Voice interaction method of learning equipment and learning equipment

Abstract

The embodiment of the invention provides a voice interaction method of learning equipment and the learning equipment, and the method comprises the steps: the learning equipment plays the voice of a first text, and collects the voice to obtain first voice information; the learning device collects second voice information followed by the user for the second time, calls the voice recognition model to recognize the first voice information to obtain the confidence rate of each syllable, forms a first confidence rate vector by the confidence rates of all the syllables, calls the voice recognition model to recognize the second voice information to obtain the confidence rate of each syllable, and sends the confidence rate vector to the user; and forming a second confidence rate vector by the confidence rate of each syllable, calculating an absolute value of an element value of the difference vector, extracting the element values of which the absolute values are greater than a deviation threshold value to obtain x element values, obtaining x syllables corresponding to the x element values, and displaying characters containing the x syllables in the first text as improved content on learning equipment.

Description

Technical Field

[0001] The present application belongs to the field of Internet and voice technology, and specifically relates to a voice interaction method for a learning device and a learning device. Background Art

[0002] Learning equipment, also known as learning machines, is an electronic teaching product, and also refers to all electronic educational equipment that assists learning. The voice follow-up function in learning equipment is currently the most commonly used function, such as English follow-up, Chinese follow-up, etc. However, the existing follow-up function can only provide simple scoring, which cannot meet the user's requirements for voice follow-up improvement. Summary of the invention

[0003] The present application provides a voice interaction method for a learning device and a learning device, which has the function of defining a specific range of a follow-up reading function, thereby meeting the user's requirements for voice follow-up reading improvement and improving the user experience.

[0004] In a first aspect, the present application provides a voice interaction method for a learning device, the method comprising the following steps:

[0005] The learning device voice plays the voice of the first text, and collects the voice to obtain first voice information;

[0006] The learning device collects the second voice information that the user follows for a second time, calls the voice recognition model to recognize the first voice information to obtain the confidence rate of each syllable, and forms a first confidence rate vector with the confidence rate of each syllable, calls the voice recognition model to recognize the second voice information to obtain the confidence rate of each syllable, and forms a second confidence rate vector with the confidence rate of each syllable, and calculates the difference vector between the first confidence rate vector and the second confidence rate vector;

[0007] The learning device determines the user's score based on the difference vector. If the score is lower than the preset score, the absolute value of the element value of the difference vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain x element values, the x syllables corresponding to the x element values ​​are obtained, and the text containing x syllables in the first text is displayed on the learning device as improved content.

[0008] In a second aspect, a learning device is provided, the system comprising:

[0009] The playing and collecting unit is used for playing the voice of the first text, collecting the voice to obtain the first voice information; and collecting the second voice information that the user follows;

[0010] A recognition unit, configured to call a speech recognition model to recognize the first speech information to obtain a confidence rate of each syllable, form a first confidence rate vector with the confidence rate of each syllable, call a speech recognition model to recognize the second speech information to obtain a confidence rate of each syllable, form a second confidence rate vector with the confidence rate of each syllable, and calculate a difference vector between the first confidence rate vector and the second confidence rate vector;

[0011] A scoring prompt unit is used to determine the user's score based on the difference vector. If the score is lower than the preset score, the absolute value of the element value of the difference vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain x element values, the x syllables corresponding to the x element values ​​are obtained, and the text containing x syllables in the first text is displayed on the learning device as improved content.

[0012] In a third aspect, the present application provides a computer storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of the present application.

[0013] The embodiments of the present application have the following beneficial effects:

[0014] The technical solution provided by the present application is that the learning device voice plays the voice of the first text, collects the voice to obtain the first voice information; the learning device collects the second voice information that the user follows for the second time, calls the voice recognition model to recognize the first voice information to obtain the confidence rate of each syllable, and composes the confidence rate of each syllable into a first confidence rate vector, calls the voice recognition model to recognize the second voice information to obtain the confidence rate of each syllable, and composes the confidence rate of each syllable into a second confidence rate vector, and calculates the difference vector between the first confidence rate vector and the second confidence rate vector; the learning device determines the user's score based on the difference vector, and if the score is lower than the preset score, calculates the absolute value of the element value of the difference vector, extracts the element value whose absolute value is greater than the deviation threshold to obtain x element values, obtains x syllables corresponding to the x element values, and displays the text containing x syllables in the first text as improved content on the learning device. In this way, by marking the specific text below a certain score value, the user's next follow-up reading can be reminded to improve, thereby improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1It is a structural diagram of a learning system architecture provided by an embodiment of the present application;

[0017] Figure 2 It is a flowchart of a voice interaction method of a learning device provided in an embodiment of the present application;

[0018] Figure 3 It is a schematic diagram of a learning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, systems, products or devices.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0022] MDT (Multi-Disciplinary Treatment) is a process in which senior experts from multiple disciplines develop personalized diagnosis and treatment plans for patients through joint discussions.

[0023] The following describes the architecture of the MDT system involved in the embodiments of the present application.

[0024] The present application also provides a learning system, specifically comprising: a server 10 and a learning device 20, such as Figure 1As shown, the server 10 is connected to the learning device 20 via a wireless network. The learning device includes at least one processor 11 and a memory 12, and may also include a communication interface 14, a display screen 16 and a bus 13. Among them, the processor 11, the memory 12, the display screen 16 and the communication interface 14 can communicate with each other through the bus 13. The communication interface 14 can transmit information, and the communication interface 14 can have a wireless communication function, and the wireless communication function can be a short-range wireless communication or a long-range communication function (such as LTE or NR mode). The processor 11 can call the logic instructions in the memory 12 to execute or support the method in the embodiment of the present application. The learning device 20 may also include: a microphone and the like.

[0025] In addition, the logic instructions in the memory 12 can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product.

[0026] The memory 12, as a computer-readable storage medium, can be configured to store software programs, computer executable programs, such as program instructions or modules corresponding to the method in the embodiment of the present disclosure. The processor 11 executes functional applications and data processing by running the software programs, instructions or modules stored in the memory 12, that is, implementing or supporting the method in the embodiment of the present application.

[0027] The above-mentioned server 10 can be multiple server devices. Of course, in an optional application scenario, the above-mentioned server 10 can be a server cluster, and the above-mentioned server cluster can be a distributed server or a cloud server, etc. This application does not limit the connection relationship or functional division between servers.

[0028] The above-mentioned learning device may be a learning machine, or a mobile phone device with general functions, etc. The present application does not limit the specific form of the above-mentioned learning device.

[0029] The following describes the main technical application scenarios of the embodiments of this application:

[0030] For learning devices, when users follow along, they do so through voice interaction. Generally, the learning machine reads once, and then the user follows along and rates it. However, the existing ratings are generally only approximate, for example, 3 stars, 5 points, etc., and there is no display of specific areas that need improvement in the follow-up reading. This may cause users to follow along multiple times in one follow-up voice, reducing the user experience.

[0031] The specific methods are introduced in detail below.

[0032] See also Figure 2 , the present application also provides a voice interaction method for a learning device, Figure 2 A flow chart of a voice interaction method for a learning device provided in this application is shown below. The above method is performed, specifically, Figure 2 The method shown can be performed by the server and the learning device in cooperation. Figure 2 As shown, the following steps are included:

[0033] Step S201: The learning device plays the voice of the first text and collects the voice to obtain first voice information;

[0034] The first text may be in Chinese, English, Japanese, etc. This application does not limit the specific language of the first text. It may even be a text corresponding to a local dialect such as Cantonese or Shanghainese.

[0035] Step S202: the learning device collects the second voice information that the user follows for a second time, calls the voice recognition model to recognize the first voice information to obtain the confidence rate of each syllable, and forms a first confidence rate vector with the confidence rate of each syllable; calls the voice recognition model to recognize the second voice information to obtain the confidence rate of each syllable, and forms a second confidence rate vector with the confidence rate of each syllable; and calculates a difference vector between the first confidence rate vector and the second confidence rate vector;

[0036] The above-mentioned speech recognition model may be a general speech recognition model, such as a neural network model, or an LSTM model, etc. The present application does not limit the specific expression form of the above-mentioned speech recognition model.

[0037] The confidence rate of each syllable is the confidence rate of the characters in the first text containing the syllable, not the maximum confidence rate of each syllable. For example, wo (I), because the user's pronunciation may not be accurate, the confidence rate of other syllables may be higher than the standard syllable. Since the solution of this application is to follow the reading, its syllables are certain.

[0038] Step S203, the learning device determines the user's score based on the difference vector. If the score is lower than the preset score, the absolute value of the element value of the difference vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain x element values, and the x syllables corresponding to the x element values ​​are obtained, and the text containing x syllables in the first text is displayed on the learning device as improved content.

[0039] The above x is an integer greater than or equal to 1.

[0040] The technical solution provided by the present application is that the learning device voice plays the voice of the first text, collects the voice to obtain the first voice information; the learning device collects the second voice information that the user follows for the second time, calls the voice recognition model to recognize the first voice information to obtain the confidence rate of each syllable, and composes the confidence rate of each syllable into a first confidence rate vector, calls the voice recognition model to recognize the second voice information to obtain the confidence rate of each syllable, and composes the confidence rate of each syllable into a second confidence rate vector, and calculates the difference vector between the first confidence rate vector and the second confidence rate vector; the learning device determines the user's score based on the difference vector, and if the score is lower than the preset score, calculates the absolute value of the element value of the difference vector, extracts the element value whose absolute value is greater than the deviation threshold to obtain x element values, obtains x syllables corresponding to the x element values, and displays the text containing x syllables in the first text as improved content on the learning device. In this way, by marking the specific text below a certain score value, the user's next follow-up reading can be reminded to improve, thereby improving the user experience.

[0041] In an optional technical scenario, the above method may further include:

[0042] If there are identical syllables among the x syllables, count the number of identical syllables and arrange them in descending order to obtain a first sequence. According to the order of the first sequence, assign corresponding syllables with reminder levels from high to low, and focus on reminding the text corresponding to the syllables with high reminder levels.

[0043] The above-mentioned key reminders include but are not limited to: highlighting, flashing reminders or severe reminders, etc.

[0044] For syllables with a relatively high error rate, it is necessary to emphasize the corresponding characters and then correct the user's pronunciation.

[0045] In an optional technical scenario, the above method may further include:

[0046] The learning device extracts the number x1 of the syllable i ranked first in the first sequence, and if x1>error threshold, the pronunciation tutorial of the above syllable i is displayed on the learning device.

[0047] By analyzing the error rate statistics, users can be trained in a targeted manner.

[0048] In an optional technical scenario, the learning device may determine the user's score based on the difference vector by:

[0049] The first total deviation value is obtained by calculating the sum of the absolute values ​​of all element values ​​in the difference vector, and the first interval corresponding to the first total deviation value is determined based on the preset mapping relationship between the total deviation value and the interval, and the first score corresponding to the first interval is determined based on the mapping relationship between the interval and the score.

[0050] In an optional technical scenario, the above method may further include, after step S202:

[0051] Calling another speech recognition model to recognize the first speech information to obtain the confidence rate of each syllable, forming a third confidence rate vector with the confidence rate of each syllable, calling another speech recognition model to recognize the second speech information to obtain the confidence rate of each syllable, forming a fourth confidence rate vector with the confidence rate of each syllable, calculating another difference vector between the third confidence rate vector and the fourth confidence rate vector, and calculating the average value of the difference vector and the other difference vector to obtain an average value vector;

[0052] The learning device determines the user's score based on the average value vector. If the score is lower than the preset score, the absolute value of the element value of the average value vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain y element values, and the y syllables corresponding to the y element values ​​are obtained, and the text containing y syllables in the first text is displayed on the learning device as improved content.

[0053] See also Figure 3 , Figure 3 A learning device is provided, the learning device comprising:

[0054] The playing and collecting unit 301 is used for playing the voice of the first text, collecting the voice to obtain the first voice information; and collecting the second voice information of the user following the reading;

[0055] The recognition unit 302 is used to call the speech recognition model to recognize the first speech information to obtain the confidence rate of each syllable, form a first confidence rate vector with the confidence rate of each syllable, call the speech recognition model to recognize the second speech information to obtain the confidence rate of each syllable, form a second confidence rate vector with the confidence rate of each syllable, and calculate the difference vector between the first confidence rate vector and the second confidence rate vector;

[0056] The scoring prompt unit 303 is used to determine the user's score based on the difference vector. If the score is lower than the preset score, the absolute value of the element value of the difference vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain x element values, and the x syllables corresponding to the x element values ​​are obtained, and the text containing x syllables in the first text is displayed on the learning device as improved content.

[0057] Optionally, the scoring prompt unit is also used to count the number of identical syllables among the x syllables, arrange them in descending order according to the same number to obtain a first sequence, assign corresponding syllables with reminder levels from high to low according to the order of the first sequence, and focus on reminding the text corresponding to the syllables with high reminder levels.

[0058] Optional,

[0059] The scoring prompt unit is also used to extract the number x1 of the syllable i ranked first in the first sequence, and if x1>error threshold, the pronunciation tutorial of the above syllable i is displayed on the learning device.

[0060] Optionally, the scoring prompt unit is also used to calculate the sum of the absolute values ​​of all element values ​​in the difference vector to obtain a first total deviation value, determine the first interval corresponding to the first total deviation value based on a preset mapping relationship between the total deviation value and the interval, and determine the first score corresponding to the first interval based on a mapping relationship between the interval and the score.

[0061] Optionally, the recognition unit is further used to call another speech recognition model to recognize the first speech information to obtain the confidence rate of each syllable, form a third confidence rate vector with the confidence rate of each syllable, call another speech recognition model to recognize the second speech information to obtain the confidence rate of each syllable, form a fourth confidence rate vector with the confidence rate of each syllable, calculate another difference vector between the third confidence rate vector and the fourth confidence rate vector, and calculate the average value of the difference vector and the other difference vector to obtain an average value vector;

[0062] The scoring prompt unit is also used to determine the user's score based on the average value vector. If the score is lower than the preset score, the absolute value of the element value of the average value vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain y element values, and the y syllables corresponding to the y element values ​​are obtained, and the text containing y syllables in the first text is displayed on the learning device as improved content.

[0063] The embodiment of the present application can divide the electronic device into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0064] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0065] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0066] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0067] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0068] In the several embodiments provided in the present application, it should be understood that the disclosed methods, devices and systems can be implemented in other ways. For example, the device embodiments described above are merely schematic; for example, the division of the units is only a logical function division, and there may be other division methods in actual implementation; for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0069] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0070] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0071] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a volatile memory or a non-volatile memory. Among them, the non-volatile memory can 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 can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM) and direct RAM bus RAM (DR RAM). Various media that can store program code are available.

[0072] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A voice interaction method for a learning device, characterized in that: The method comprises the following steps: The learning device voice plays the voice of the first text, and collects the voice to obtain first voice information; The learning device collects the second voice information that the user follows for a second time, calls the voice recognition model to recognize the first voice information to obtain the confidence rate of each syllable, and forms a first confidence rate vector with the confidence rate of each syllable, calls the voice recognition model to recognize the second voice information to obtain the confidence rate of each syllable, and forms a second confidence rate vector with the confidence rate of each syllable, and calculates the difference vector between the first confidence rate vector and the second confidence rate vector; The learning device determines the user's score based on the difference vector. If the score is lower than the preset score, the absolute value of the element value of the difference vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain x element values, the x syllables corresponding to the x element values ​​are obtained, and the text containing x syllables in the first text is displayed on the learning device as improved content.

2. The method according to claim 1, characterized in that The method further comprises: If there are identical syllables among the x syllables, count the number of identical syllables and arrange them in descending order to obtain a first sequence. According to the order of the first sequence, assign corresponding syllables with reminder levels from high to low, and focus on reminding the text corresponding to the syllables with high reminder levels.

3. The method according to claim 2, characterized in that The method further comprises: The learning device extracts the number x1 of the syllable i ranked first in the first sequence, and if x1>error threshold, the pronunciation tutorial of the above syllable i is displayed on the learning device.

4. The method according to claim 1, characterized in that: The learning device determines the user's score according to the difference vector specifically including: The first total deviation value is obtained by calculating the sum of the absolute values ​​of all element values ​​in the difference vector, and the first interval corresponding to the first total deviation value is determined based on the preset mapping relationship between the total deviation value and the interval, and the first score corresponding to the first interval is determined based on the mapping relationship between the interval and the score.

5. The method according to claim 1, characterized in that The method further comprises: Calling another speech recognition model to recognize the first speech information to obtain the confidence rate of each syllable, forming a third confidence rate vector with the confidence rate of each syllable, calling another speech recognition model to recognize the second speech information to obtain the confidence rate of each syllable, forming a fourth confidence rate vector with the confidence rate of each syllable, calculating another difference vector between the third confidence rate vector and the fourth confidence rate vector, and calculating the average value of the difference vector and the other difference vector to obtain an average value vector; The learning device determines the user's score based on the average value vector. If the score is lower than the preset score, the absolute value of the element value of the average value vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain y element values, and the y syllables corresponding to the y element values ​​are obtained, and the text containing y syllables in the first text is displayed on the learning device as improved content.

6. A learning device, characterized in that: The learning device comprises: The playing and collecting unit is used for playing the voice of the first text, collecting the voice to obtain the first voice information; and collecting the second voice information that the user follows; A recognition unit, configured to call a speech recognition model to recognize the first speech information to obtain a confidence rate of each syllable, form a first confidence rate vector with the confidence rate of each syllable, call a speech recognition model to recognize the second speech information to obtain a confidence rate of each syllable, form a second confidence rate vector with the confidence rate of each syllable, and calculate a difference vector between the first confidence rate vector and the second confidence rate vector; A scoring prompt unit is used to determine the user's score based on the difference vector. If the score is lower than the preset score, the absolute value of the element value of the difference vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain x element values, the x syllables corresponding to the x element values ​​are obtained, and the text containing x syllables in the first text is displayed on the learning device as improved content.

7. The learning device according to claim 6, characterized in that The scoring prompt unit is also used to count the number of identical syllables among the x syllables, arrange them in descending order according to the same number to obtain a first sequence, assign corresponding syllables with reminder levels from high to low according to the order of the first sequence, and focus on reminding the text corresponding to the syllables with high reminder levels.

8. The learning device according to claim 7, characterized in that The scoring prompt unit is also used to extract the number x1 of the syllable i ranked first in the first sequence, and if x1>error threshold, the pronunciation tutorial of the above syllable i is displayed on the learning device.

9. The learning device according to claim 6, characterized in that The scoring prompt unit is also used to calculate the sum of the absolute values ​​of all element values ​​in the difference vector to obtain a first total deviation value, determine the first interval corresponding to the first total deviation value based on a preset mapping relationship between the total deviation value and the interval, and determine the first score corresponding to the first interval based on a mapping relationship between the interval and the score.

10. The learning device according to claim 6, characterized in that The recognition unit is further used to call another speech recognition model to recognize the first speech information to obtain the confidence rate of each syllable, form a third confidence rate vector with the confidence rate of each syllable, call another speech recognition model to recognize the second speech information to obtain the confidence rate of each syllable, form a fourth confidence rate vector with the confidence rate of each syllable, calculate another difference vector between the third confidence rate vector and the fourth confidence rate vector, and calculate the average value of the difference vector and the other difference vector to obtain an average value vector; The scoring prompt unit is also used to determine the user's score based on the average value vector. If the score is lower than the preset score, the absolute value of the element value of the average value vector is calculated, the element value whose absolute value is greater than the deviation threshold is extracted to obtain y element values, and the y syllables corresponding to the y element values ​​are obtained, and the text containing y syllables in the first text is displayed on the learning device as improved content.

Images