associated with the target key information is displayed in the window, and the second page parameter at this time is shown as label 402. The control at this time includes "2 / 3 next original text".

[0054] When the target key information is associated with at least two paragraphs, by first switching the text content of the displayed first text to the first paragraph, and then switching the text content of the displayed first text to the next paragraph when receiving the second input from the user on the second page, the paragraphs associated with the target key information can be switched and displayed conveniently and quickly without the user having to manually slide the page, thereby further improving the convenience of information acquisition.

[0055] In some optional implementations of this embodiment, based on the above implementations, the following steps may be further performed: based on the display order, determining the last paragraph of at least two paragraphs; when the text content of the displayed first text includes the last paragraph, receiving a third input from the user on the second page; and in response to the third input, switching the second page to the first page. The third input may be used to trigger the switching of pages.

[0056] As an example, see Figure 5. The second page is shown as label 501. The second page includes a control 502. There are 3 paragraphs associated with the target key information, and the paragraph associated with the target key information currently displayed in the window is the third one. The above control 502 can include the display order of the paragraphs associated with the target key information currently displayed in the window, and the total number of paragraphs associated with the target key information, for example, "3 / 3 return to original position". When the user clicks the control 502, the second page can be switched to the first page as shown by label 503.

[0057] Therefore, after the user browses each paragraph associated with the target key information, he or she can quickly and easily jump to the first page displaying the above key information without the user having to manually close the second page and open the first page, thereby improving the convenience of information acquisition.

[0058] In some optional implementations of this embodiment, when the above-mentioned first page is displayed, a fourth input from the user to the second area can also be received. The fourth input can be used to edit the first text. In response to the fourth input, the text content of the first text can be updated to obtain the second text. Furthermore, the text content of the displayed first text can be switched to the text content of the second text. Thus, the user can edit or delete the paragraphs in the first text returned by the first model, which means that the user can correct errors in the first text, add supplementary information to the first text, or delete unnecessary content, thereby improving the accuracy of the text.

[0059] Furthermore, in some optional implementations of the present embodiment, when receiving a user's first input of target key information in at least one key information, it can be determined whether the second text contains a paragraph associated with the target key information; when the second text contains a paragraph associated with the target key information, the paragraph associated with the target key information in the second text can be displayed; when the second text does not contain a paragraph associated with the target key information, a prompt message is displayed, and the prompt message is used to indicate that the paragraph associated with the target key information does not exist. In this way, users can be helped to understand the changes in the text, avoid jump errors caused by missing paragraphs, and improve the continuity and accuracy of the information retrieval process.

[0060] The method provided by the above embodiment of the present application first inputs the speech to be processed into the first model, obtains the first text corresponding to the speech to be processed output by the first model, and the first text includes multiple paragraphs; then, through the second model, at least one key information in the first text and the paragraphs in the first text associated with the above at least one key information are determined; then, the above at least one key information is displayed on the display interface of the first text; in the case of receiving the first input of the target key information in the at least one key information from the user, the paragraphs in the first text associated with the target key information are displayed. On the one hand, at least one key information in the first text is extracted by the second model, and the paragraphs associated with each key information are identified, which saves the process of the user manually replaying the speech to understand the speech content, and saves the process of the user manually refining the key information in the speech by browsing the text. In the case of a long speech to be processed, the efficiency of obtaining information from the audio and the accuracy of the information obtained can be greatly improved. On the other hand, in the case of receiving the first input of the target key information from the user, the paragraphs in the first text associated with the target key information are displayed, which can facilitate the user to quickly locate the paragraph corresponding to the target key information in the first text, further improving the efficiency of obtaining information from the audio.

[0061] It should be noted that the information display method provided in the embodiment of the present application can be executed by an information display device. In the embodiment of the present application, the information display device executing the information display method is taken as an example to illustrate the information display device provided in the embodiment of the present application.

[0062] like Figure 6 As shown, the information display device 600 of this embodiment includes: a speech recognition unit 601, used to input the speech to be processed into a first model, and obtain a first text corresponding to the speech to be processed output by the first model, wherein the first text includes a plurality of paragraphs; a processing unit 602, used to determine at least one key information in the first text and a paragraph in the first text associated with the at least one key information through a second model; a first display unit 603, used to display the at least one key information on the display interface of the first text; and a second display unit 604, used to display the paragraph in the first text associated with the target key information when receiving a first input from a user for the target key information in the at least one key information.

[0063] In some optional implementations of the present embodiment, the first display unit 602 is further used to: display a first page, wherein the first page includes at least a first area and a second area, wherein the first area includes the at least one key information, and the second area includes the text content of the first text. By displaying the key information in the first text and the text content of the first text in different areas, it is convenient for the user to browse the original text content in the first text without switching pages when browsing the key information in the first text, so as to further understand more content in the first text, thereby improving the efficiency of information acquisition. Through an intelligent user interaction interface, the user can easily jump between key information and related paragraphs, thereby realizing efficient browsing and processing of text corresponding to long-term voice content.

[0064] In some optional implementations of this embodiment, the second display unit 603 is further used to: switch the first page to a second page, the second page including the text content of the first text; and switch the displayed text content of the first text to a paragraph associated with the target key information. By switching the first page to a second page including the text content of the first text upon receiving the user's first input of the target key information, and switching the text content of the first text displayed in the second page to a paragraph associated with the target key information, the user can not only browse the content of the paragraph, but also obtain the context information of the paragraph, thereby improving the richness and convenience of information acquisition.

[0065] In some optional implementations of the present embodiment, the second display unit 603 is further used to: when the target key information is associated with at least two paragraphs, determine the display order of the at least two paragraphs based on the position of each paragraph in the at least two paragraphs in the first text; select the first paragraph from the at least two paragraphs based on the display order; switch the text content of the displayed first text to the first paragraph; when receiving the second input of the user to the second page, select the next paragraph from the at least two paragraphs based on the display order; switch the text content of the displayed first text to the next paragraph. When the target key information is associated with at least two paragraphs, by first displaying the first paragraph and then switching to the next paragraph when receiving the second input of the user to the second page, the switching display of the paragraphs associated with the target key information can be realized conveniently and quickly without the user having to manually slide the page, further improving the convenience of information acquisition.

[0066] In some optional implementations of this embodiment, the device further includes a switching unit, which is used to: determine the last paragraph of the at least two paragraphs based on the display order; receive a third input from the user to the second page when the text content of the displayed first text includes the last paragraph; and switch the second page to the first page in response to the third input. In this way, after the user browses each paragraph associated with the target key information, the user can quickly and conveniently jump to the first page displaying the key information without the user having to manually close the second page and open the first page, thereby improving the convenience of information acquisition.

[0067] In some optional implementations of this embodiment, the device further includes an updating unit, which is used to: receive a fourth input from a user to the second area; in response to the fourth input, update the text content of the first text to obtain a second text; and switch the displayed text content of the first text to the text content of the second text. Thus, the user can edit or delete the paragraphs in the first text returned by the first model, which means that the user can correct errors in the first text, add supplementary information to the first text, or delete unnecessary content, thereby improving the accuracy of the text.

[0068] In some optional implementations of the present embodiment, the second display unit is further used to: determine whether the second text contains a paragraph associated with the target key information in the at least one key information when receiving a first input from the user; display the paragraph associated with the target key information in the second text when the second text contains the paragraph associated with the target key information; and display a prompt message when the second text does not contain the paragraph associated with the target key information, wherein the prompt message is used to indicate that the paragraph associated with the target key information does not exist. Thus, the user can be helped to understand the changes in the text, avoid jump errors caused by missing paragraphs, and improve the continuity and accuracy of the information retrieval process.

[0069] The device provided by the above embodiment of the present application first inputs the speech to be processed into the first model, obtains the first text corresponding to the speech to be processed output by the first model, and the first text includes multiple paragraphs; then, through the second model, at least one key information in the first text and the paragraphs in the first text associated with the above at least one key information are determined; then, the above at least one key information is displayed on the display interface of the first text; in the case of receiving the first input of the target key information in the at least one key information from the user, the paragraphs in the first text associated with the target key information are displayed. On the one hand, at least one key information in the first text is extracted by the second model, and the paragraphs associated with each key information are identified, which saves the process of the user manually replaying the speech to understand the speech content, and saves the process of the user manually refining the key information in the speech by browsing the text. In the case of a long speech to be processed, the efficiency of obtaining information from the audio and the accuracy of information acquisition can be greatly improved. On the other hand, in the case of receiving the first input of the target key information from the user, the paragraphs in the first text associated with the target key information are displayed, which can facilitate the user to quickly locate the paragraph corresponding to the target key information in the first text, further improving the efficiency of obtaining information from the audio.

[0070] The information display device in the embodiment of the present application can be an electronic device, or a component in the electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal, or it can be other devices other than the terminal. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, a vehicle-mounted electronic device, a mobile Internet device (Mobile Internet Device, MID), an augmented reality (Augmented Reality, AR) / virtual reality (Virtual Reality, VR) device, a robot, a wearable device, an ultra-mobile personal computer (Ultra-Mobile Personal Computer, UMPC), a netbook or a personal digital assistant (Personal Digital Assistant, PDA), etc., and can also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (Personal Computer, PC), a television (Television, TV), a teller machine or a self-service machine, etc., and the embodiment of the present application is not specifically limited.

[0071] The information display device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0072] The information display device provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0073] Alternatively, if Figure 7 As shown, an embodiment of the present application also provides an electronic device 700, including a processor 701 and a memory 702, wherein the memory 702 stores programs or instructions that can be executed on the processor 701, and when the program or instructions are executed by the processor 701, the various steps of the above-mentioned information display method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, they are not described here.

[0074] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile electronic devices and non-mobile electronic devices.

[0075] Figure 8 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0076] The electronic device 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, and a processor 810 and other components.

[0077] Those skilled in the art will appreciate that the electronic device 800 may also include a power source (such as a battery) for supplying power to each component, and the power source may be logically connected to the processor 810 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 8 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0078] Among them, the processor 810 is used to input the speech to be processed into the first model, and obtain the first text corresponding to the speech to be processed output by the first model, wherein the first text includes multiple paragraphs; the processing unit is used to determine at least one key information in the first text and the paragraphs in the first text associated with the at least one key information through the second model; the display unit 806 is used to display the at least one key information on the display interface of the first text; when the user receives the first input of the target key information in the at least one key information through the user input unit 807, the paragraph in the first text associated with the target key information is displayed.

[0079] By extracting at least one key information in the first text through the second model and identifying the paragraphs associated with each key information, the user is saved from the process of manually replaying the voice to understand the voice content, and the user is saved from the process of manually refining the key information in the voice by browsing the text. In the case of a long voice to be processed, the efficiency of obtaining information from the audio and the accuracy of information acquisition can be greatly improved. In addition, when the user's first input of the target key information is received, the paragraphs in the first text associated with the target key information are displayed, which can facilitate the user to quickly locate the paragraph in the first text corresponding to the target key information, further improving the efficiency of obtaining information from the audio.

[0080] In some optional implementations of the present embodiment, the display unit 806 is also used to display a first page, wherein the first page includes at least a first area and a second area, wherein the first area includes the at least one key information, and the second area includes the text content of the first text. By displaying the key information and text content in the first text in different areas, it is convenient for the user to browse the original text content in the first text without switching pages when browsing the key information in the first text, thereby understanding more content in the first text and improving information acquisition efficiency. Through an intelligent user interaction interface, the user can easily jump between key information and related paragraphs, thereby achieving efficient browsing and processing of text corresponding to long-term voice content.

[0081] In some optional implementations of this embodiment, the processor 810 is further configured to switch the first page to a second page, the second page including the text content of the first text; and switch the displayed text content of the first text to a paragraph associated with the target key information through the display unit 806. Thus, the user can not only browse the content of the paragraph, but also obtain the context information of the paragraph, thereby improving the richness and convenience of information acquisition.

[0082] In some optional implementations of this embodiment, the processor 810 is further used to, when the target key information is associated with at least two paragraphs, determine the display order of the at least two paragraphs based on the position of each paragraph in the at least two paragraphs in the first text; select the first paragraph from the at least two paragraphs based on the display order; switch the text content of the first text displayed to the first paragraph through the display unit 806; when the user receives the second input of the second page from the user through the user input unit 807, select the next paragraph from the at least two paragraphs based on the display order; and switch the text content of the first text displayed to the next paragraph through the display unit 806. When the target key information is associated with at least two paragraphs, by first displaying the first paragraph, and when the user receives the second input of the second page from the user, switching the display content to display the next paragraph, the switching display of the paragraphs associated with the target key information can be realized conveniently and quickly without the user having to manually slide the page, further improving the convenience of information acquisition.

[0083] In some optional implementations of this embodiment, the processor 810 is further used to determine the last paragraph of the at least two paragraphs based on the display order; when the text content of the displayed first text includes the last paragraph, receive the user's third input to the second page through the user input unit 807; and in response to the third input, switch the second page to the first page. In this way, after the user browses each paragraph associated with the target key information, it is possible to quickly and conveniently jump to the first page displaying the key information, without the user having to manually close the second page and open the first page, thereby improving the convenience of information acquisition.

[0084] In some optional implementations of this embodiment, the user input unit 807 is further used to receive a fourth input from the user to the second area; the processor 810 is further used to update the text content of the first text in response to the fourth input to obtain the second text; and the text content of the displayed first text is switched to the text content of the second text through the display unit 806. Thus, the user can edit or delete the paragraphs in the first text returned by the first model, which means that the user can correct errors in the first text, add supplementary information to the first text, or delete unnecessary content, thereby improving the accuracy of the text.

[0085] In some optional implementations of the present embodiment, the processor 810 is further used to determine whether the second text contains a paragraph associated with the target key information when receiving a first input of the target key information in the at least one key information from the user through the user input unit 807; when the second text contains a paragraph associated with the target key information, the display unit 806 is controlled to display the paragraph associated with the target key information in the second text; when the second text does not contain a paragraph associated with the target key information, the display unit 806 is controlled to display a prompt message, the prompt message is used to indicate that the paragraph associated with the target key information does not exist. In this way, the user can be helped to understand the changes in the text, avoid jump errors caused by missing paragraphs, and improve the continuity and accuracy of the information retrieval process.

[0086] It should be understood that in the embodiment of the present application, the input unit 804 may include a graphics processor (Graphics Processing Unit, GPU) 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0087] The memory 809 can be used to store software programs and various data. The memory 809 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 809 may include a volatile memory or a non-volatile memory, or the memory 809 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0088] The processor 810 may include one or more processing units; optionally, the processor 810 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 810.

[0089] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned information display method embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0090] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0091] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned information display method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0092] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0093] An embodiment of the present application provides a computer program product, which is stored in a storage medium. The program product is executed by at least one processor to implement the various processes of the above-mentioned information display method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0094] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0095] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0096] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An information display method, characterized in that: The method comprises: Inputting the speech to be processed into a first model, obtaining a first text corresponding to the speech to be processed output by the first model, wherein the first text includes a plurality of paragraphs; Determining, by a second model, at least one key information in the first text and a paragraph in the first text associated with the at least one key information; Displaying the at least one key information on the display interface of the first text; When a first input of a user for target key information among the at least one key information is received, a paragraph in the first text associated with the target key information is displayed.

2. The method according to claim 1, characterized in that The displaying of the at least one key information on the first text display interface includes: A first page is displayed, wherein the first page includes at least a first area and a second area, wherein the first area includes the at least one key information, and the second area includes text content of the first text.

3. The method according to claim 2, characterized in that The displaying of the paragraph in the first text associated with the target key information includes: Switching the first page to a second page, where the second page includes text content of the first text; Switch the displayed text content of the first text to a paragraph associated with the target key information.

4. The method according to claim 3, characterized in that The step of switching the displayed text content of the first text to a paragraph associated with the target key information includes: In a case where the target key information is associated with at least two paragraphs, determining a display order of the at least two paragraphs based on a position of each of the at least two paragraphs in the first text; Based on the display order, selecting a first paragraph from the at least two paragraphs; Switching the displayed text content of the first text to the first paragraph; When receiving a second input from the user on the second page, selecting a next paragraph from the at least two paragraphs based on the display order; The displayed text content of the first text is switched to the next paragraph.

5. The method according to claim 4, characterized in that The method further comprises: Based on the display order, determining a last paragraph of the at least two paragraphs; In a case where the displayed text content of the first text includes the last paragraph, receiving a third input of the user on the second page; In response to the third input, the second page is switched to the first page.

6. The method according to claim 2, characterized in that The method further comprises: receiving a fourth input from a user regarding the second area; In response to the fourth input, updating the text content of the first text to obtain a second text; The displayed text content of the first text is switched to the text content of the second text.

7. The method according to claim 6, characterized in that The method of, upon receiving a first input of a user for target key information in the at least one key information, displaying a paragraph in the first text associated with the target key information comprises: In case of receiving a first input of a user for target key information among the at least one key information, determining whether the second text includes a paragraph associated with the target key information; In a case where the second text includes a paragraph associated with the target key information, displaying the paragraph associated with the target key information in the second text; In a case where the second text does not include the paragraph associated with the target key information, prompt information is displayed, where the prompt information is used to indicate that the paragraph associated with the target key information does not exist.

8. An information display device, characterized in that: The device comprises: A speech recognition unit, configured to input the speech to be processed into a first model, and obtain a first text output by the first model and corresponding to the speech to be processed, wherein the first text includes a plurality of paragraphs; a processing unit, configured to determine, by using a second model, at least one key information in the first text and a paragraph in the first text associated with the at least one key information; A first display unit, configured to display the at least one key information on a display interface of the first text; The second display unit is configured to display a paragraph in the first text associated with the target key information when receiving a first input from a user regarding the target key information in the at least one key information.

9. The device according to claim 8, characterized in that The first display unit is further used for: A first page is displayed, wherein the first page includes at least a first area and a second area, wherein the first area includes the at least one key information, and the second area includes text content of the first text.

10. The device according to claim 9, characterized in that The second display unit is further used for: Switching the first page to a second page, where the second page includes text content of the first text; Switch the displayed text content of the first text to a paragraph associated with the target key information.

11. The device according to claim 10, characterized in that The second display unit is further used for: In a case where the target key information is associated with at least two paragraphs, determining a display order of the at least two paragraphs based on a position of each of the at least two paragraphs in the first text; Based on the display order, selecting a first paragraph from the at least two paragraphs; Switching the displayed text content of the first text to the first paragraph; When receiving a second input from the user on the second page, selecting a next paragraph from the at least two paragraphs based on the display order; The displayed text content of the first text is switched to the next paragraph.

12. The device according to claim 11, characterized in that The device also includes a switching unit, which is used to: Based on the display order, determining a last paragraph of the at least two paragraphs; In a case where the displayed text content of the first text includes the last paragraph, receiving a third input of the user on the second page; In response to the third input, the second page is switched to the first page.

13. The device according to claim 9, characterized in that The device also includes an updating unit, configured to: receiving a fourth input from a user regarding the second area; In response to the fourth input, updating the text content of the first text to obtain a second text; The displayed text content of the first text is switched to the text content of the second text.

14. The device according to claim 13, characterized in that The second display unit is further used for: In case of receiving a first input of a user for target key information among the at least one key information, determining whether the second text includes a paragraph associated with the target key information; In a case where the second text includes a paragraph associated with the target key information, displaying the paragraph associated with the target key information in the second text; In a case where the second text does not include the paragraph associated with the target key information, prompt information is displayed, where the prompt information is used to indicate that the paragraph associated with the target key information does not exist.

Images