Voice interaction method for solving difficulty in man-machine interaction of user

Abstract

The invention provides a voice interaction method for solving the difficulty of man-machine interaction of a user, and aims to simplify the man-machine interaction process of the user and intelligent equipment. The method comprises the following steps: presetting simple numbers and corresponding instructions on each operation interface of the intelligent equipment; a user enters an operation interface; playing a video for guiding a user to operate, and displaying how to input a digital execution instruction through voice; a user inputs voice containing digits; recognizing and extracting digits, and neglecting irrelevant voices; if the number is matched with the preset number, executing an instruction corresponding to the number; and if not, prompting an error and replaying the video for guiding the user to operate. The system is especially suitable for the elderly group, adopts a simplified voice interaction mode, and can significantly improve the accuracy and convenience of accessing and using various digital products and services, thereby effectively reducing the digital gap.

Description

Technical Field

[0001] The present invention relates to the field of human-computer interaction technology, and more specifically, to a human-computer interaction technology for recognizing numbers in user voice and executing instructions corresponding to the numbers. Background Art

[0002] With the widespread penetration of smart devices and the popularity of digital life around the world, more and more elderly people are trying to integrate into this trend and enjoy the convenience brought by digital services. However, for this group, daily digital operations such as online shopping, online food ordering, stock trading, ticket booking, mobile payment, online medical registration, etc. pose a huge challenge, further exacerbating the "digital divide" in society. When faced with these complex interfaces and processes, the elderly often feel at a loss and urgently need a more accurate and easy-to-master interactive method to help them overcome this obstacle and enjoy the convenience of the digital age equally.

[0003] With the continuous advancement and innovation of technology, how to make smart devices respond to user commands more conveniently and accurately has always been the focus of research in the field of human-computer interaction technology.

[0004] At present, although there are many interactive methods such as keyboard input and touch screen, they do promote information exchange between users and smart devices to a certain extent. However, these traditional methods have significant problems of high operation complexity and high learning cost for certain groups, especially the elderly. These users often find it difficult to adapt to the rapidly changing digital technology, which leads to many obstacles when using smart devices.

[0005] The rise of voice interaction technology has provided a new way to simplify user operations. It allows users to interact with devices through verbal commands, greatly improving the convenience of operation. However, voice interaction technology still has limitations. First, environmental noise, accent differences, grammatical complexity, etc. will affect voice recognition. The accuracy of voice recognition is difficult to reach a perfect level, and user commands are sometimes not correctly recognized. Second, even if voice recognition technology can accurately capture user voices, it is difficult to accurately convert user colloquial expressions into specific operational intentions, because there is often a mismatch between the diversity of user expressions and the system's preset commands. Third, the applicable population is limited. For certain groups, especially the elderly, voice interaction technology is still complicated to operate, and it is difficult for these users to use it, and the "digital divide" still exists.

[0006] In view of the technical difficulties and social needs in the above background, the present invention proposes a voice interaction method that solves the difficulties of user-computer interaction. The method realizes a highly simplified interaction mode, and users can easily complete the originally complex operation tasks through simple voice input. The core advantage of this method lies in its extremely high ease of use. It can be used without special learning, while ensuring the accurate recognition and error-free execution of voice commands, solving the problems of insufficient accuracy and convenience in existing voice interaction methods. Summary of the invention

[0007] In order to solve the problems of insufficient accuracy and convenience in existing voice interaction methods, the present invention proposes a voice interaction method for solving the difficulties in user-computer interaction. The method combines the intuitive mapping relationship between simple numbers and instructions, uses guided videos to assist user operations, and integrates voice recognition technology to achieve a highly simplified interaction mode.

[0008] Technical Solution A voice interaction method for solving the difficulty of user-computer interaction includes presetting instructions, collecting and recognizing user voice, generating corresponding instructions according to the voice, and executing the instructions. The method is characterized in that the method includes the following steps: Step 1 In smart devices, each operation interface is pre-set with a number of simple numbers and corresponding instructions. In the same operation interface, each number uniquely corresponds to a specific instruction; Step 2 The user uses a smart device to enter any operation interface; Step 3 Play a video to guide the user to operate. The video content shows in detail that the user uses the smart device to input voice and accurately says any number preset on the current interface to execute the corresponding command; Step 4 The user uses the smart device to input voice containing numbers; Step 5: Collect and recognize the user's voice, extract the numbers in the user's voice, and ignore other irrelevant voice content; Step 6 If the recognized number completely matches any number preset in the current operation interface, a corresponding instruction is generated based on the recognized number and the generated instruction is executed; if the recognized number does not match any number preset in the current operation interface, the user is prompted that the voice input is incorrect, a video guiding the user operation is replayed or other forms of help are provided to guide the user to input the voice correctly, and the process returns to Step 4.

[0009] Beneficial Effects Compared with the prior art, the technical solution adopted by the present invention has at least the following advantages: 1. Extremely easy to use, no special learning is required to get started, while ensuring accurate recognition and error-free execution of voice commands; 2. Low cost, no additional equipment is required, and the invention can be realized by using existing smart devices; 3. It is suitable for a wide range of people, especially the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a step diagram of the present invention.

[0011] Figure 2 This is a structural diagram of the online shopping APP operation interface in an embodiment of the present invention; DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the following will be combined with the attached Figure 1 , Attachment Figure 2 The technical solution of the present application is described in detail with reference to specific embodiments. It should be noted that the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the protection scope of the present application. See also Figure 1 , the specific steps of the embodiment of the present invention are as follows:

[0013] Step 1 In smart devices, each operation interface is pre-set with a number of simple numbers and corresponding instructions. In the same operation interface, each number uniquely corresponds to a specific instruction; In the online shopping apps of smartphones, each operation interface is pre-set with a number of simple numbers and corresponding instructions. In the same operation interface, each number uniquely corresponds to a specific instruction. In the operation interface for selecting specifications and models, the numbers 1, 2, 3, 4, 5, 6, and 7 and corresponding instructions are preset. The instruction corresponding to number 1 is "buy three pounds of apples"; the instruction corresponding to number 2 is "buy five pounds of apples"; the instruction corresponding to number 3 is "find someone to bargain"; the instruction corresponding to number 4 is "share with WeChat friends"; the instruction corresponding to number 5 is "return to homepage", the instruction corresponding to number 6 is "return to the previous step"; the instruction corresponding to number 7 is "need help".

[0014] Step 2 The user uses a smart device to enter any operation interface; The user wants to buy an Apple product. He uses a smartphone to open the online shopping app and enters the online shopping app's specification and model selection operation interface. For the operation interface, refer to Figure 2 .

[0015] Step 3 Play a video to guide the user to operate. The video content shows in detail that the user uses the smart device to input voice and accurately says any number preset on the current interface to execute the corresponding command; The online shopping app plays a pre-recorded video to guide the user. In the video (2), the host points to the voice control (1) and explains the corresponding instructions for each number one by one: "To buy three pounds of apples, please press and hold the voice control and say 1. To buy five pounds of apples, please press and hold the voice control and say 2. To find someone to bargain, please press and hold the voice control and say 3. To share with WeChat friends, please press and hold the voice control and say 4. To return to the homepage, please press and hold the voice control and say 5. To return to the previous step, please press and hold the voice control and say 6. If you need help, please press and hold the voice control and say 7"; The video also demonstrates how the host can press and hold the voice control (1) and say a number to execute the corresponding command.

[0016] Step 4 The user uses the smart device to input voice containing numbers; If a user wants to buy five pounds of apples, he or she follows the instructions in the video to press and hold the voice control of the online shopping app on the smartphone and say "2".

[0017] Step 5: Collect and recognize the user's voice, extract the numbers in the user's voice, and ignore other irrelevant voice content; The online shopping APP collects and recognizes the voice input by the user, recognizes the number "2", extracts the number "2" from the user's voice, and ignores other irrelevant voice content.

[0018] Step 6 If the recognized number completely matches any number preset in the current operation interface, a corresponding instruction is generated according to the recognized number and the generated instruction is executed; if the recognized number does not match any number preset in the current operation interface, the user is prompted that the voice input is wrong, a video guiding the user operation is replayed to guide the user to input the voice correctly, and the process returns to Step 4; The number recognized by the online shopping APP is "2", and it is determined that it completely matches the number "2" preset in the current operation interface. It generates an instruction "Buy five pounds of apples" corresponding to the number "2", and executes the generated instruction "Buy five pounds of apples".

[0019] Embodiments of the present invention also have the ability to execute a variety of other instructions, including but not limited to checking order details, safely exiting the application, obtaining the user's mobile phone number, and determining the geographic location of the device. Due to space limitations, they are not listed here one by one.

[0020] Finally, it should be noted that the above is only a preferred embodiment of the present invention and does not constitute a limitation of the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify, replace or improve the technical solutions described in the aforementioned embodiments without departing from the spirit and principles of the present invention. For example, those skilled in the art can use simple character strings to replace numbers, such as replacing the preset number '1' with 'the first', replacing the preset number '2' with 'the second', and so on, and such replacement should be regarded as an equivalent replacement. Therefore, any modification, equivalent replacement or improvement made within the spirit and principles of the present invention should be deemed to be included in the scope of protection of the present invention.

Claims

1. A voice interaction method for solving the difficulty of user-computer interaction, including preset instructions, collecting and recognizing user voice, generating and executing corresponding instructions according to the voice, characterized in that: The method comprises the following steps: Step 1 In smart devices, each operation interface is pre-set with a number of simple numbers and corresponding instructions. In the same operation interface, each number uniquely corresponds to a specific instruction; Step 2 The user uses a smart device to enter any operation interface; Step 3 Play a video to guide the user to operate. The video content shows in detail that the user uses the smart device to input voice and accurately says any number preset on the current interface to execute the corresponding command; Step 4 The user uses the smart device to input voice containing numbers; Step 5: Collect and recognize the user's voice, extract the numbers in the user's voice, and ignore other irrelevant voice content; Step 6 If the recognized number completely matches any number preset in the current operation interface, a corresponding instruction is generated based on the recognized number and the generated instruction is executed; if the recognized number does not match any number preset in the current operation interface, the user is prompted that the voice input is incorrect, a video guiding the user operation is replayed or other forms of help are provided to guide the user to input the voice correctly, and the process returns to Step 4.

2. The smart device according to claim 1, characterized in that: The smart device has a touch screen and voice functions, and specifically includes but is not limited to devices such as smart phones and tablet computers.

3. The operation interface according to claim 1, characterized in that: The operation interface includes but is not limited to a main interface, a setting interface, an application interface, a function interface, etc.

4. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 1, each operation interface is pre-set with a number of simple numbers and corresponding instructions. These numbers may be different between different operation interfaces, or may be partially or completely the same; but within the same operation interface, each number uniquely corresponds to a specific instruction.

5. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 4, the user uses the microphone of the smart device to input voice.

6. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 4, the user uses the voice control of the smart device to input voice.

7. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 6, if the recognized number does not match any number preset in the current operation interface, when the user is prompted that the voice input is wrong, it is displayed to the user through video, text or icons, providing the cause of the error or suggestions to help the user correct the error.

8. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 6, after the matching number is identified, the instruction corresponding to the number can be generated and executed immediately to achieve a quick response.

9. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In the Step 5, if the user's voice contains multiple numbers, the first number in the user's voice is extracted, and other numbers and irrelevant voice content are ignored.

10. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: Also included is Step 7: after executing the generated instructions, automatically return to Step 2 so that the user can perform the next operation.

11. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 6, the executed instructions include but are not limited to daily digital operations such as opening applications, adjusting settings, taking photos and recording videos, scanning codes, querying information, and operating applications.

12. The voice interaction method for solving the difficulty of user-computer interaction according to claim 1, characterized in that: In Step 6, after executing the instruction, the smart device provides instant feedback, such as a prompt sound indicating successful operation, a change in screen display, voice feedback or video feedback, so that the user can clearly know the operation result.

13. The video for guiding user operation according to claim 1, characterized in that: The video guiding the user operation supports multiple languages ​​or dialects to meet the language needs of different users. The video content shows in detail how the user uses the smart device to input voice and accurately says any number preset on the current interface to execute the corresponding instruction.

14. The voice interaction method for solving the difficulty of human-computer interaction according to claim 1, characterized in that: Record users' operating habits and preferences, and adjust the content of the video based on the recording results to improve user operation convenience and personalized experience.

15. The voice interaction method for solving the difficulty of human-computer interaction according to claim 1, characterized in that: When the user enters the operation interface for the first time, provide additional videos, texts or icons to help the user understand the correspondence between numbers and instructions and the operation methods.

16. The voice interaction method for solving the difficulty of human-computer interaction according to claim 1, characterized in that: In Step 2, the user enters any operation interface by means of touch, voice command or gesture recognition.

Images