Method for voice-controlled switching of front-end tabs based on transfer learning

Abstract

The present invention relates to a method for implementing voice-controlled switching of front-end tabs based on transfer learning. The verification test results of the model of the method for implementing voice-controlled switching of front-end tabs based on transfer learning of the present invention show that, based on the comparison of similar products, the present invention uses voice control technology to implement the front-end tab switching operation through a transfer learning method, so that the user does not need to be next to a computer or other equipment, and can directly control the page switching through voice commands, which is convenient for users to use, improves the freedom of using the front-end tabs, improves the work efficiency of some scenarios, and enriches the user experience.

Description

Technical Field

[0001] The present invention belongs to the field of computer technology and relates to a method for realizing voice-controlled switching of front-end tabs based on transfer learning in computer technology. Background Art

[0002] With the rapid development of the Internet and computer technology, various electronic products are applied to people's lives, work and study, such as multimedia teaching, company PPT presentations, e-books, etc. However, the current front-end tab switching scheme is mainly through clicking the mouse to switch the sub-page tab, touching the sub-page tab with a finger or touch device, triggering the page switch with a keyboard key, setting a timed automatic switch, etc. The existing technical means require the use of tangible input devices and direct contact to achieve tab switching. If the timing and other logical controls are used to switch tabs, it is not smart. In some scenarios, such as speeches in large venues, someone needs to be next to the device to control the switching of pages, and the degree of freedom is relatively small. Summary of the invention

[0003] One aspect of the present invention relates to a method for implementing voice-controlled switching of front-end tabs based on transfer learning. In embodiments of these methods, the method comprises the following steps:

[0004] A) receiving the voice control switch on command sent by the application client to the application server; opening the tag name and the URL corresponding to it;

[0005] B) receiving a voice command sent by a voice receiving device to the application client; recognizing the voice command and converting it into a correct label name;

[0006] C) matching the correct label name with the transfer learning training result data to generate a label name that matches successfully;

[0007] D) Find the opened tag name corresponding to the successfully matched tag name and the URL corresponding thereto and select them;

[0008] Sending a triggering URL command for the selected tag name and its corresponding URL to the application server;

[0009] E) the application server receives the triggering tag name and the URL instruction corresponding to the selected tag and sends it to the application client;

[0010] F) The application client receives the triggering instruction for the selected tag name and the URL corresponding thereto; the application executes tag switching based on the selected tag name and the URL corresponding thereto.

[0011] On the other hand, the present invention also relates to a device for implementing voice-controlled switching of front-end tabs based on transfer learning, comprising at least one processor and a memory storing instructions. When the instructions are executed by at least one processor, the steps of any of the methods described above are implemented.

[0012] The beneficial effect of the present invention is that a method for implementing voice-controlled switching of front-end tabs based on transfer learning is provided. The verification test results of the model of the method for implementing voice-controlled switching of front-end tabs based on transfer learning of the present invention show that, based on the comparison of similar products, the present invention uses voice control technology to implement the front-end tab switching operation through a transfer learning method, so that the user does not need to be next to a computer or other equipment, and can directly control the page switching through voice commands, which is convenient for users to use, improves the freedom of using the front-end tabs, improves the work efficiency of some scenarios, and enriches the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 Schematic diagram of the method for implementing voice-controlled switching of front-end tabs based on transfer learning;

[0014] Figure 2 A method for implementing voice-controlled switching of front-end tabs based on transfer learning to prepare a logical diagram;

[0015] Figure 3 Hardware device structure and function relationship diagram. DETAILED DESCRIPTION

[0016] The technical features of different embodiments of the present invention may be arbitrarily combined in accordance with the spirit of the present invention. Therefore, any specific embodiment should not be construed as limiting the protection scope of the present invention.

[0017] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the following steps are included:

[0018] A) receiving the voice control switch on command sent by the application client to the application server; opening the tag name and the URL corresponding to it;

[0019] B) receiving a voice command sent by a voice receiving device to the application client; recognizing the voice command and converting it into a correct label name;

[0020] C) matching the correct label name with the transfer learning training result data to generate a label name that matches successfully;

[0021] D) Find the opened tag name corresponding to the successfully matched tag name and the URL corresponding thereto and select them;

[0022] Sending a triggering URL command for the selected tag name and its corresponding URL to the application server;

[0023] E) the application server receives the triggering tag name and the URL instruction corresponding to the selected tag and sends it to the application client;

[0024] F) The application client receives the triggering instruction for the selected tag name and the URL corresponding thereto; the application executes tag switching based on the selected tag name and the URL corresponding thereto.

[0025] In terms of terminology, "URL" generally refers to the Uniform Resource Locator, such as the address of a file or image in a computer program;

[0026] In terms of terminology, "transfer learning" is a machine learning method that uses a model developed for task A as a starting point to reuse it in the process of developing a model for task B.

[0027] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the opened tab name and the corresponding URL are the tab name and the corresponding URL of the application that the application client is about to use, which are received and sent from the application server.

[0028] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the transfer learning training result data is obtained by collecting voice training data generated by a database through one or more channels such as browser downloads and imports from other devices, and then training by a transfer learner calling a training method.

[0029] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, an instance of a transfer learner is created using speech training data through the collectExample method of speechcommand, and the instance of the transfer learner is used to perform method calls for all subsequent processes.

[0030] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the transfer learner includes one or more of the following functions:

[0031] Creating a training button in the transfer learner, clicking the training button to call the train method to train the speech training data multiple times;

[0032] Create an open listening button in the transfer learner to call the listen method to listen to the opened tag name and the URL corresponding to the voice command sent by the voice receiving device connected to the application client;

[0033] Create a close listening button in the transfer learner and call the stopListening method to close the listening.

[0034] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the voice training data range includes one or more names of labels and buttons; the voice training data is stored in a wma format with a relatively good compression ratio and sound quality;

[0035] The transfer learning training result data is saved in a binary file, and then the content in the binary file is converted into a JavaScript Array Buffer type and loaded into the transfer learner.

[0036] In terms of terminology, "WMA format" is a new audio format launched by Microsoft that is as famous as the MP3 format.

[0037] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, after the application client receives the instruction that triggers the selected tag name and the corresponding URL, the application calls the corresponding event processing function based on the selected tag name and the corresponding URL instruction to perform the selection interaction, and can switch pages or perform other actions as the tag is selected.

[0038] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the application client is connected to the application server via the Internet, and the application client is connected to the receiving device via a wired connection; the application server is connected to the switching server via a wired or wireless connection.

[0039] In some embodiments of the method for implementing voice-controlled switching of front-end tabs based on transfer learning, the application client includes an instruction receiving unit and one or more structures in a voice-controlled switch; the application is loaded and used at the application client;

[0040] The switching server includes one or more modules of a voice receiving module, a voice analyzing module, and a voice processing module.

[0041] The present invention will be further described below by more specific embodiments:

[0042] refer to Figure 1 As shown, a logical schematic diagram of a method for implementing voice-controlled switching of front-end tabs based on transfer learning in this embodiment is shown; wherein, the following steps are included:

[0043] A) receiving the voice control switch on command sent by the application client to the application server; opening the tag name and the URL corresponding to it;

[0044] B) receiving a voice command sent by a voice receiving device to the application client; recognizing the voice command and converting it into a correct label name;

[0045] C) matching the correct label name with the transfer learning training result data to generate a label name that matches successfully;

[0046] D) Find the opened tag name corresponding to the successfully matched tag name and the URL corresponding thereto and select them;

[0047] Sending a triggering URL command for the selected tag name and its corresponding URL to the application server;

[0048] E) the application server receives the triggering tag name and the URL instruction corresponding to the selected tag and sends it to the application client;

[0049] F) The application client receives the triggering instruction for the selected tag name and the URL corresponding thereto; the application executes tag switching based on the selected tag name and the URL corresponding thereto.

[0050] refer to Figure 2 As shown, the method for implementing voice-controlled switching of front-end tabs based on transfer learning in this embodiment is a logical schematic diagram of preparation work; wherein: it includes the following steps:

[0051] S2.1) receiving the speech training data imported by the collection device; calling the train method in the transfer training algorithm to train the speech training data multiple times to generate the transfer learning training result data;

[0052] S2.2) receiving a tag switching request sent by the application server; sending a collection tag name and a URL instruction corresponding to the tag name to the application server;

[0053] S2.3) After receiving the instruction to collect the tag name and the URL corresponding to the tag name, the application server collects the tag name and the corresponding URL of the application that the application client is about to use;

[0054] S2.4) The application client receives the tag name and corresponding URL of the application program to be used sent by the application server.

[0055] refer to Figure 3 As shown, the hardware device structure function relationship diagram of this embodiment; wherein the function relationship between the structures is:

[0056] S1.1) The voice processing unit receives a voice control switch turn-on instruction sent by the voice control switch in the application client;

[0057] S1.2) The voice receiving module receives the voice command sent by the voice receiving device connected to the application client; the voice receiving module sends the voice command to the voice analysis module;

[0058] S1.3) The voice analysis module recognizes the voice data from the voice command sent by the voice receiving module and converts it into a correct label name;

[0059] Sending the correct tag name to the speech processing unit;

[0060] S1.4) The speech processing unit matches the correct label name sent from the speech analysis module with the transfer learning training result data;

[0061] S1.5) Find the opened tag name and the URL corresponding to the successfully matched tag name in the transfer learner and select them;

[0062] S1.6) The voice processing unit sends a trigger instruction to the instruction receiving unit of the application client;

[0063] S1.7) The front-end page application of the application client performs front-end page tag switching based on the opened selected tag name corresponding to the successfully matched tag name and the URL corresponding thereto;

[0064] S1.8) The voice processing unit receives a voice control switch turn-off instruction sent by the voice control switch in the application client.

[0065] The implementation and functional operations of the subject matter described in this specification may be implemented in: digital electronic circuitry, tangibly implemented computer software or firmware, computer hardware, including the structures disclosed in this specification and their structural equivalents, or a combination of more than one of the above. The implementation of the subject matter described in this specification may be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on one or more tangible non-transitory program carriers, for execution by a data processing device or to control the operation of a data processing device.

[0066] A computer program (which may also be referred to or described as a program, software, software application, module, software module, script or code) may be written in any form of programming language, including compiled or interpreted languages ​​or declarative or procedural languages, and the computer program may be deployed in any form, including as a stand-alone program or as a module, component, subroutine or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program may be stored in a portion of a file that stores other programs or data, for example, one or more scripts stored in the following: in a markup language document; in a single file dedicated to a related program; or in multiple collaborative files, for example, files storing one or more modules, subroutines or code portions. A computer program may be deployed to execute on one or more computers, the computers being located in one place or distributed to multiple locations and interconnected by a communication network.

[0067] The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform functions by operating on input data and generating output.

[0068] The embodiments of the subject matter described in this specification can be implemented in a computing system, which includes a back-end component such as a data server, or includes an intermediate component such as an application server, or includes a front-end component such as a client computer, which has a graphical user interface or a web browser, and a user can interact with the implementation of the subject matter described in this specification through a graphical user interface or a web browser, or the computer system includes any combination of one or more such back-end components, intermediate components or front-end components. The components in the system can be interconnected by digital data communication of any form or medium such as a communication network. Examples of communication networks include local area networks ("LANs") and wide area networks ("WANs"), for example, the Internet. The computing system can include a client and a server. The client and the server are usually far away from each other and usually interact through a communication network. The relationship between the client and the server is generated using a computer program that runs on each computer and has a client-server relationship between each other.

[0069] Although this specification contains many specific implementation details, these should not be interpreted as limitations on the scope of any invention or the scope of what can be claimed, but rather as an illustration of features that can concretize a particular embodiment of a particular invention. The specific features described in this specification in the context of independent embodiments can also be implemented in combination with a single embodiment. Conversely, the various features described in the context of a single embodiment can also be implemented independently in multiple embodiments, or in any suitable sub-combination. In addition, although the features can be described above as a combination effect and even initially required, one or more features from the required combination can be removed from the combination in some cases, and the required combination can be turned to a sub-combination or a variation of the sub-combination.

[0070] Similarly, although operations are described in the accompanying drawings in a particular order, it should not be understood that: in order to achieve the desired results, such operations are required to be performed in the particular order shown or in a sequential order, or that all illustrated operations are performed. In certain cases, multitasking and parallel processing can be advantageous. In addition, the separation of various system modules and components in the above-mentioned embodiments should not be understood as requiring such separation in all embodiments, and it should be understood that program components and systems can generally be integrated into a single software product or packaged into multiple software products.

[0071] Specific implementations of the subject matter have been described. Other implementations are within the scope of the following claims. For example, the activities recited in the claims can be performed in a different order and still achieve the desired results. As an example, the processes described in the accompanying drawings do not necessarily require the specific order or sequential order shown in order to achieve the desired results. In certain implementations, multitasking and parallel processing may be advantageous.

Claims

1. A method for implementing voice-controlled switching of front-end tabs based on transfer learning, wherein the front-end tab includes multiple tabs, characterized in that , including the following steps: A) receiving the voice control switch on command sent by the application client to the application server; opening the tag name and the URL corresponding to it; B) receiving a voice command sent from a voice receiving device to the application client; recognizing and converting the voice command into a correct label name; the application client is connected to the voice receiving device via a wired connection; C) matching the correct label name with the transfer learning training result data to generate a successfully matched label name; D) Find the opened tag name corresponding to the successfully matched tag name and the URL corresponding thereto and select them; Sending a triggering URL command for the selected tag name and its corresponding URL to the application server; E) the application server receives the triggering tag name and the URL instruction corresponding to the selected tag and sends it to the application client; F) the application client receives the triggering of the selected tag name and the URL instruction corresponding thereto; the application executes tag switching based on the selected tag name and the URL instruction corresponding thereto; In step C), the transfer learning training result data is obtained by training the speech training data generated by the database through one or more channels, such as downloading from a browser or importing from other devices, by the transfer learner calling the training method; the transfer learning training result data is saved in a binary file, and then the content in the binary file is converted into a JavaScript Array Buffer type and loaded into the transfer learner; Creating a training button in the transfer learner, and clicking the training button to call a training method to train the speech training data multiple times; Create an open monitoring button in the transfer learner to call a monitoring method to monitor the opened tag name and the URL corresponding to the voice command sent by the voice receiving device connected to the application client; Create a close monitoring button in the transfer learner to call a close monitoring method; In step A), the opened tag name and the corresponding URL are the tag name and the corresponding URL of the application to be used by the application client received from the application server; The functional relationship between the structures based on steps A) to E) is as follows: S1.1) The voice processing unit receives a voice control switch turn-on instruction sent by the voice control switch in the application client; S1.2) The voice receiving module receives the voice command sent by the voice receiving device connected to the application client; the voice receiving module sends the voice command to the voice analysis module; S1.3) The voice analysis module recognizes the voice data from the voice command sent by the voice receiving module and converts it into a correct label name; Sending the correct tag name to the speech processing unit; S1.4) The speech processing unit matches the correct label name sent from the speech analysis module with the transfer learning training result data; S1.5) Find the opened tag name and the URL corresponding to the successfully matched tag name in the transfer learner and select them; S1.6) The voice processing unit sends a trigger instruction to the instruction receiving unit of the application client; S1.7) The front-end page application program of the application client performs front-end page tag switching based on the opened selected tag name corresponding to the successfully matched tag name and the URL corresponding thereto; S1.8) The voice processing unit receives a voice control switch off instruction sent by the voice control switch in the application client.

2. According to claim 1, a method for implementing voice-controlled switching of front-end tabs based on transfer learning is characterized in that: The voice training data range includes one or several names of labels and buttons; the voice training data is stored in wma format.

3. According to claim 1, a method for implementing voice-controlled switching of front-end tabs based on transfer learning is characterized in that , the application client is connected to the application server via the Internet; the application server is connected to the switching server via wired or wireless means.

4. According to claim 3, a method for implementing voice-controlled switching of front-end tabs based on transfer learning is characterized in that ,The application client includes a command receiving unit and one or more structures in the voice controlled switch; ,the application is loaded and used at the application client; The switching server includes one or more modules of a voice receiving module, a voice analyzing module, and a voice processing module.

5. A device for implementing voice-controlled switching of front-end tabs based on transfer learning, comprising at least one processor; and a memory storing instructions, which, when executed by at least one processor, implements the method described in any one of claims 1-4.

Images