Content recording and managing method, terminal equipment, storage medium and computer equipment

Abstract

The invention provides a voice assistant-based content recording and management method, a terminal device, a storage medium and a computer device. The method comprises the following steps: through the voice assistant, receiving voice input from a user; converting the voice input into a text content item and storing the text content item in a predetermined data format; uploading data representing the text content item to a cloud server; and receiving associated content associated with the text content item from the cloud server, wherein the associated content is formed by the cloud server based on the uploaded data. According to the invention, the voice content from the user can be conveniently recorded and managed, the associated content can be provided for the user for use, such as reference, and the user experience can be improved.

Description

Technical Field

[0001] The present invention relates to the field of voice content recording and management, and in particular to a content recording and management method based on a voice assistant, a terminal device for content recording and management, and a corresponding computer-readable storage medium and a computer device. Background Art

[0002] Nowadays, as the pace of life is getting faster and faster, people may have a lot of content to record every day. It is very difficult and time-consuming to systematically record and organize the recorded content. Creators (such as singers and writers) may have inspiration that needs to be recorded in real time at a certain time. At this time, they may need to record it relatively accurately in order to further develop their ideas.

[0003] Voice assistants are applications that interact with people through conversations and answering questions. At present, the application of voice assistants has occupied a considerable proportion in our daily lives and is becoming more and more important. Figure 1 As shown in . Figure 1 The terms "AI assistant" and "voice assistant" are used interchangeably in .

[0004] Currently, there are some products on the market. One type of product is that the user manually activates the Notepad APP, then manually enters the subject and content that he wants to record, and finally saves the subject and content and exits the Notepad APP. Another type of product is that the user activates the Notepad APP through a wake-up word, then uses voice as input - the input is then converted into text content by the Notepad APP, and finally saves the text content and exits the Notepad APP.

[0005] The existing products have some problems, such as one or some of the following problems:

[0006] 1) Since existing products can only convert user's voice into text content, but cannot add topics to the text content, it is not convenient to manage the recorded text content;

[0007] 2) activating the notebook application and adding topics via voice was generally cumbersome as it did not provide a timely experience for the user; and

[0008] 3) As time goes by, the recorded content becomes chaotic and huge in volume, and the creator may find it difficult to remember when the content was recorded; therefore, without constructive organization, the chaotic recorded content cannot provide reasonable inspiration for the creator for reference.

[0009] Therefore, there exists a need for improved voice content recording and management solutions. Summary of the invention

[0010] An object of the present invention is to provide a content recording and management solution based on a voice assistant to solve or alleviate at least some of the above-mentioned problems of the prior art.

[0011] In a first aspect of the present invention, a content recording and management method based on a voice assistant is provided, comprising: using the voice assistant:

[0012] receiving voice input from a user;

[0013] converting the speech input into a text content item and storing the text content item in a predetermined data format;

[0014] uploading data representing the text content item to a cloud server; and

[0015] Receiving associated content associated with the text content item from the cloud server, wherein the associated content is formed by the cloud server based on the uploaded data.

[0016] In a second aspect of the present invention, a terminal device for content recording and management is provided, comprising:

[0017] A voice assistant, wherein the voice assistant is configured to:

[0018] receiving voice input from a user;

[0019] converting the speech input into a text content item and storing the text content item in a predetermined data format;

[0020] uploading data representing the text content item to a cloud server; and

[0021] receiving, from the cloud server, associated content associated with the text content item,

[0022] The associated content is formed by the cloud server based on the uploaded data.

[0023] In a third aspect of the present invention, a computer-readable storage medium is provided, 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 of the present invention are implemented.

[0024] In a fourth aspect of the present invention, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method described in the first aspect of the present invention are implemented.

[0025] The solution according to the present invention can facilitate the recording and management of voice content from users, and can provide users with associated related content for use such as reference, which is conducive to improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Non-limiting and non-exhaustive embodiments of the present invention are described, by way of example, with reference to the following drawings, in which:

[0027] Figure 1 Shows the usage rate of AI assistants among Chinese consumers;

[0028] Figure 2 The flowchart of the content recording and management method based on the voice assistant according to an embodiment of the present invention is schematically shown;

[0029] Figure 3 A block diagram schematically shows a terminal device for content recording and management according to an embodiment of the present invention; and

[0030] Figure 4 The flowchart of a content recording and management method based on a voice assistant according to a specific embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0031] In order to make the above and other features and advantages of the present invention clearer, the present invention is further described below in conjunction with the accompanying drawings. The accompanying drawings constitute a part of this application and are used to illustrate the present invention together with the embodiments of the present invention. For the purpose of clarity and simplification, detailed specific descriptions of known functions and structures of the devices, devices and / or equipment described herein will be omitted when they may obscure the subject matter of the present invention. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are only exemplary and non-restrictive.

[0032] The features described herein may be embodied in different forms and should not be construed as being limited to the embodiments described herein. Rather, the embodiments described herein are provided only to illustrate some of the many possible ways of implementing the devices and / or systems described herein, which will be apparent after understanding the disclosure of the present application.

[0033] As used herein, the term "and / or" includes any one of the associated listed items and any combination of any two or more of the associated listed items.

[0034] Although terms such as "first," "second," "third," and "fourth" may be used herein to describe various components, parts, portions, or elements, these components, parts, portions, or elements are not limited by these terms. Instead, these terms are only used to distinguish one component, part, portion, or element from another component, part, portion, or element. Therefore, without departing from the teachings of the present invention, a first component, part, portion, or element mentioned herein may also be referred to as a second component, part, portion, or element.

[0035] The terms used herein are only used to describe various embodiments and are not used to limit the present disclosure. Unless the context clearly indicates otherwise, "a", "an" and "the" are intended to include plural forms as well. The terms "include", "comprise" and "have" specify the presence of stated features, operations, components, elements and / or combinations thereof, but do not exclude the presence or addition of one or more other features, operations, components, elements and / or combinations thereof.

[0036] In the following description, many specific details are set forth to provide a thorough understanding of the present invention. However, it will be apparent to one of ordinary skill in the art that the present invention does not need to be practiced using the specific details. In other cases, well-known steps or operations are not described in detail to avoid obscuring the present invention.

[0037] The basic concept of the present invention is to provide an improved voice content recording and management solution based on a voice assistant to facilitate the recording and management of voice content from users and provide users with associated information for use such as reference, thereby improving user experience. The voice assistant can be installed on a voice-activated terminal device. Thus, the improved voice content recording and management solution based on a voice assistant of the present invention can make the terminal device smarter. The voice-activated terminal device can be various intelligent terminal devices that support voice input and interaction, such as home appliances, mobile phones, computer devices, etc.

[0038] The present invention is described below by way of example only with reference to the accompanying drawings.

[0039] Figure 2 The flowchart of a method 200 for recording and managing content based on a voice assistant according to an embodiment of the present invention is schematically shown. The method 200 includes executing the following steps S201-S204 by an activated voice assistant.

[0040] In step S201, a voice input from a user is received. Specifically, the voice input from the user can be received via a voice receiving component suitable for receiving voice information inside or outside the terminal device on which the voice assistant is installed. The voice receiving component can be, for example, a built-in microphone of the terminal device or a microphone coupled to the terminal device in a communicative manner. The microphone converts the user's voice input into an electrical signal and transmits the electrical signal to the voice assistant.

[0041] In step S202, the voice input is converted into a text content item and the text content item is stored in a predetermined data format. The voice input can be converted into a text content item in various suitable ways known in the art, which will not be described in detail here.

[0042] Depending on the circumstances, the predetermined data format may be a default data format, or may be based on recording mode information from a user indicating a recording mode. The recording mode information may be in various possible forms. For example, the recording mode information may be a part of the voice input, such as one or more characters or words contained in a text content item converted from the voice input; or, the recording mode information may be a separate input independent of the voice input (e.g., a mode selection signal for selecting a recording mode), which may be provided by the user before or after inputting the voice input.

[0043] In one embodiment, the method 200 also includes: receiving, through the voice assistant, recording mode information indicating a recording mode from a user, wherein in response to the recording mode information, the voice assistant operates in the recording mode indicated by the recording mode information, and stores the text content item in a predetermined data format corresponding to the recording mode indicated by the recording mode information.

[0044] In one embodiment, the recording mode includes a non-subject recording mode and a subject recording mode, the predetermined data format corresponding to the non-subject recording mode has at least one field and does not have a "subject" field indicating the subject of the text content item, and the predetermined data format corresponding to the subject recording mode has the at least one field and has a "subject" field indicating the subject of the text content item.

[0045] In one embodiment, the at least one field includes a "content" field indicating the content of the text content item and a "keyword" field indicating a keyword of the text content item.

[0046] In one embodiment, the recording mode indicated by the recording mode information is a recording mode with a subject, and storing the text content item in a predetermined data format includes: identifying the subject of the text content item; determining whether there is a created subject for the identified subject; if the determination result is affirmative, storing the text content item under the created subject in a predetermined data format corresponding to the recording mode with a subject; if the determination result is negative, creating the identified subject and storing the text content item under the created subject in a predetermined data format corresponding to the recording mode with a subject.

[0047] In step S203, the data representing the text content item is uploaded to the cloud server. It should be understood that the terminal device on which the voice assistant is installed can communicate with the cloud server wirelessly or by wire, so that the data representing the text content item can be uploaded to the cloud server. Uploading the data representing the text content item to the cloud server can be performed in response to an upload instruction from the user or automatically; in the former case, the user can decide whether to upload the data representing the text content item to the cloud server.

[0048] In step S204, associated content associated with the text content item is received from the cloud server, wherein the associated content is formed by the cloud server based on the uploaded data. In one embodiment, the associated content includes: content associated with the text content item searched by the cloud server via the Internet using big data technology and / or AI technology; and / or content associated with the text content item generated by the cloud server using big data technology and / or AI technology.

[0049] Specifically, in response to receiving data representing the text content item, the cloud server forms associated content associated with the text content item based on the uploaded data. Depending on the situation, the cloud server may automatically provide the associated content to the voice assistant, or provide the associated content to the voice assistant in response to a triggering event. For example, in the latter case, the cloud server may store the associated content locally and establish an association relationship between the associated content and the text content item; based on this association relationship, in response to an event associated with the text content item being accessed (i.e., when a triggering event occurs), the cloud server provides the locally stored associated content to the voice assistant for presentation to the user. This association relationship can be embodied and implemented in various possible ways or forms. This is further described in detail below through examples.

[0050] In one embodiment, the cloud server receives and stores uploaded data representing the text content item (referred to as "data A"), and then uses big data technology and / or AI technology to search the Internet and / or use big data technology and / or AI technology to generate content associated with the text content item (referred to as "content B"), and stores the content B on the cloud server. Afterwards, when the user consults the text content item represented by data A, in response to this, the cloud server provides the locally stored content B to the voice assistant for presentation to the user, and the user automatically sees content B. As a result, it can help users expand their thinking, save development time, reduce workload, easily find valuable references or documents, etc. The content B can be any form of content associated with the text content item, such as text, voice or web page link, for example, content B can be displayed near the text content item.

[0051] To further facilitate understanding, two examples are described below.

[0052] Example 1: The user is a programmer. At a certain moment, he suddenly has an inspiration and thinks of a solution to a problem (such as quick sorting), and forms a pseudocode (Pseudocode), or just a basic flow chart of ideas. The user provides the pseudocode or the flow chart to the voice assistant on his smart terminal device in the form of voice input. According to the method of the present invention, the voice assistant converts the voice input into a text content item and uploads the data representing the text content item to the cloud server; in response, the cloud server searches for codes, web links, document introductions, etc. related to sorting according to the data (such as the content, tags, keywords, etc. of the text content item represented by it), thereby forming associated content associated with the text content item. When the user subsequently writes code about quick sorting, by accessing, such as viewing, the text content item stored on his terminal device, the cloud server can be triggered to provide associated content associated with the text content item, so that the associated content associated with the text content item can be viewed and utilized.

[0053] Example 2: The user is a designer or creator, and the associated content generated by the cloud server can even be a design work, a novel fragment, etc. generated by AIGC (AI-generated content) technology. Other aspects may be similar to Example 1 and will not be elaborated here.

[0054] Figure 3 The block diagram of a terminal device 300 for content recording and management according to an embodiment of the present invention is schematically shown. The terminal device 300 may be, for example but not limited to, a home appliance, a mobile phone, a computer device, etc.

[0055] The terminal device includes a voice assistant 301, wherein the voice assistant 301 is configured to: receive voice input from a user; convert the voice input into a text content item and store the text content item in a predetermined data format; upload data representing the text content item to a cloud server communicatively coupled to the terminal device; and receive associated content associated with the text content item from the cloud server, wherein the associated content is formed by the cloud server based on the uploaded data.

[0056] The specific features, operations and details described above with respect to the content recording and management method based on a voice assistant of the present invention can also be similarly applied to the terminal device for content recording and management of the present invention. In addition, each step of the method of the present invention described above can be performed by a voice assistant installed on the terminal device of the present invention.

[0057] Figure 4 A flowchart of a content recording and management method based on a voice assistant according to a specific embodiment of the present invention is schematically shown, wherein boxes of different grayscale represent user input, voice assistant answers, data flow operations, and big data and AI platforms / operations thereof.

[0058] Two example scenarios are shown in this specific embodiment.

[0059] In an example scenario, the voice input received from the user by the voice assistant installed on the terminal device is "Please help me record something". The voice assistant replies "OK, start recording". Then, as Figure 4 As shown in , the voice assistant converts and stores.

[0060] Specifically, the voice assistant converts the voice input into a text content item. Since the voice input does not contain any content indicating a subject, the voice assistant cannot recognize any subject and therefore operates in a no-subject recording mode by default. In this no-subject recording mode, the voice assistant stores the text content item in a predetermined data format corresponding to the no-subject recording mode. Figure 4 As shown in , the predetermined data format corresponding to the subject-free record mode has a "content" field indicating the content of the text content item and a "keyword" field indicating a keyword (e.g., automatically generated keyword) of the text content item, and does not have a "subject" field indicating the subject of the text content item (in Figure 4 In other words, the predetermined data format corresponding to the no-subject record mode is the "content-keyword" data format.

[0061] In another example scenario, the voice input received from the user by the voice assistant installed on the terminal device is "Please help me record some content under the painting". The voice assistant replies "OK, start recording". Then, as Figure 4 As shown in , the voice assistant converts and stores.

[0062] Specifically, the voice assistant converts the voice input into a text content item. The voice input contains content indicating a theme "painting", in response to which the voice assistant operates in a theme recording mode and stores the text content item in a predetermined data format corresponding to the theme recording mode. Figure 4 As shown in , the predetermined data format corresponding to the subject recording mode has a "subject" field indicating the subject of the text content item (i.e., the subject "painting" - which is recognized by the voice assistant), a "content" field indicating the content of the text content item, and a "keyword" field indicating the keywords of the text content item (e.g., automatically generated keywords); in other words, the predetermined data format corresponding to the subject recording mode is a "subject-content-keyword" data format.

[0063] After identifying the theme "painting" and before storing it, the voice assistant determines whether there is a created theme for "painting". Figure 4 As shown in , if there is no created topic for "painting" in the memory of the terminal device (that is, "painting" does not exist), the voice assistant generates a "painting" topic and then stores it under the created "painting" topic. If there is a created topic for "painting" in the memory of the terminal device (that is, "painting" exists), the voice assistant directly stores it under the created topic.

[0064] Figure 4It is also shown that the data representing the text content item is uploaded to the cloud server. The cloud server forms associated content associated with the text content item based on big data technology and / or AI technology to provide feedback information to the user; in this sense, the cloud server can be regarded as a big data and AI platform. The associated content is formed by the cloud server based on the uploaded data, and may include: content associated with the text content item searched by the cloud server via the Internet using big data technology and / or AI technology; and / or content associated with the text content item generated by the cloud server using big data technology and / or AI technology. For example, the cloud server can classify the text content item represented by the data, generate valuable reference information, generate valuable reference works, generate summary reports, etc. as associated content associated with the text content item. The voice assistant can receive associated content associated with the text content item from the cloud server.

[0065] It should be understood by those skilled in the art that Figure 3 The schematic diagram shown in the figure is only an exemplary block diagram of a part of the structure related to the scheme of the present invention, and does not constitute a limitation on the computer device, processor or computer program embodying the scheme of the present invention. The specific computer device, processor or computer program may include more or fewer components or modules than shown in the figure, or combine or split certain components or modules, or have different arrangements of components or modules.

[0066] The present invention may be implemented as a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the method of the present invention. In one embodiment, the computer program is distributed on a plurality of computer devices or processors coupled to a network so that the computer program is stored, accessed, and executed in a distributed manner by one or more computer devices or processors. One or more method steps / operations may be performed by one or more computer devices or processors, and one or more other method steps / operations may be performed by one or more other computer devices or processors. One or more computer devices or processors may perform a single method step / operation, or perform two or more method steps / operations.

[0067] In one embodiment, the present invention provides a computer device, which includes a memory and a processor, wherein a computer program that can be run on the processor is stored on the memory, and the processor implements the steps of the method of the present invention when executing the computer program. The computer device can be broadly a server, a vehicle-mounted terminal, or any other electronic device with necessary computing and / or processing capabilities. In one embodiment, the computer device may include a processor, a memory, a network interface, a communication interface, etc. connected via a system bus. The processor of the computer device can be used to provide necessary computing, processing and / or control capabilities. The memory of the computer device may include a non-volatile storage medium and an internal memory. An operating system, a computer program, etc. may be stored in or on the non-volatile storage medium. The internal memory may provide an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface and the communication interface of the computer device can be used to connect and communicate with external devices through a network. When the computer program is executed by the processor, each step of the content recording and management method based on a voice assistant of the present invention is performed.

[0068] It will be appreciated by those skilled in the art that all or part of the steps of the content recording and management method based on a voice assistant of the present invention can be completed by instructing related hardware such as a computer device or a processor through a computer program, and the computer program can be stored in a non-temporary computer-readable storage medium, and the computer program is executed to cause the steps of the content recording and management method based on a voice assistant of the present invention to be executed. Depending on the circumstances, any reference to memory, storage, database or other media herein may include non-volatile and / or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magnetic storage device, optical storage device, hard disk, solid state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0069] The various technical features described above can be combined arbitrarily. Although all possible combinations of these technical features are not described, any combination of these technical features should be considered to be covered by this specification as long as there is no contradiction in such combination.

Claims

1. A content recording and management method based on a voice assistant, comprising: receiving voice input from a user; converting the speech input into a text content item and storing the text content item in a predetermined data format; uploading data representing the text content item to a cloud server; as well as Receiving associated content associated with the text content item from the cloud server, wherein the associated content is formed by the cloud server based on the uploaded data.

2. The method according to claim 1, further comprising: Recording mode information indicating a recording mode is received from a user through the voice assistant, wherein in response to the recording mode information, the voice assistant operates in the recording mode indicated by the recording mode information and stores the text content item in a predetermined data format corresponding to the recording mode indicated by the recording mode information.

3. The method according to claim 2, wherein the recording mode includes a no-subject recording mode and a subject recording mode, the predetermined data format corresponding to the no-subject recording mode has at least one field and does not have a "subject" field indicating the subject of the text content item, and the predetermined data format corresponding to the subject recording mode has the at least one field and has a "subject" field indicating the subject of the text content item.

4. The method according to claim 3, wherein the at least one field includes a “content” field indicating the content of the text content item and a “keyword” field indicating a keyword of the text content item.

5. The method according to claim 3, wherein the recording mode indicated by the recording mode information is a subject recording mode, and storing the text content item in a predetermined data format comprises: identifying a subject matter of the textual content item; determining whether there is a created topic for the identified topic; If the determination result is positive, storing the text content item under the created topic in a predetermined data format corresponding to the topic record mode; If the determination result is negative, the identified topic is created and the text content item is stored under the created topic in a predetermined data format corresponding to the topic-recording mode. 6 . The method of claim 1 , wherein uploading the data representing the text content item to a cloud server is performed in response to an upload instruction from a user or is performed automatically.

7. The method according to claim 1, wherein the associated content comprises: The cloud server searches for content associated with the text content item via the Internet using big data technology and / or AI technology; and / or, The cloud server generates content associated with the text content item using big data technology and / or AI technology.

8. A terminal device for content recording and management, comprising: A voice assistant, wherein the voice assistant is configured to: receiving voice input from a user; converting the speech input into a text content item and storing the text content item in a predetermined data format; uploading data representing the text content item to a cloud server; as well as Receiving associated content associated with the text content item from the cloud server, wherein the associated content is formed by the cloud server based on the uploaded data.

9. The terminal device according to claim 8, The voice assistant is further configured to receive recording mode information indicating a recording mode from a user, wherein in response to the recording mode information, the voice assistant operates in the recording mode indicated by the recording mode information and stores the text content item in a predetermined data format corresponding to the recording mode indicated by the recording mode information.

10. The terminal device according to claim 9, wherein the recording mode comprises a non-subject recording mode and a subject recording mode, the predetermined data format corresponding to the non-subject recording mode has at least one field and does not have a "subject" field indicating the subject of the text content item, and the predetermined data format corresponding to the subject recording mode has the at least one field and has a "subject" field indicating the subject of the text content item.

11. The terminal device according to claim 10, wherein the at least one field includes a "content" field indicating content of the text content item and a "keyword" field indicating a keyword of the text content item.

12. The terminal device according to claim 10, wherein the recording mode indicated by the recording mode information is a subject recording mode, and storing the text content item in a predetermined data format comprises: identifying a subject matter of the textual content item; determining whether there is a created topic for the identified topic; If the determination result is positive, storing the text content item under the created topic in a predetermined data format corresponding to the topic record mode; If the determination result is negative, the identified topic is created and the text content item is stored under the created topic in a predetermined data format corresponding to the topic-recording mode.

13. The terminal device according to claim 8, wherein the associated content comprises: The cloud server searches for content associated with the text content item via the Internet using big data technology and / or AI technology; and / or, The cloud server generates content associated with the text content item using big data technology and / or AI technology.

14. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 7.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of any one of the methods of claims 1 to 7 when executing the computer program.

Images