Emotion analysis system

Abstract

The invention relates to the technical field of education, in particular to an emotion analysis system which comprises a conversation party A, a conversation party B, voice analysis equipment and an emotion test question bank. The big data voice processing software can convert the voice recorded by the microphone into characters, analyze the emotion of the conversation party A and / or the conversation party B, and determine the identity of a person according to the audio of the recorded voice. Big data voice processing software capable of selecting questions of an emotion test question bank according to current analysis results of voice of a conversation party A and / or a conversation party B and prompting the conversation party B to ask the conversation party A and / or directly ask the conversation party A so as to determine emotion types of the conversation party A and / or the conversation party B or exclude the conversation party A and / or the conversation party B and emotion types of the prescription. By setting the emotion test question bank, the test problem can be selected according to the current analysis result of the forepart conversation of the conversation A party, so that the emotion feature can be more determined or a certain emotion feature can be eliminated, and the emotion analysis efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of education, and in particular to a sentiment analysis system. Background Art

[0002] In the student sentiment analysis, students’ Figure 1 Generally, they are not aware of it, so we can get students' emotional problems by asking a lot of questions, and then provide targeted teaching based on their emotions, which can help students grow up healthily. At present, the test question bank determines the students' emotions based on the probability of the answers to several test questions, and judges the emotions by the proportion of wrong answers. This judgment method is not accurate enough and there is a possibility of misjudgment. Asking too many questions will also cause students to be disgusted and bored. Summary of the invention

[0003] In order to solve the problems in the above-mentioned background technology, the present invention provides a sentiment analysis system for sentiment analysis, and solves the problem of inaccurate sentiment analysis in the prior art.

[0004] The solution adopted by the present invention to solve its technical problems is: an emotion analysis system, including a conversation party A, a conversation party B, a speech analysis device, and an emotion test question bank, wherein the speech analysis device is provided with a microphone for recording, a display for displaying text, and a processor for installing big data speech processing software, wherein the microphone can record the voices of the conversation party A and the conversation party B, the big data speech processing software can convert the voice recorded by the microphone into text and then analyze the emotions of the conversation party A and / or the conversation party B and determine the identity of the person according to the audio of the recorded voice, the display can display the analysis results and processing solutions of the big data speech processing software, and the big data speech processing software can select questions from the emotion test question bank according to the current analysis results of the voice of the conversation party A and / or the conversation party B and prompt the conversation party B to ask questions to the conversation party A and / or directly ask questions to the conversation party A so as to determine the emotion types of the conversation party A and / or the conversation party B or exclude the emotion types of the conversation party A and / or the conversation party B.

[0005] Furthermore, the voice analysis device is provided with a speaker, and the conversation party B is the voice analysis device.

[0006] Furthermore, the big data speech processing software is a large language model, which may be ChatGPT or Wenxin Yiyan or Tongyi Qianwen or 360 Zhinao or iFlytek Spark.

[0007] Furthermore, the test questions in the emotion test question bank are connected in a parent-child relationship through the listed answers. The parent set test question has one or more answers, and one answer to the parent set test question corresponds to one subset test question. An answer to the parent set test question recorded by the big data voice processing software continues to ask the subset test question corresponding to the answer, and the subset test question has one or more answers.

[0008] Furthermore, the parent set test questions have only one answer and the test ends when the answer is correct.

[0009] Furthermore, if the answer to the test question of the subset appears outside the provided answers, the test question of the parent set is returned to and the test question of the parent set is restarted.

[0010] Furthermore, the test question corresponding to the answer to the subset test question is the subset test question with the subset as the parent set.

[0011] Furthermore, when the subset test question has only one answer, the subset test question is a sufficient condition for the emotion corresponding to the subset test question, and when the subset test question has multiple answers, the subset test question is a necessary condition for the emotion corresponding to the subset test question.

[0012] To sum up, the beneficial effects of the present invention are as follows: by setting up an emotion test question bank, the big data voice processing software can select test questions based on the current analysis results of the previous conversation of Party A, and prompt the selected test questions to Party B to ask, so that the characteristics of the emotions can be more determined or certain emotional characteristics can be eliminated, aimless questioning can be avoided, the efficiency of emotion analysis can be improved, and emotion analysis can be more accurate, thereby better managing the emotions of Party A.

[0013] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the following specifically cites a preferred embodiment and describes it in detail with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is the parent-child relationship diagram of the emotion test question bank. DETAILED DESCRIPTION

[0015] In order to make the content of the present invention more clearly understood, the present invention is further described below based on specific embodiments in conjunction with the accompanying drawings.

[0016] It should be noted that the terms "center", "upper", "lower", "front", "back", "left", "right", "inner", "outer" and the like used herein to indicate directions or positional relationships are based on directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. Unless otherwise specified, "plurality" means two or more.

[0017] Unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0018] Referring to the accompanying drawings, a sentiment analysis system includes a conversation party A, a conversation party B, a speech analysis device, and a sentiment test question bank, wherein the speech analysis device is provided with a microphone for recording, a display for displaying text, a processor for installing big data speech processing software, and a memory for storing the sentiment test question bank, wherein the microphone can record the voices of the conversation party A and the conversation party B, the big data speech processing software can convert the voice recorded by the microphone into text and then analyze the sentiment of the conversation party A and / or the conversation party B and determine the identity of the person according to the audio of the recorded voice, the display can display the analysis results and processing solutions of the big data speech processing software, the big data speech processing software can select questions from the sentiment test question bank according to the current analysis results of the voices of the conversation party A and / or the conversation party B and prompt the conversation party B to ask questions to the conversation party A and / or directly ask questions to the conversation party A so as to determine the emotion types of the conversation party A and / or the conversation party B or exclude the emotion types of the conversation party A and / or the conversation party B.

[0019] Furthermore, the voice analysis device is provided with a speaker, and the conversation party B is the voice analysis device.

[0020] Furthermore, the big data speech processing software is a large language model, which may be ChatGPT or Wenxin Yiyan or Tongyi Qianwen or 360 Zhinao or iFlytek Spark.

[0021] Furthermore, the test questions in the emotion test question bank are connected in a parent-child relationship through the listed answers. The parent set test question has one or more answers, and one answer to the parent set test question corresponds to one subset test question. An answer to the parent set test question recorded by the big data voice processing software continues to ask the subset test question corresponding to the answer, and the subset test question has one or more answers.

[0022] Furthermore, the parent set test questions have only one answer and the test ends when the answer is correct.

[0023] Furthermore, if the answer to the test question of the subset appears outside the provided answers, the test question of the parent set is returned to and the test question of the parent set is restarted.

[0024] Furthermore, the test question corresponding to the answer to the subset test question is the subset test question with the subset as the parent set.

[0025] Furthermore, when the subset test question has only one answer, the subset test question is a sufficient condition for the emotion corresponding to the subset test question, and when the subset test question has multiple answers, the subset test question is a necessary condition for the emotion corresponding to the subset test question.

[0026] The present invention sets up an emotion test question bank, and the big data voice processing software can select test questions based on the current analysis results of the previous conversation of the testee, and prompt the selected test questions to the conversation party B to ask questions, so as to avoid aimless questions, so that the characteristics of emotions can be more determined or certain emotional characteristics can be excluded, so that the efficiency of emotion analysis can be improved, and the emotion analysis can be more accurate, so as to better manage the conversation party A for emotions. Just like a doctor diagnosing a disease, it is necessary to determine what disease it is based on some characteristics, or to exclude what disease it is based on some characteristics. At this time, generally according to the existing emotional characteristics, there may be several emotional judgment directions, and you can ask more questions to get an emotion in one direction.

[0027] Specifically, it has the following beneficial effects:

[0028] 1. The big data speech processing software of the present invention can select test questions based on the current analysis results of the previous conversation of Party A, and prompt the selected test questions to Party B to ask, so as to avoid aimless inquiries;

[0029] 2. The test questions in the emotional test question bank are connected by the listed answers to achieve a parent-child relationship. The answer to a parent set of test questions leads to one or more subset test questions. It is logical and can be peeled off layer by layer until a definite answer is obtained.

[0030] 3. Starting from the necessary conditions, through questioning, gradually narrow the scope until you reach the sufficient conditions and get the inevitable result;

[0031] 4. Using voice analysis equipment to ask questions can avoid emotional questions from the questioner;

[0032] 5. Big data speech processing software or big data models have rich knowledge structures and comprehensive sentiment analysis to avoid mistakes.

[0033] The embodiments described above are only preferred implementation modes of the present invention and cannot be used to limit the protection scope of the present invention. Any non-substantial changes and modifications made by those skilled in the art on the basis of the invention shall fall within the protection scope of the present invention.

Claims

1. A sentiment analysis system, characterized in that: It includes a conversation party A, a conversation party B, a speech analysis device, and an emotion test question bank, wherein the speech analysis device is provided with a microphone for recording, a display for displaying text, and a processor for installing big data speech processing software, wherein the microphone can record the speech of the conversation party A and the conversation party B, the big data speech processing software can convert the speech recorded by the microphone into text and then analyze the emotion of the conversation party A and / or the conversation party B and determine the identity of the person according to the audio of the recorded speech, the display can display the analysis result and processing plan of the big data speech processing software, the big data speech processing software can select questions from the emotion test question bank according to the current analysis result of the speech of the conversation party A and / or the conversation party B and prompt the conversation party B to ask questions to the conversation party A and / or directly ask questions to the conversation party A so as to determine the emotion type of the conversation party A and / or the conversation party B or exclude the emotion type of the conversation party A and / or the conversation party B.

2. The sentiment analysis system according to claim 1, characterized in that: The speech analysis device is provided with a speaker, and the second party in the conversation is the speech analysis device.

3. The sentiment analysis system according to claim 1, characterized in that: The big data speech processing software is a large language model, and the large language model can be ChatGPT or Wenxin Yiyan or Tongyi Qianwen or 360 Zhinao or iFlytek Spark.

4. The sentiment analysis system according to claim 1, characterized in that: The test questions in the emotion test question bank are connected in a parent-child relationship through the listed answers. The parent set test question has one or more answers, and one answer to the parent set test question corresponds to a subset test question. An answer to the parent set test question recorded by the big data voice processing software continues to ask questions according to the subset test question corresponding to the answer, and the subset test question has one or more answers.

5. The sentiment analysis system according to claim 4, characterized in that: The parent set test question has only one answer and the test ends when the answer is correct.

6. The sentiment analysis system according to claim 4 or 5, characterized in that: If the answer to the test question of the subset appears outside the provided answer, the test question of the parent set is returned to and the test question of the parent set is restarted.

7. The sentiment analysis system according to claim 4, characterized in that: The test question corresponding to the answer to the subset test question is the subset test question with the subset as the parent set.

8. The sentiment analysis system according to claim 4, characterized in that: When the subset test question has only one answer, the subset test question is a sufficient condition for the emotion corresponding to the test question. When the subset test question has multiple answers, the subset test question is a necessary condition for the emotion corresponding to the test question.

Images