Student speech skills training method and system based on virtual reality scene

Abstract

The present invention discloses a student speech skill training method and system based on a virtual reality scene, and relates to the field of intelligent learning technology. The method includes: real-time acquisition of the body coordinate information and voice information of the current student in the process of giving a speech based on a virtual reality scene; the coordinate information is the coordinate information of the current student in the preset coordinate system of the virtual reality scene; according to the body coordinate information of the current student, the gesture state of the current student is obtained; according to the gesture state and voice information of the current student, the speech normative mark value of the current student is calculated; according to the speech normative mark value of the current student, whether the current student has any irregular situation in the speech process and the judgment result is sent to the preset monitoring device. The present invention can effectively reduce the time cost of teacher guidance and improve the teaching quality and effect.

Description

Technical Field

[0001] The present invention relates to the field of intelligent learning technology, and in particular to a student speech skill training method and system based on a virtual reality scene. Background Art

[0002] Public speaking ability is a reflection of one's comprehensive qualities such as eloquence, knowledge, and courage. In the current situation of advocating quality-oriented education, many Chinese teachers have tried this effective practical activity, which can stimulate students' strong sense of self-expression, expand their extracurricular knowledge, integrate listening, speaking, reading and writing training, improve students' ability to comprehensively use Chinese knowledge, and lay a good foundation for students to enter the workplace in the future.

[0003] In order to improve students' speaking ability, the current method mainly adopts teacher comments + a lot of on-stage practice. Students give speeches on stage many times, and teachers constantly correct the irregularities in students' speeches, so as to achieve the purpose of improving students' speaking ability. However, this method is purely offline training, and teachers need to spend a lot of time to guide students. The time cost is high and the dependence on manual work is strong. In addition, the speech training environment is not real enough, and students lack interactive experience, resulting in poor teaching effect. Summary of the invention

[0004] The present invention provides a student speech skill training method based on a virtual reality scene, which is used to solve the problems that the existing student speech skill training method has strong artificial dependence, high teaching time cost and poor effect. The present invention provides a student speech skill training method and system based on a virtual reality scene, which can enable students to realize speech skill training through electronic devices in a virtual reality scene, effectively reducing the time cost of teacher guidance and having a high degree of intelligence.

[0005] In a first aspect, the present invention provides a method for training student speech skills based on a virtual reality scene, comprising:

[0006] Real-time collection of body coordinate information and voice information of the current student during a speech in a virtual reality scene; the coordinate information is the coordinate information of the current student in a preset coordinate system of the virtual reality scene;

[0007] According to the body coordinate information of the current student, obtain the gesture status of the current student;

[0008] Calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student;

[0009] According to the speech normativeness flag value of the current student, it is determined whether the current student has any irregularities during the speech and the determination result is sent to a preset monitoring device.

[0010] In an optional embodiment, the gesture state includes a primary gesture state;

[0011] The step of obtaining the gesture state of the current student according to the body coordinate information of the current student includes:

[0012] According to the hand coordinate information of the current student, calculate the first-level gesture state flag value of the current student;

[0013] Determine whether the first-level gesture state flag value of the current student is not less than a preset value;

[0014] If the first-level gesture state flag value of the current student is not less than the preset value, it is determined that the first-level gesture state of the current student is a non-fist-clenching state;

[0015] If the first-level gesture state flag value of the current student is less than a preset value, it is determined that the first-level gesture state of the current student is a fisting state.

[0016] In an optional embodiment, the calculating of the primary gesture state flag value of the current student according to the hand coordinate information of the current student includes:

[0017] The first level gesture state flag value of the current student is calculated according to the following first formula:

[0018]

[0019] In the first formula, δ represents the primary gesture state flag value of the current student; (X t ,Y t ,Z t ) represents the coordinate of the tth finger of the current student, and its value is 1, 2, 3, 4, 5; (X 3 ,Y 3 ,Z 3 ) represents the coordinates of the middle finger of the current student; (X i ,Y i ,Z i ) represents the palm coordinates of the current student.

[0020] In an optional embodiment, the gesture state further includes: a secondary gesture state subordinate to the primary gesture state;

[0021] After determining that the primary gesture state of the current student is a non-fisting state, the method further includes:

[0022] According to the second formula, the secondary gesture state mark matrix of the current student in the non-fist-clenching state is calculated;

[0023] Determine the secondary gesture state of the current student in the non-clenched fist state according to the secondary gesture state flag matrix of the current student in the non-clenched fist state and a predetermined judgment strategy;

[0024] Wherein, the second formula is:

[0025] λ={γ(Z 0 >0),γ(Z i >Z j )}

[0026] In the second formula, λ represents the secondary gesture state flag matrix of the current student in the non-clenched fist state; γ() represents the judgment function, if the formula in the brackets is true, the function value is 1, if the formula in the brackets is false, the function value is 0; Z 0 Represents the coordinate value of the Z-axis coordinate in the unit normal vector of the current student's palm, Z j Represents the Z-axis coordinate value of the current student's shoulder.

[0027] In an optional embodiment, the predetermined judgment strategy is:

[0028] If λ={0,0}, it is determined that the current secondary gesture state of the student in the non-fist state is that the palm is facing up and the palm is below the shoulder;

[0029] If λ = {0,1}, then the secondary gesture state of the current student in the non-fist state is determined to be that the palm is facing up and the palm is higher than the shoulder;

[0030] If λ={1,0}, it is determined that the current secondary gesture state of the student in the non-fist state is that the palm is facing down and the palm is lower than the shoulder;

[0031] If λ={1,1}, it is determined that the secondary gesture state of the current student in the non-fist-clenching state is that the palm is facing down and the palm is higher than the shoulder.

[0032] In an optional embodiment, the calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student includes:

[0033] Acquire multiple emotional states corresponding to the gesture state of the current student to obtain a first emotional state number array; perform semantic analysis on the voice information of the current student, acquire the emotional state corresponding to the semantics obtained by the analysis, and obtain a second emotional state number array; wherein each emotional state has a one-to-one correspondence with the number;

[0034] The standardization mark value of the current student's speech is calculated according to the third formula:

[0035]

[0036] In the third formula, P represents the standardization mark value of the current student's speech; S a represents the ath emotional state number value in the first emotional state number array; Y b represents the bth emotional state number value in the second emotional state number array; n is the number of elements in the first emotional state number array, and m is the number of elements in the second emotional state number array.

[0037] In an optional embodiment, judging whether the current student has any irregularities in the speech process according to the speech normativeness flag value of the current student includes:

[0038] Determine whether the current student's speech normativeness mark value is equal to a preset normative threshold;

[0039] If the standardization flag value of the current student's speech is equal to the preset standard threshold, it is determined that the current student has not made any irregularities in the speech, and a first prompt message is issued;

[0040] If the standardization flag value of the current student's speech is not equal to the preset standard threshold, it is determined that the current student has made irregularities in the speech and a second prompt message is issued.

[0041] In an optional embodiment, the preset standard threshold is 0.

[0042] In an optional embodiment, the issuing of the first prompt information includes: controlling a preset prompt light to display a first preset color; and the issuing of the second prompt information includes: controlling a preset prompt light to display a second preset color.

[0043] In a second aspect, the student speech skills training system based on virtual reality scene provided by the present invention is characterized by comprising:

[0044] Acquisition module: used for real-time acquisition of body coordinate information and voice information of the current student during the speech in the virtual reality scene; the coordinate information is the coordinate information of the current student in the preset coordinate system of the virtual reality scene;

[0045] The gesture state acquisition module is used to obtain the gesture state of the current student according to the body coordinate information of the current student;

[0046] A speech normativeness mark value calculation module, used for calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student;

[0047] The judgment and display module is used to judge whether the current student has any irregularities in the speech process according to the speech normativeness mark value of the current student and send the judgment result to the preset monitoring device.

[0048] The student speech skill training program based on virtual reality scene provided by the present invention first obtains the student's gesture state according to the body coordinates of the student in the virtual reality speech scene collected in real time, then calculates the student's speech standardization mark value according to the gesture state and the collected student voice information, and finally judges whether the current student has any irregularities in the speech process according to the speech standardization mark value and provides the judgment result to the user. The present invention provides students with a virtual reality speech environment, and reminds students of irregularities in the speech process in real time. Since it is separated from manual work, it can effectively reduce the time cost of teacher guidance and has a high degree of intelligence.

[0049] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0050] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 Flow chart of a method for training student speech skills based on a virtual reality scene in an embodiment of the present invention;

[0053] Figure 2 is a flow chart of an implementation method of S102;

[0054] Figure 3 Schematic diagram of the structure of a student speech skills training system based on a virtual reality scenario in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0056] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Before the method provided by the present invention is implemented, a speech training scene based on virtual reality technology is first established. For example, students can enter a virtual reality-based speech scene through a client based on virtual reality technology to give a speech. The virtual reality-based speech scene can enable users to have an immersive speech experience.

[0058] Figure 1 Flow chart of the method for training student speech skills based on virtual reality scene in an embodiment of the present invention. Figure 1 The method comprises the following steps S101-S104:

[0059] S101: Real-time collection of body coordinate information and voice information of the current student during a speech in a virtual reality scene;

[0060] The coordinate information is the coordinate information of the current student in the preset coordinate system of the virtual reality scene, that is, the coordinates described in this embodiment all refer to the coordinates in the preset coordinate system of the virtual reality scene.

[0061] S102: Obtaining the gesture state of the current student according to the body coordinate information of the current student.

[0062] The body coordinate information of the current student includes the hand coordinate information of the current student.

[0063] In an optional embodiment, the gesture state includes a primary gesture state. The primary gesture state includes a fist-clenching state and a non-fist-clenching state. Figure 2 The step S102 may include the following steps S201-S204:

[0064] S201: Calculate the primary gesture state flag value of the current student according to the hand coordinate information of the current student.

[0065] Preferably, the primary gesture state flag value of the current student is calculated according to the following first formula (1):

[0066]

[0067] In the first formula, δ represents the primary gesture state flag value of the current student; (X t ,Y t ,Z t ) represents the coordinate of the tth finger of the current student, and its value is 1, 2, 3, 4, 5; (X 3 ,Y 3 ,Z 3 ) represents the coordinates of the middle finger of the current student; (X i ,Y i ,Zi ) represents the palm coordinates of the current student.

[0068] S202: Determine whether the first-level gesture state flag value of the current student is not less than a preset value; if so, execute S203, otherwise execute S204.

[0069] Preferably, the preset value is 1, that is, when the first-level gesture state mark value δ≥1, it indicates that the current student's hand is in a non-fist state; when δ<1, it indicates that the current student's hand is in a fist state.

[0070] S203: Determine that the primary gesture state of the current student is a non-fist-clenching state.

[0071] As an optional embodiment, the gesture state further includes: a secondary gesture state subordinate to the primary gesture state; then in this embodiment, after S203, S2031-S2032 may also be included:

[0072] S2031: Calculate the secondary gesture state mark matrix of the current student in the non-fist-clenching state according to the second formula.

[0073] The second formula is:

[0074] λ={γ(Z 0 >0),γ(Z i >Z j )} (2)

[0075] In the second formula (2), λ represents the secondary gesture state flag matrix of the current student in the non-clenched fist state; γ() represents the judgment function, if the formula in the brackets is true, the function value is 1, if the formula in the brackets is false, the function value is 0; Z 0 Represents the coordinate value of the Z-axis coordinate in the unit normal vector of the current student's palm, Z j It represents the Z-axis coordinate value of the current student's shoulder (specifically, the specific part of the shoulder is the position of the middle point where the neck and the arm meet).

[0076] S2032: Determine the secondary gesture state of the current student in the non-clenched fist state according to the secondary gesture state mark matrix of the current student in the non-clenched fist state and a predetermined judgment strategy.

[0077] In this embodiment, the predetermined judgment strategy is: if λ={0,0}, then the secondary gesture state of the current student in the non-fist state is determined to be that the palm is facing up and the palm is below the shoulder; if λ={0,1}, then the secondary gesture state of the current student in the non-fist state is determined to be that the palm is facing up and the palm is above the shoulder; if λ={1,0}, then the secondary gesture state of the current student in the non-fist state is determined to be that the palm is facing down and the palm is below the shoulder; if λ={1,1}, then the secondary gesture state of the current student in the non-fist state is determined to be that the palm is facing down and the palm is above the shoulder.

[0078] S204: Determine that the primary gesture state of the current student is a fist state.

[0079] S103: Calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student;

[0080] As an optional embodiment, the S103 may include the following steps S1031-S1032:

[0081] S1031: Acquire multiple emotional states corresponding to the gesture state of the current student to obtain a first emotional state number array; and simultaneously perform semantic analysis on the voice information of the current student to acquire the emotional state corresponding to the semantics obtained by the analysis to obtain a second emotional state number array;

[0082] Among them, each emotional state and the number are in a one-to-one correspondence.

[0083] In this embodiment, various emotional states can be pre-numbered and assigned values, such as nervousness, excitement, happiness, crying and other emotions, which are numbered 1, 2, 3, and 4 respectively. When a student is giving a speech, each gesture state will correspond to multiple emotional states. For example, a clenched fist state can represent nervousness, excitement and other emotions, and the first emotional state number array is {1, 2}; after semantic analysis of the student's voice information, it is learned that the student is "cheer up", and the second emotional state number array is {2}. Before the implementation of the present invention, a first correspondence table between various gestures and emotional states is pre-stored, and a second correspondence table between various semantics and emotional states is pre-stored. The same gesture can correspond to multiple emotional states, and the same semantics can correspond to multiple emotional states.

[0084] S1032: Calculate the standardization mark value of the current student's speech according to the third formula;

[0085] Wherein, the third formula is:

[0086]

[0087] In the third formula, P represents the standardization mark value of the current student's speech; Sa represents the ath emotional state number value in the first emotional state number array; Y b Represents the bth emotional state number value in the second emotional state number array; a=1, 2, ..., n; n is the number of elements in the first emotional state number array, b=1, 2, ..., m; m is the number of elements in the second emotional state number array.

[0088] According to the third formula, if any element in the first emotional state number array exists in the second emotional state number array, then P = 0. Assuming that the first emotional state number array is {1, 2} and the second emotional state number array is {2}, then

[0089] S104: judging whether the current student has any irregularities in the speech according to the standardization flag value of the current student's speech, and sending the judgment result to a preset monitoring device.

[0090] As an optional embodiment, this step S104 may include S1041-S1043:

[0091] S1041: Determine whether the current student's speech normativeness flag value is equal to a preset normative threshold; if yes, execute S1042; otherwise, execute S1043;

[0092] In this embodiment, the preset standard threshold is 0.

[0093] S1042: Determine that the current student has not made any irregularities during the speech, and issue a first prompt message.

[0094] In this embodiment, the sending of the first prompt information includes: controlling a preset prompt light to display a first preset color, such as displaying green, which indicates that the student's current speech is normal.

[0095] S1043: Determine that the current student has made irregularities during the speech, and issue a second prompt message.

[0096] In this embodiment, the sending of the second prompt information includes: controlling a preset prompt light to display a second preset color, such as red, indicating that an irregularity has occurred during the current student's speech.

[0097] The student speech skill training method based on the virtual reality scene provided by the embodiment of the present invention first obtains the student's gesture state according to the real-time collected student's body coordinates in the virtual reality speech scene, then calculates the student's speech standardization mark value according to the gesture state and the collected student voice information, and finally judges whether the current student has any irregularities in the speech process according to the speech standardization mark value and sends the judgment result to the preset monitoring device through the color of the prompt light. The present invention provides students with a virtual reality speech environment and reminds them of irregularities in the speech process in real time, effectively reducing the time cost of teacher guidance and improving the teaching quality and effect.

[0098] Corresponding to the student speech skill training method based on virtual reality scene provided by the embodiment of the present invention, the embodiment of the present invention also provides a student speech skill training system based on virtual reality scene, such as Figure 3 As shown, the system includes:

[0099] The acquisition module 1 is used to acquire in real time the body coordinate information and voice information of the current student during a speech based on a virtual reality scene; wherein the coordinate information is the coordinate information of the current student in a preset coordinate system of the virtual reality scene.

[0100] The gesture state acquisition module 2 is used to obtain the gesture state of the current student according to the body coordinate information of the current student. Preferably, the gesture state acquisition module 2 is specifically used to calculate the primary gesture state flag value of the current student according to the first formula, and then obtain the primary gesture state according to the primary gesture state flag value. Furthermore, the gesture state acquisition module 2 is also specifically used to calculate the secondary gesture state flag matrix of the current student in the non-fist state according to the second formula when the primary gesture state is a non-fist state, and then obtain the secondary gesture state of the current student in the non-fist state according to the secondary gesture state flag matrix.

[0101] The speech normativeness mark value calculation module 3 is used to calculate the speech normativeness mark value of the current student according to the gesture state and voice information of the current student; preferably, the speech normativeness mark value calculation module 3 is specifically used to calculate the speech normativeness mark value of the current student according to the above-mentioned third formula.

[0102] The judging and displaying module 4 is used to judge whether the current student has any irregularities in the speech process according to the speech normativeness flag value of the current student and send the judgment result to a preset monitoring device.

[0103] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program codes.

[0104] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A student speech skills training method based on a virtual reality scene, characterized in that: The following steps are involved: Real-time collection of body coordinate information and voice information of the current student during a speech in a virtual reality scene; the coordinate information is the coordinate information of the current student in a preset coordinate system of the virtual reality scene; According to the body coordinate information of the current student, obtain the gesture status of the current student; Calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student; According to the speech normativeness flag value of the current student, determine whether the current student has any irregularities in the speech and send the determination result to a preset monitoring device; Wherein, the gesture state includes a first-level gesture state; The step of obtaining the gesture state of the current student according to the body coordinate information of the current student includes: According to the hand coordinate information of the current student, calculate the first-level gesture state flag value of the current student; Determine whether the first-level gesture state flag value of the current student is not less than a preset value; If the first-level gesture state flag value of the current student is not less than the preset value, it is determined that the first-level gesture state of the current student is a non-fist-clenching state; If the first-level gesture state flag value of the current student is less than a preset value, determining that the first-level gesture state of the current student is a fisting state; The step of calculating the primary gesture state flag value of the current student according to the hand coordinate information of the current student includes: The first level gesture state flag value of the current student is calculated according to the following first formula: In the first formula, δ represents the primary gesture state flag value of the current student; (X t ,Y t ,Z t ) represents the coordinates of the tth finger of the current student, and the values ​​are 1, 2, 3, 4, 5; (X3, Y3, Z3) represents the coordinates of the middle finger of the current student; (X i ,Y i ,Z i ) represents the palm coordinates of the current student; The step of calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student includes: Acquire multiple emotional states corresponding to the gesture state of the current student to obtain a first emotional state number array; perform semantic analysis on the voice information of the current student, acquire the emotional state corresponding to the semantics obtained by the analysis, and obtain a second emotional state number array; wherein each emotional state has a one-to-one correspondence with the number; The standardization mark value of the current student's speech is calculated according to the third formula: In the third formula, P represents the standardization mark value of the current student's speech; S a represents the ath emotional state number value in the first emotional state number array; Y b represents the bth emotional state number value in the second emotional state number array; n is the number of elements in the first emotional state number array, and m is the number of elements in the second emotional state number array.

2. The student speech skills training method based on virtual reality scene as claimed in claim 1, characterized in that: The gesture state further includes: a secondary gesture state subordinate to the primary gesture state; After determining that the primary gesture state of the current student is a non-fisting state, the method further includes: According to the second formula, the secondary gesture state mark matrix of the current student in the non-fist-clenching state is calculated; Determine the secondary gesture state of the current student in the non-clenched fist state according to the secondary gesture state flag matrix of the current student in the non-clenched fist state and a predetermined judgment strategy; Wherein, the second formula is: λ={γ(Z0>0),γ(Z i >From j )} In the second formula, λ represents the secondary gesture state flag matrix of the current student in the non-clenched fist state; γ() represents the judgment function, if the formula in the brackets is true, the function value is 1, if the formula in the brackets is false, the function value is 0; Z0 represents the coordinate value of the Z-axis coordinate in the unit normal vector of the current student's palm, Z j Represents the Z-axis coordinate value of the current student's shoulder.

3. The student speech skills training method based on virtual reality scene as claimed in claim 2, characterized in that: The predetermined judgment strategy is: If λ={0,0}, it is determined that the current secondary gesture state of the student in the non-fist state is that the palm is facing up and the palm is below the shoulder; If λ = {0,1}, then the secondary gesture state of the current student in the non-fist state is determined to be that the palm is facing up and the palm is higher than the shoulder; If λ={1,0}, it is determined that the current secondary gesture state of the student in the non-fist state is that the palm is facing down and the palm is lower than the shoulder; If λ={1,1}, it is determined that the secondary gesture state of the current student in the non-fist-clenching state is that the palm is facing down and the palm is higher than the shoulder.

4. The student speech skills training method based on virtual reality scene as claimed in claim 1, characterized in that: The step of judging whether the current student has any irregularities in his speech according to the speech normativeness flag value of the current student includes: Determine whether the current student's speech normativeness mark value is equal to a preset normative threshold; If the standardization flag value of the current student's speech is equal to the preset standard threshold, it is determined that the current student has not made any irregularities in the speech, and a first prompt message is issued; If the standardization flag value of the current student's speech is not equal to the preset standard threshold, it is determined that the current student has made irregularities in the speech and a second prompt message is issued.

5. The student speech skills training method based on virtual reality scene as claimed in claim 4, characterized in that: The preset standard threshold is 0.

6. The student speech skills training method based on virtual reality scene as claimed in claim 4, characterized in that: The sending of the first prompt information includes: controlling a preset prompt light to display a first preset color; the sending of the second prompt information includes: controlling a preset prompt light to display a second preset color.

7. A student speech skills training system based on virtual reality scenes, characterized in that: include: A collection module, used to collect in real time the body coordinate information and voice information of the current student during the speech in the virtual reality scene; the coordinate information is the coordinate information of the current student in the preset coordinate system of the virtual reality scene; The gesture state acquisition module is used to obtain the gesture state of the current student according to the body coordinate information of the current student; A speech normativeness mark value calculation module, used for calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student; A judgment and display module, used to judge whether the current student has any irregularities in the speech process according to the speech normativeness flag value of the current student and send the judgment result to a preset monitoring device; Wherein, the gesture state includes a first-level gesture state; The step of obtaining the gesture state of the current student according to the body coordinate information of the current student includes: According to the hand coordinate information of the current student, calculate the first-level gesture state flag value of the current student; Determine whether the first-level gesture state flag value of the current student is not less than a preset value; If the first-level gesture state flag value of the current student is not less than the preset value, it is determined that the first-level gesture state of the current student is a non-fist-clenching state; If the first-level gesture state flag value of the current student is less than a preset value, determining that the first-level gesture state of the current student is a fisting state; The step of calculating the primary gesture state flag value of the current student according to the hand coordinate information of the current student includes: The first level gesture state flag value of the current student is calculated according to the following first formula: In the first formula, δ represents the primary gesture state flag value of the current student; (X t ,Y t ,Z t ) represents the coordinates of the tth finger of the current student, and the values ​​are 1, 2, 3, 4, 5; (X3, Y3, Z3) represents the coordinates of the middle finger of the current student; (X i ,Y i ,Z i ) represents the palm coordinates of the current student; The step of calculating the speech normativeness mark value of the current student according to the gesture state and voice information of the current student includes: Acquire multiple emotional states corresponding to the gesture state of the current student to obtain a first emotional state number array; perform semantic analysis on the voice information of the current student, acquire the emotional state corresponding to the semantics obtained by the analysis, and obtain a second emotional state number array; wherein each emotional state has a one-to-one correspondence with the number; The standardization mark value of the current student's speech is calculated according to the third formula: In the third formula, P represents the standardization mark value of the current student's speech; S a represents the ath emotional state number value in the first emotional state number array; Y b represents the bth emotional state number value in the second emotional state number array; n is the number of elements in the first emotional state number array, and m is the number of elements in the second emotional state number array.

Images