Method and device for determining discussion popularity of student group, equipment and storage medium

Abstract

The invention discloses a method, device and equipment for determining the discussion popularity of a student group and a storage medium. The method comprises the following steps: acquiring spectrum features and voice stream features of voice data discussed by a group; according to the spectrum features and the voice stream features, first key features of group discussion are extracted, and the first key features comprise the number of speaking objects and speaking time period distribution information of the speaking objects; and based on a preset evaluation parameter, obtaining a popularity value of the student group discussion, the preset evaluation parameter including the first key feature. According to the method, the participation degree problem of group discussion among the students is fully considered, the quality of group discussion of the students can be objectively evaluated, and powerful teaching analysis reference data is provided for teachers.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence, and more specifically, to a method, apparatus, device and storage medium for determining the discussion enthusiasm of a student group. Background Art

[0002] Group discussions among students are an important form of classroom interaction. Teachers can divide students into groups and discuss specific topics. This teaching method of group discussion not only livens up the classroom atmosphere, but also stimulates students' interest in learning, encourages them to think and communicate, and improves the quality and fun of teaching.

[0003] However, during actual discussions, some students in the discussion groups often exhibit low participation and rarely contribute to the discussion. This defeats the purpose of group discussions and hinders their effectiveness. Furthermore, teachers are often unable to provide full supervision during discussions, leading students to discuss unrelated topics, which can negatively impact the effectiveness of the discussion.

[0004] Therefore, there is an urgent need for a method that can objectively evaluate the quality of students' group discussions as part of teaching feedback to promote teacher development. Summary of the Invention

[0005] In order to overcome at least one of the defects described in the above-mentioned prior art, the present invention provides a method, device, equipment and storage medium for determining the discussion enthusiasm of a student group. The technical solution adopted by the present invention is as follows.

[0006] In a first aspect, the present invention provides a method for determining the discussion enthusiasm of a student group, comprising:

[0007] Obtaining the spectrum characteristics and voice flow characteristics of the voice data of the group discussion;

[0008] Extracting first key features of the group discussion based on the spectral features and the voice stream features, wherein the first key features include: the number of speakers and distribution information of time periods in which each speaker speaks;

[0009] Based on preset evaluation parameters, a heat value of the student group discussion is obtained, wherein the preset evaluation parameters include the first key feature.

[0010] In one embodiment, the first key feature further includes: the total duration of speeches by all speakers.

[0011] In one embodiment, the first key feature further includes: speech coherence and intonation.

[0012] In one embodiment, the first key feature further includes: average speaking speed and average volume.

[0013] In one embodiment, it further includes:

[0014] Obtaining the voice transcript of the group discussion voice data;

[0015] Extracting second key features of the group discussion based on the speech text, wherein the second key features include: the total number of words spoken by all group members, and the overlap rate between high-frequency words in the speech content and preset keywords;

[0016] Wherein, the preset evaluation parameters also include the second key feature.

[0017] In one embodiment, the second key feature also includes: the number of content-sensitive words and the number of modal particles preset in the speech content.

[0018] In one embodiment, the process of obtaining the popularity value of the student group discussion based on the preset evaluation parameters includes:

[0019] Obtain the weight corresponding to each evaluation parameter;

[0020] The heat value of the student group discussion is obtained according to the evaluation parameters and the corresponding weights.

[0021] In a second aspect, the present invention provides a method for a sending end to determine the discussion heat of a student group, comprising:

[0022] Obtaining a first popularity value for a first time period and a second popularity value for a second time period, wherein the first popularity value and the second popularity value are obtained using the method for determining student group discussion enthusiasm described in any of the previous embodiments, and the second time period is a time period after the first time period;

[0023] The first heat value and the second heat value are compared to obtain a comparison result, and the comparison result is fed back.

[0024] In one embodiment, the method further includes: issuing a reminder message when the comparison result is that the second heat value is less than the first heat value.

[0025] In a third aspect, the present invention provides a device for determining the discussion enthusiasm of a student group at a sending end, comprising:

[0026] An acquisition module, used to obtain the spectrum characteristics and voice flow characteristics of the voice data of the group discussion;

[0027] an extraction module, configured to extract first key features of the group discussion based on the spectral features and the voice stream features, wherein the first key features include: the number of speakers and distribution information of time periods in which each speaker speaks;

[0028] The analysis module is used to obtain the popularity value of the student group discussion based on preset evaluation parameters, wherein the preset evaluation parameters include the first key feature.

[0029] In a fourth aspect, the present invention provides a device for determining the discussion enthusiasm of a student group at a sending end, characterized by comprising:

[0030] a receiving module, configured to obtain a first popularity value of a first time period and a second popularity value of a second time period, wherein the first popularity value and the second popularity value are obtained using the aforementioned device for determining the student group discussion popularity, and the second time period is a time period after the first time period;

[0031] The comparison module compares the first heat value and the second heat value, obtains a comparison result, and feeds back the comparison result.

[0032] In a fifth aspect, the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method of any of the above-mentioned embodiments when executing the program.

[0033] In a sixth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the method of any of the above-mentioned embodiments is implemented.

[0034] This method acquires spectral and speech stream features, extracts the number of speakers and the distribution of each speaker's speaking time periods, and uses this information to derive the intensity of student group discussions. Furthermore, during classroom instruction, the method monitors the intensity of each group in real time, providing timely feedback to teachers. This method fully considers student engagement in group discussions, objectively assesses their quality, and provides teachers with valuable reference data for teaching analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the overall process of an implementation method of Example 1 of the present invention.

[0036] Figure 2 It is a schematic diagram of the overall process of another implementation method of Example 1 of the present invention.

[0037] Figure 3 It is a schematic diagram of the overall structure of an implementation method of Example 2 of the present invention.

[0038] Figure 4 It is a schematic diagram of the overall structure of another implementation method of Example 2 of the present invention. DETAILED DESCRIPTION

[0039] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0040] It should be noted that the terms "first, second, ..." used in the embodiments of the present invention are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the terms "first, second, ..." may interchangeably represent a specific order or precedence, where permitted. It should be understood that the objects distinguished by "first, second, ..." may be interchangeable, where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0041] Example 1

[0042] See Figure 1 , Figure 1 This is a flow chart of a method for determining the discussion heat of a student group provided in Example 1 of the present invention, which includes step S110, step S120 and step S130. It should be noted that step S110, step S120 and step S130 are only reference numerals for the purpose of clearly explaining the embodiment and the appendix. Figure 1 The corresponding relationship does not limit the order of the steps in this embodiment.

[0043] Step S110, obtaining the spectrum characteristics and voice flow characteristics of the voice data of the group discussion;

[0044] Step S120: extracting first key features of the group discussion based on the spectral features and the voice stream features, wherein the first key features include: the number of speakers and distribution information of time periods when each speaker spoke;

[0045] Step S130: obtaining the heat value of the student group discussion based on preset evaluation parameters, wherein the preset evaluation parameters include the first key feature.

[0046] In the classroom scenario, the classroom observation system is an important system for realizing smart education classrooms. The classroom observation system uses microphones and other sound receiving systems in the classroom scene, and uses computer voice analysis and other technologies to analyze the student group discussions in the classroom, and provides classroom quality-related data (for example, student participation, student discussion status, teaching skills), which is used as part of teaching feedback to promote teacher development. Through the microphones and other sound receiving systems in the classroom scene, the voice data of the course group discussions can be obtained. It should be noted here that this method can be used for real-time monitoring and analysis of the enthusiasm of student group discussions, and can also be used as a review of the enthusiasm of student group discussions by teachers after class.

[0047] After acquiring the speech data from the course group discussions, we process it to obtain its spectral features. The frequency characteristics of speech data refer to the various properties of sound in the frequency domain, which can reveal the nature and characteristics of the sound. The frequency characteristics of speech data can generally be derived through spectral analysis of the sound signal. Common frequency characteristics include fundamental frequency, harmonic frequencies, and the spectral shape of the sound.

[0048] Furthermore, speech data processing also yields speech stream features. These are a series of attributes and parameters used to describe a continuous speech stream (i.e., the sound of continuous speech), reflecting the dynamic temporal characteristics of the speech signal. These include syllables, phonemes, intonation, and speech rate.

[0049] After processing the spectral features and speech flow features of the speech data, step S110 acquires this data. In step S120, this data is processed and key features are extracted, including the number of speakers and the distribution of time periods in which each speaker spoke.

[0050] There's a close relationship between the frequency characteristics and speech stream characteristics of audio data and human voiceprints. By analyzing frequency characteristics such as fundamental frequency, harmonics, spectrum, and formants, and speech stream characteristics such as speech rate, prosody, speech coherence, syllable duration, and pronunciation habits, we can identify and differentiate different human voiceprints, thereby deriving the individual speakers, and subsequently determining the number of speakers and the distribution of the time periods during which each speaker spoke.

[0051] A larger number of speakers indicates a greater number of participants in the group, which in turn indicates a more lively discussion, higher participation, and greater enthusiasm. By analyzing the distribution of speaking time periods for each speaker, we can understand the actual participation of each speaker, determining whether everyone is actively speaking or whether the conversation is concentrated among a few speakers. This helps address the quality of the speeches.

[0052] In step S130, an evaluation model is pre-set, which includes several evaluation parameters. Using this model and parameters, the popularity value of the student group discussion can be obtained. In this method, the pre-set evaluation parameters include the first key features extracted in step S120. As previously mentioned, these key features have a certain relationship with the popularity value of the classroom group discussion. The pre-set evaluation model can use this relationship to derive the popularity value of the student group discussion.

[0053] This method acquires spectral and speech stream features, extracts the number of speakers and the distribution of each speaker's speaking time periods, and finally uses this information to derive the intensity of student group discussions. This method fully considers student engagement in group discussions, objectively assesses their quality, and provides valuable data for teachers' instructional analysis.

[0054] In one embodiment, the first key feature further includes: the total duration of speeches by all speakers.

[0055] When the group members are speaking, everyone rushes to speak, one after another. The more active and enthusiastic everyone is, and the higher their willingness to participate, the longer the total time everyone speaks, and naturally the higher the heat value of the student group discussion.

[0056] In one embodiment, the first key feature further includes: speech coherence and intonation.

[0057] The more fluent, coherent and high-pitched the group members' speeches are, the more enthusiastically they participate in the discussion, which means that the group discussion is more heated.

[0058] In one embodiment, the first key feature further includes: average speaking speed and average volume.

[0059] The faster the average speaking speed and the higher the average volume of group members, the more excited the group members are and the more enthusiastic they are in participating in the discussion, which means that the group discussion is more heated.

[0060] In one embodiment, the method for determining the discussion heat of a student group further includes: step S140 and step S150.

[0061] Step S140, obtaining the voice text of the voice data of the group discussion;

[0062] Step S150: extracting the second key features of the group discussion based on the voice text, wherein the second key features include: the total number of words in the speeches of all group members, and the overlap rate between high-frequency words in the speeches and preset keywords.

[0063] Wherein, the preset evaluation parameters also include the second key feature.

[0064] In addition to analyzing the discussion heat of student groups through spectral features and voice stream features, this embodiment also analyzes the discussion heat of student groups through the language content itself, so the voice text is obtained in step S140, and the heat is analyzed based on the voice text. In this embodiment, the second key feature of the group discussion is extracted from the voice text. This second key feature includes the total number of words in the group members' speeches and the overlap rate between high-frequency words and preset keywords in the speech content. The more total words a group member speaks, the more content the group members discuss, which indicates that the group discussion heat is higher; in addition, the higher the overlap rate between high-frequency words and preset keywords in the group members' speeches, the more it indicates that the group members are discussing content related to the topic and are not distracted to discuss other issues, which indicates that the group discussion heat is higher.

[0065] In one embodiment, the second key feature further includes: a preset number of content-sensitive words and a preset number of modal particles.

[0066] This is the second key feature of negative situations. Some content-sensitive words that are irrelevant to the topic are preset. If the number of these preset content-sensitive words and modal particles in the speeches of group members is greater, it means that the probability of group members' discussion going off topic is greater and the discussion heat is lower. Conversely, it means that the discussion heat is higher.

[0067] In one embodiment, the process of step S130 includes: step S131 and step S132.

[0068] Step S131, obtaining the weight corresponding to each evaluation parameter;

[0069] Step S132: Obtain the heat value of the student group discussion based on the evaluation parameters and their corresponding weights.

[0070] Each evaluation parameter has its own corresponding weight. A positive evaluation parameter may have a positive corresponding weight, and a negative evaluation parameter may have a negative corresponding weight. By using the weights corresponding to these evaluation parameters to rationalize the proportion of each parameter in the evaluation model, we can better derive the heat value of the student group discussion.

[0071] In this embodiment, see Figure 2 , Figure 2 This is a flowchart of another method for determining the discussion enthusiasm of a student group provided in the first embodiment of the present invention. The method includes: step S210 and step S220.

[0072] Step S210: Obtain a first popularity value of a first time period and a second popularity value of a second time period, wherein the first popularity value and the second popularity value are obtained using the aforementioned method for determining the discussion enthusiasm of a student group, and the second time period is a time period after the first time period;

[0073] Step S220 , comparing the first heat value and the second heat value, obtaining a comparison result, and feeding back the comparison result.

[0074] In a classroom setting, the teacher monitors the enthusiasm of each group in real time. When a group's enthusiasm is too low, the teacher reminds the group members to return to the topic and actively participate in the group discussion. After the teacher reminds them, the teacher can know whether the reminder has worked through the comparison result of step S220.

[0075] In one embodiment, the other method for determining the discussion heat of a student group further includes: step S230.

[0076] Step S230: When the comparison result shows that the second heat value is less than the first heat value, a reminder message is issued.

[0077] In a classroom scenario, the teacher will monitor the heat value of each group in real time. When the second heat value is less than the first heat value, that is, when the heat value shows a downward trend, it means that everyone has discussed almost everything and there are not many opinions that can be expressed. At this time, a reminder message will be sent to remind the teacher to end the group discussion.

[0078] Example 2

[0079] Corresponding to the method of determining the discussion enthusiasm of student groups in Example 1, Figure 3 As shown, the present invention also provides a device 3 for determining the discussion heat of a student group, including: an acquisition module 310, an extraction module 320, and an analysis module 330.

[0080] An acquisition module 310 is used to acquire spectral features and speech flow features of speech data of a group discussion;

[0081] An extraction module 320 is configured to extract first key features of the group discussion based on the spectral features and the voice stream features, wherein the first key features include: the number of speakers and the time period distribution information of each speaker;

[0082] The analysis module 330 is used to obtain the popularity value of the student group discussion based on preset evaluation parameters, wherein the preset evaluation parameters include the first key feature.

[0083] In one embodiment, the first key feature further includes: the total duration of speeches by all speakers.

[0084] In one embodiment, the first key feature further includes: speech coherence and intonation.

[0085] In one embodiment, the first key feature further includes: average speaking speed and average volume.

[0086] In one embodiment, the acquisition module is further configured to acquire a voice text of the voice data of the group discussion;

[0087] The extraction module is further configured to extract second key features of the group discussion based on the speech text, wherein the second key features include: the total number of words spoken by all group members, and the overlap rate between high-frequency words in the speech content and preset keywords;

[0088] The preset evaluation parameters also include the second key feature.

[0089] In one embodiment, the second key feature further includes: a preset number of content-sensitive words and a preset number of modal particles.

[0090] In one embodiment, the analysis module performs the process of obtaining the popularity value of the student group discussion based on the preset evaluation parameters, including:

[0091] Obtain the weight corresponding to each evaluation parameter;

[0092] The heat value of the student group discussion is obtained according to the evaluation parameters and the corresponding weights.

[0093] Corresponding to another method of determining the discussion enthusiasm of student groups in embodiment 1, Figure 4 As shown, the present invention also provides another device 4 for determining the discussion enthusiasm of a student group, including: a receiving module 410 and a comparing module 420.

[0094] A receiving module 410 is configured to obtain a first popularity value of a first time period and a second popularity value of a second time period, wherein the first popularity value and the second popularity value are obtained using the aforementioned apparatus for determining student group discussion popularity, and the second time period is a time period after the first time period;

[0095] The comparison module 420 compares the first heat value and the second heat value, obtains a comparison result, and feeds back the comparison result.

[0096] In one embodiment, the device for determining the discussion heat of a student group further includes: a reminder module.

[0097] The reminder module is used to issue a reminder message when the comparison result shows that the second heat value is less than the first heat value.

[0098] This device acquires spectral and speech stream features, extracts the number of speakers and the distribution of each speaker's speaking time periods, and uses this information to derive the intensity of student group discussions. During class, it monitors the intensity of each group in real time, providing timely feedback to the teacher. This device fully considers student engagement in group discussions, objectively assessing their quality and providing valuable data for teacher analysis.

[0099] Example 3

[0100] An embodiment of the present invention further provides a storage medium storing computer instructions, which, when executed by a processor, implement the method for determining the discussion enthusiasm of a student group according to any of the above embodiments.

[0101] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: mobile storage devices, random access memory (RAM), read-only memory (ROM), magnetic disk or optical disk, etc. Various media that can store program codes.

[0102] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, RAM, ROM, magnetic disks or optical disks.

[0103] Corresponding to the above-mentioned computer storage medium, in one embodiment, a computer device is also provided, which includes a memory, an encoder, and a computer program stored on the memory and runnable on the encoder, wherein when the encoder executes the program, it implements any one of the methods for determining the discussion heat of a student group in the above-mentioned embodiments.

[0104] The computer device acquires spectral and speech stream features, extracts the number of speakers and the distribution of each speaker's speaking time periods, and uses this information to derive the intensity of student group discussions. During class, the device monitors the intensity of each group in real time, providing timely feedback to the teacher. This computer device fully considers student engagement in group discussions, objectively assessing their quality and providing valuable data for teacher analysis.

[0105] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] Obviously, the above embodiments of the present invention are merely examples for the purpose of clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. A method for determining the discussion enthusiasm of a student group, characterized in that: include: Obtaining the spectrum characteristics and voice flow characteristics of the voice data of the group discussion; Extracting first key features of the group discussion based on the spectral features and the voice stream features, wherein the first key features include: the number of speakers and distribution information of time periods in which each speaker speaks; Based on preset evaluation parameters, a heat value of the student group discussion is obtained, wherein the preset evaluation parameters include the first key feature.

2. The method for determining the discussion enthusiasm of a student group according to claim 1, characterized in that: The first key feature also includes: the total duration of speeches by all speakers.

3. The method for determining the discussion enthusiasm of a student group according to claim 1, characterized in that: The first key features also include: speech coherence and intonation.

4. The method for determining the discussion enthusiasm of a student group according to claim 1, characterized in that: The first key feature also includes: average speaking speed and average volume.

5. The method for determining the discussion enthusiasm of a student group according to claim 1, characterized in that: Also includes: Obtaining the voice transcript of the group discussion voice data; Extracting second key features of the group discussion based on the speech text, wherein the second key features include: the total number of words spoken by all group members, and the overlap rate between high-frequency words in the speech content and preset keywords; Wherein, the preset evaluation parameters also include the second key feature.

6. The method for determining the discussion enthusiasm of a student group according to claim 5, characterized in that: The second key feature also includes: the number of content-sensitive words and modal particles preset in the speech content.

7. The method for determining the discussion enthusiasm of a student group according to claim 1, characterized in that: The process of obtaining the heat value of the student group discussion based on the preset evaluation parameters includes: Obtain the weight corresponding to each evaluation parameter; The heat value of the student group discussion is obtained according to the evaluation parameters and the corresponding weights.

8. A method for determining the discussion enthusiasm of a student group at a sending end, characterized in that: include: Obtaining a first popularity value of a first time period and a second popularity value of a second time period, wherein the first popularity value and the second popularity value are obtained using the method for determining student group discussion enthusiasm according to any one of claims 1 to 7, and the second time period is a time period after the first time period; The first heat value and the second heat value are compared to obtain a comparison result, and the comparison result is fed back.

9. The method for determining the discussion enthusiasm of a student group according to claim 8, characterized in that: Also includes: When the comparison result is that the second heat value is less than the first heat value, a reminder message is issued.

10. A device for determining the discussion enthusiasm of a student group at a sending end, characterized in that: include: An acquisition module, used to obtain the spectrum characteristics and voice flow characteristics of the voice data of the group discussion; an extraction module, configured to extract first key features of the group discussion based on the spectral features and the voice stream features, wherein the first key features include: the number of speakers and distribution information of time periods in which each speaker speaks; The analysis module is used to obtain the popularity value of the student group discussion based on preset evaluation parameters, wherein the preset evaluation parameters include the first key feature.

11. A device for determining the discussion enthusiasm of a student group at a sending end, characterized in that: include: a receiving module, configured to obtain a first popularity value of a first time period and a second popularity value of a second time period, wherein the first popularity value and the second popularity value are obtained using the apparatus for determining student group discussion popularity according to claim 10, and the second time period is a time period after the first time period; The comparison module compares the first heat value and the second heat value, obtains a comparison result, and feeds back the comparison result.

12. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 9 is implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images