Online course chat record processing method, device and electronic device

Abstract

The present invention provides a method, device and electronic device for processing online course chat records. The chat records generated by current students in the online course are analyzed to obtain the current student's speech ratio, the current student's emotional index in the online course and the current student's classroom water index, so as to analyze the quality of the teacher's teaching by using the obtained current student's speech ratio, classroom emotional index and classroom water index. Compared with the method in the related art that can only evaluate the teaching quality of the online course teacher indirectly from the conversion rate, renewal rate and other aspects, the teaching quality of the online course teacher can be evaluated more directly and objectively from the parameters related to classroom teaching, such as the current student's speech ratio, the current student's emotional index in the online course and the current student's classroom water index.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device and electronic device for processing online course chat records. Background Art

[0002] At present, with the gradual development of online education, more and more parents of students choose online courses as a supplement to their children's extracurricular tutoring. However, how to evaluate the teaching quality of online course teachers, how to understand whether the teacher is engaged in the current class, and whether the children have truly mastered what the teacher said has gradually become a new issue that needs to be urgently solved.

[0003] The teaching quality of online course teachers is mainly evaluated indirectly through conversion rate and renewal rate, but it is not accurate to reflect the teaching quality of online course teachers through conversion rate and renewal rate. Summary of the invention

[0004] To solve the above problems, the purpose of the embodiments of the present invention is to provide a method, device and electronic device for processing online course chat records.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing online course chat records, comprising:

[0006] When the time length from the last acquisition of the online course chat record reaches a preset time length, the online course chat record generated between the time when the chat record was last acquired and the current time is acquired;

[0007] Obtaining online course attendance information of the online course, wherein the online course attendance information carries the total number of students taking the online course;

[0008] Using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time, the current student's speaking ratio is obtained;

[0009] Analyze the online course chat records generated between the last time the chat records were obtained and the current time to determine the current student's emotional index in the online course and the current student's classroom water index;

[0010] The teaching quality of the online course is evaluated by using the speaking proportion of the current students, the emotional index of the current students in the online course, and the classroom water filling index of the current students.

[0011] In a second aspect, an embodiment of the present invention further provides an online course chat record processing device, comprising:

[0012] The first acquisition module is used to acquire the online course chat records generated between the time when the chat records were last acquired and the current time when the time length since the last acquisition of the online course chat records reaches a preset time length;

[0013] A second acquisition module is used to acquire the online course participant information of the online course, wherein the online course participant information carries the total number of students taking the online course;

[0014] The first processing module is used to obtain the speaking ratio of the current students by using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time;

[0015] The second processing module is used to analyze the online course chat records generated between the time when the chat records were last obtained and the current time, and determine the current student's emotional index in the online course and the current student's classroom water index;

[0016] The third processing module is used to evaluate the teaching quality of the online course by using the current student's speaking ratio, the current student's emotional index in the online class, and the current student's classroom water filling index.

[0017] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are executed.

[0018] In a fourth aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor and one or more programs, wherein the one or more programs are stored in the memory and configured so that the processor executes the steps of the method described in the first aspect above.

[0019] In the solutions provided in the first to fourth aspects of the embodiments of the present invention, by analyzing the chat records generated by the current students in the online course, the current student's speech ratio, the current student's emotional index in the online class and the current student's classroom water index are obtained, and the quality of the teacher's teaching is analyzed using the obtained current student's speech ratio, classroom emotional index and classroom water index. Compared with the method in the related art that can only evaluate the teaching quality of the online course teacher indirectly from the conversion rate, renewal rate and other aspects, the teaching quality of the online course teacher can be evaluated more directly and objectively from the parameters related to classroom teaching, such as the current student's speech ratio, the current student's emotional index in the online class and the current student's classroom water index.

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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.

[0022] Figure 1 A flowchart of a method for processing online course chat records provided by Embodiment 1 of the present invention is shown;

[0023] Figure 2 A schematic diagram showing the structure of an online course chat record processing device provided by Embodiment 2 of the present invention is shown;

[0024] Figure 3 A schematic structural diagram of an electronic device provided by Embodiment 3 of the present invention is shown. DETAILED DESCRIPTION

[0025] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0026] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0027] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like 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 it can be 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 according to specific circumstances.

[0028] At present, with the gradual development of online education, more and more parents choose online courses as a supplement to their children's extracurricular tutoring. However, how to evaluate the teaching quality of online teachers, how to understand whether the teacher is engaged in the current class, and whether the children really understand what the teacher says, has gradually become a new issue that needs to be solved urgently. The evaluation of the teaching quality of online teachers is mainly reflected indirectly from the conversion rate and renewal rate, but reflecting the teaching quality of online teachers from the conversion rate and renewal rate is too one-sided and inaccurate.

[0029] By analyzing the chat records of students in class, we can get the students' enthusiasm for the course and the current students' acceptance of the teacher's content. At the same time, through cluster analysis of students' chat records, we can know whether students are spamming in class and obtain the spamming index of students' chat records, thereby reflecting the quality of the teacher's class. This application is based on a deep learning model and uses the principle of transfer learning. It can obtain better results of students' classroom emotional tendencies through very few labeled data. At the same time, using a deep learning model trained based on massive data, it can effectively extract sentence vectors, and then through cosine distance calculation, it can reflect the discrete degree of students' classroom chat content, and finally reflect the quality of the teacher's class.

[0030] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0031] Example 1

[0032] This embodiment introduces a method for processing online course chat records, and the execution subject is a server.

[0033] See also Figure 1 The flowchart of a method for processing online course chat records is shown in FIG. 1 . This embodiment proposes a method for processing online course chat records, including the following specific steps:

[0034] Step 100: When the time length from the last acquisition of the online course chat record reaches a preset time length, the online course chat record generated between the time when the chat record was last acquired and the current time is acquired.

[0035] In the above step 100, the preset time length can be set to any time length between 10 seconds and 60 seconds.

[0036] The online course chat records are stored in the server, and the online course chat records carry the time when the chat records were generated and the student ID of the student who generated the chat records. Therefore, the server can query and process the online course chat records generated between the time when the chat records were last obtained and the current time according to the time when the chat records were generated.

[0037] Step 102: Obtain the online course participant information of the online course, wherein the online course participant information carries the total number of students taking the online course.

[0038] In the above step 102, the online course participation information is stored in the server. The total number of students attending the online course carried in the online course participation information is obtained by the server by counting the number of students entering the online course room before the online course starts, and the total number of students attending the online course is stored in the online course participation information.

[0039] Step 104: derive the speaking ratio of the current students by using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time.

[0040] In the above step 104, in order to obtain the current student's speaking ratio, the following steps (1) to (2) may be performed:

[0041] (1) using the student IDs carried in the online course chat records generated between the last time the chat records were obtained and the current time, counting the number of students currently speaking;

[0042] (2) The speaking ratio of the current students is calculated by using the statistical number of students currently speaking / the total number of students attending the online course.

[0043] In the above step (1), the number of students currently speaking refers to the number of students who have spoken between the time when the chat record was last obtained and the current time.

[0044] Step 106: Analyze the online course chat records generated between the last time the chat records were obtained and the current time to determine the current student's emotional index in the online course and the current student's classroom water index.

[0045] In the above step 106, in order to determine the current student's emotional index in the online class and the current student's class watering index, the following steps (1) to (12) may be performed:

[0046] (1) filtering out invalid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, obtaining valid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, and counting the number of chat record entries in the valid chat records;

[0047] (2) When the number of valid chat records is greater than or equal to a chat record threshold, performing a word segmentation operation on each chat record entry in the valid chat records to obtain words constituting the valid chat records;

[0048] (3) counting the total number of words in the valid chat record and the number of occurrences of the words constituting the valid chat record in the valid chat record, and calculating the word frequency of the words in the valid chat record by using the number of occurrences of the words constituting the valid chat record in the valid chat record and the total number of words in the valid chat record;

[0049] (4) counting the number of chat record entries containing the term in the valid chat record, and calculating the inverse document frequency of the term in the online course chat record generated between the time when the chat record was last obtained and the current time by using the number of chat record entries containing the term and the number of chat record entries in the valid chat record;

[0050] (5) calculating the word frequency-inverse document frequency of the words in the valid chat record according to the obtained word frequency and the inverse document frequency;

[0051] (6) Using a word embedding model (word2vec model) to process the words in the valid chat records to obtain word vectors of the words, and using the word frequency-inverse document frequency and word vector of the words to calculate the weighted word vector of the words;

[0052] (7) Accumulating the weighted word vectors of the words constituting each chat record entry to obtain a first accumulated result;

[0053] (8) Counting the number of words included in each chat record entry in the valid chat record, and using the first accumulation result of each chat record entry and the number of words included in each chat record entry to calculate the average vector representation of each chat record entry;

[0054] (9) accumulating the average vector representations of all chat record entries in the valid chat record to obtain a second accumulated result, and performing an average calculation on the second accumulated result to obtain a topic vector representation of the chat content indicated by the valid chat record;

[0055] (10) calculating the distance between the average vector representation of the chat record entries and the subject vector representation;

[0056] (11) determining the chat record entries whose calculated distance is less than the distance threshold as spam chat records;

[0057] (12) Counting the number of the spam chat records, and calculating the proportion of the spam chat records in the valid chat records based on the number of the spam chat records obtained by counting and the number of chat record entries in the valid chat records, and determining the proportion of the spam chat records as the classroom spam index.

[0058] In the above step (1), the server determines whether the online course chat records generated between the last time the chat records were obtained and the current time can be queried in the invalid chat record dictionary. If so, it means that the online course chat records generated between the last time the chat records were obtained and the current time are invalid chat records. Then, the server deletes the invalid chat records generated between the last time the chat records were obtained and the current time, thereby performing the operation of filtering out the invalid chat records in the online course chat records generated between the last time the chat records were obtained and the current time.

[0059] The invalid chat record dictionary records but is not limited to: emoticons and single characters. The characters can be but are not limited to: English characters, Greek characters and Roman characters.

[0060] In the above step (2), the chat record threshold can be set to any value between 30 and 80, which will not be described in detail here.

[0061] The specific process of performing word segmentation operation on each chat record item in the valid chat record to obtain the words constituting the valid chat record is prior art and will not be described in detail here.

[0062] In the above step (3), when counting the total number of words in the valid chat record, if a word appears repeatedly in the valid chat record, the number of times the word appears repeatedly in the valid chat record needs to be recorded in the total number of words.

[0063] The frequency of words in the valid chat records is calculated using the following formula:

[0064] Frequency of words in valid chat records = number of occurrences of words in valid chat records in the valid chat records / total number of words in the valid chat records

[0065] In the above step (4), counting the number of chat record entries containing the word in the valid chat record is a statistical result obtained by counting the number of chat record entries containing different words in the valid chat record.

[0066] The inverse document frequency of a word in the online course chat record generated between the time when the chat record was last obtained and the current time is calculated by the following formula:

[0067] The inverse document frequency of a word in the online course chat records generated between the last time the chat records were obtained and the current time = log [the number of chat record entries / (the number of chat record entries in the valid chat records containing the word + 1)]

[0068] In the above step (5), the word frequency-inverse document frequency of the words in the valid chat record is calculated by the following formula:

[0069] The word frequency in the effective chat record - the inverse document frequency = the inverse document frequency of the word in the online course chat record generated between the last time the chat record was obtained and the current time * the word frequency in the effective chat record

[0070] In the above step (6), the specific process of using the word embedding model (word2vec model) to process the words in the valid chat records to obtain the word vectors of the words is a prior art and will not be described here one by one.

[0071] The weighted word vector of the word is calculated by the following formula:

[0072] Weighted word vector of a word = word vector of the word * word frequency of the word - inverse document frequency

[0073] In the above step (8), the average vector representation of each chat record entry is calculated by the following formula:

[0074] Average vector representation of chat log entries = first accumulation result of chat log entries / number of words included in the chat log entries

[0075] In the above step (9), the second accumulated result is averaged by the following formula to obtain the topic vector representation of the chat content indicated by the valid chat record:

[0076] The topic vector representation of the chat content indicated by the valid chat record = the second accumulation result / the number of chat record entries

[0077] In the above step (10), the distance between the average vector representation of the chat record entries and the topic vector representation is calculated, which may be but is not limited to: Euclidean distance and cosine distance.

[0078] The specific process of calculating the Euclidean distance or cosine distance between the average vector representation of the chat record entries and the subject vector representation is prior art and will not be described in detail here.

[0079] In the above step (11), the distance threshold can be set to any value less than or equal to 0.3, which will not be described in detail here.

[0080] In the above step (12), the proportion of spam chat records in the valid chat records is calculated by the following formula:

[0081] The proportion of spam chat records = the number of spam chat records / the number of chat record entries

[0082] After determining the current student's class watering index through the above steps (1) to (12), the following steps (21) to (24) may be continued to determine the current student's emotion index in the online class:

[0083] (21) inputting each chat record item in the valid chat record into a sentiment classification model to obtain a sentiment classification result of each chat record item; the sentiment classification result includes: positive sentiment, negative sentiment, and neutral sentiment;

[0084] (22) respectively counting the number of first chat record entries with positive emotions, the number of second chat record entries with negative emotions, and the number of third chat record entries with neutral emotions;

[0085] (23) determining the emotion classification result corresponding to the largest number of items among the first number of items, the second number of items, and the third number of items as the current student's emotional tendency in the online class;

[0086] (24) The current student's emotional index in the online class is determined by the following formula:

[0087] The current student's emotional index in the online class = (number of second items - number of first items) / (number of first items + number of second items + number of third items).

[0088] In the above step (21), the emotion classification model is obtained by pre-training a deep learning model using chat records with different emotions (positive emotions, negative emotions and neutral emotions).

[0089] In one embodiment, chat records with positive emotions include, but are not limited to: chat records in which students express affirmation of the online course teacher's teaching, such as "the teacher's explanation is very clear" and "this class is so interesting"; chat records with negative emotions include, but are not limited to: chat records in which students express dissatisfaction with the teacher's teaching, such as "the explanation is not clear at all, I am confused" and "this class is so boring, I don't want to listen to it"; chat records with neutral emotions mainly refer to chat records that express emotions between positive and negative emotions and chat records that are not related to the class.

[0090] The specific process of inputting each chat record item in the valid chat record into the emotion classification model to obtain the emotion classification result of each chat record item is prior art and will not be described in detail here.

[0091] After determining the current student's emotion index in the online class and the current student's class watering index, the following step 108 may be continued to evaluate the teaching quality of the online class.

[0092] Step 108: Evaluate the teaching quality of the online course by using the current student's speaking ratio, the current student's emotional index in the online course, and the current student's classroom water index.

[0093] In the above step 108, the evaluation index of the teaching quality of the online course can be calculated by the following formula:

[0094] Evaluation index of teaching quality = w1*current student speech ratio + w2*current student emotional index in online class + w3*classroom watering index

[0095] Among them, w1, w2 and w3 are preset parameters.

[0096] Optionally, w1, w2 and w3 can also be obtained by training a linear regression model. The specific process of obtaining w1, w2 and w3 by training a linear regression model is prior art and will not be described in detail here.

[0097] From the above content, we can determine that based on the deep learning model and using the principle of transfer learning, we can get better results of students' classroom emotional tendencies through very small amounts of labeled data. At the same time, by using the deep learning model trained on massive data, we can effectively extract sentence vectors, and then through cosine distance calculation, we can reflect the degree of discreteness of students' classroom chat content, and ultimately reflect the quality of the teacher's class.

[0098] In summary, this embodiment proposes a method for processing online course chat records, by analyzing the chat records generated by the current students in the online course, to obtain the current student's speech ratio, the current student's emotional index in the online class and the current student's classroom water index, so as to use the obtained current student's speech ratio, classroom emotional index and classroom water index to analyze the quality of the teacher's teaching. Compared with the method in the related art that can only evaluate the teaching quality of the online course teacher indirectly from the conversion rate, renewal rate and other aspects, the teaching quality of the online course teacher can be evaluated more directly and objectively from the parameters related to classroom teaching, such as the current student's speech ratio, the current student's emotional index in the online class and the current student's classroom water index.

[0099] Example 2

[0100] This embodiment provides an online course chat record processing device, which is used to execute the online course chat record processing method proposed in the above embodiment 1.

[0101] See also Figure 2 The structure diagram of an online course chat record processing device shown in FIG. 1 is a schematic diagram of an online course chat record processing device, and this embodiment proposes an online course chat record processing device, including:

[0102] The first acquisition module 200 is used to acquire the online course chat records generated between the time when the chat records were last acquired and the current time when the time length since the last acquisition of the online course chat records reaches a preset time length;

[0103] The second acquisition module 202 is used to acquire the online course participant information of the online course, wherein the online course participant information carries the total number of students taking the online course;

[0104] The first processing module 204 is used to obtain the current student's speaking ratio by using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time;

[0105] The second processing module 206 is used to analyze the online course chat records generated between the last time the chat records were obtained and the current time, and determine the current student's emotional index in the online course and the current student's classroom water index;

[0106] The third processing module 208 is used to evaluate the teaching quality of the online course by using the current student's speaking ratio, the current student's emotional index in the online course, and the current student's classroom water index.

[0107] Specifically, the chat record carries a student ID of a student who generated the chat record; and the first processing module is specifically used to:

[0108] Using the student IDs carried in the online course chat records generated between the last time the chat records were obtained and the current time, counting the number of students currently speaking;

[0109] The speaking ratio of the current students is calculated by using the statistically obtained number of students currently speaking / the total number of students attending the online course.

[0110] Specifically, the second processing module is used to analyze the online course chat records generated between the time when the chat records were last obtained and the current time to determine the current student's class watering index, including:

[0111] Filter out invalid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, obtain valid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, and count the number of chat record entries in the valid chat records;

[0112] When the number of the valid chat records is greater than or equal to the chat record threshold, performing a word segmentation operation on each chat record entry in the valid chat records to obtain words constituting the valid chat records;

[0113] Counting the total number of words in the valid chat record and the number of occurrences of the words constituting the valid chat record in the valid chat record, and calculating the word frequency of the words in the valid chat record by using the number of occurrences of the words constituting the valid chat record in the valid chat record and the total number of words in the valid chat record;

[0114] Counting the number of chat record entries containing the word in the valid chat record, and using the number of chat record entries containing the word and the number of chat record entries in the valid chat record, calculating the inverse document frequency of the word in the online course chat record generated between the time when the chat record was last obtained and the current time;

[0115] Calculating the word frequency-inverse document frequency of the words in the valid chat record according to the obtained word frequency and the inverse document frequency;

[0116] The words in the valid chat records are processed using a word embedding model word2vec model to obtain word vectors of the words, and the weighted word vectors of the words are calculated using the word frequency-inverse document frequency and word vector of the words;

[0117] Accumulate the weighted word vectors of the words constituting each chat record entry to obtain a first accumulated result after accumulation;

[0118] Counting the number of words included in each chat record entry in the valid chat record, and calculating the average vector representation of each chat record entry by using the first accumulation result of each chat record entry and the number of words included in each chat record entry;

[0119] Accumulating the average vector representations of all chat record entries in the valid chat record to obtain a second accumulated result, and performing an average calculation on the second accumulated result to obtain a topic vector representation of the chat content indicated by the valid chat record;

[0120] Calculate the distance between the average vector representation of the chat record entries and the topic vector representation;

[0121] Determine the chat record entries whose calculated distance is less than the distance threshold as spam chat records;

[0122] The number of the water chat records is counted, and based on the number of the water chat records obtained by counting and the number of chat record entries in the valid chat records, the proportion of the water chat records in the valid chat records is calculated, and the proportion of the water chat records is determined as the classroom watering index.

[0123] In summary, this embodiment proposes an online course chat record processing device, which analyzes the chat records generated by the current students in the online course to obtain the current student's speech ratio, the current student's emotional index in the online course and the current student's classroom water index, so as to analyze the quality of the teacher's teaching by using the obtained current student's speech ratio, classroom emotional index and classroom water index. Compared with the related art that can only evaluate the teaching quality of the online course teacher indirectly from the conversion rate, renewal rate and other aspects, the teaching quality of the online course teacher can be evaluated more directly and objectively from the parameters related to classroom teaching, such as the current student's speech ratio, the current student's emotional index in the online course and the current student's classroom water index.

[0124] Example 3

[0125] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the online class chat record processing method described in the above embodiment 1 are executed. For specific implementation, please refer to method embodiment 1, which will not be repeated here.

[0126] In addition, see Figure 3The structural diagram of an electronic device shown in FIG. 1 is a schematic diagram of a structure of an electronic device. This embodiment further provides an electronic device, which includes a bus 51 , a processor 52 , a transceiver 53 , a bus interface 54 , a memory 55 and a user interface 56 . The electronic device includes a memory 55 .

[0127] In this embodiment, the electronic device further includes: one or more programs stored in the memory 55 and executable on the processor 52, and configured to be executed by the processor to perform the following steps (1) to (5):

[0128] (1) When the time length from the last time the online course chat record was obtained reaches a preset time length, the online course chat record generated between the time when the chat record was last obtained and the current time is obtained;

[0129] (2) obtaining online course participant information of the online course, wherein the online course participant information includes the total number of students taking the online course;

[0130] (3) using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time, to obtain the current student's speaking ratio;

[0131] (4) analyzing the online course chat records generated between the last time the chat records were obtained and the current time, and determining the current student's emotional index in the online course and the current student's classroom water index;

[0132] (5) The teaching quality of the online course is evaluated by using the current student's speaking ratio, the current student's emotional index in the online course, and the current student's classroom water index.

[0133] The transceiver 53 is used to receive and send data under the control of the processor 52.

[0134] Among them, the bus architecture (represented by bus 51), bus 51 can include any number of interconnected buses and bridges, and bus 51 links various circuits including one or more processors represented by processor 52 and memory represented by memory 55. Bus 51 can also link various other circuits such as peripherals, voltage regulators, and power management circuits together, which are all well known in the art, so this embodiment will not be further described. Bus interface 54 provides an interface between bus 51 and transceiver 53. Transceiver 53 can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. For example: transceiver 53 receives external data from other devices. Transceiver 53 is used to send data processed by processor 52 to other devices. Depending on the nature of the computing system, a user interface 56, such as a keypad, display, speaker, microphone, joystick, can also be provided.

[0135] The processor 52 is responsible for managing the bus 51 and general processing, such as running a general operating system as mentioned above, while the memory 55 can be used to store data used by the processor 52 when performing operations.

[0136] Optionally, the processor 52 may be, but is not limited to: a central processing unit, a single-chip microcomputer, a microprocessor or a programmable logic device.

[0137] It can be understood that the memory 55 in the embodiment of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. 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 RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (DRRAM). The memory 55 of the system and method described in the present embodiment is intended to include but is not limited to these and any other suitable types of memory.

[0138] In some implementations, the memory 55 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof: an operating system 551 and application programs 552 .

[0139] The operating system 551 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 552 includes various application programs, such as a media player (MediaPlayer), a browser (Browser), etc., which are used to implement various application services. The program for implementing the method of the embodiment of the present invention can be included in the application 552.

[0140] In summary, the present embodiment proposes a computer-readable storage medium and an electronic device, which analyze the chat records generated by the current students in the online course to obtain the current student's speech ratio, the current student's emotional index in the online course and the current student's classroom water index, so as to analyze the quality of the teacher's teaching by using the obtained current student's speech ratio, classroom emotional index and classroom water index. Compared with the method in the related art that can only evaluate the teaching quality of the online course teacher indirectly from the conversion rate, renewal rate and other aspects, the teaching quality of the online course teacher can be evaluated more directly and objectively from the parameters related to classroom teaching, such as the current student's speech ratio, the current student's emotional index in the online course and the current student's classroom water index.

[0141] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for processing online course chat records, characterized in that: include: When the time length from the last acquisition of the online course chat record reaches a preset time length, the online course chat record generated between the time when the chat record was last acquired and the current time is acquired; Obtaining online course attendance information of the online course, wherein the online course attendance information carries the total number of students taking the online course; Using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time, the current student's speaking ratio is obtained; Analyze the online course chat records generated between the last time the chat records were obtained and the current time to determine the current student's emotional index in the online course and the current student's classroom water index; The teaching quality of the online course is evaluated by using the current student's speaking ratio, the current student's emotional index in the online course, and the current student's classroom watering index; Analyze the online course chat records generated between the last time the chat records were obtained and the current time to determine the current student's class watering index, including: Filter out invalid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, obtain valid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, and count the number of chat record entries in the valid chat records; When the number of the valid chat records is greater than or equal to the chat record threshold, performing a word segmentation operation on each chat record entry in the valid chat records to obtain words constituting the valid chat records; Counting the total number of words in the valid chat record and the number of occurrences of the words constituting the valid chat record in the valid chat record, and calculating the word frequency of the words in the valid chat record by using the number of occurrences of the words constituting the valid chat record in the valid chat record and the total number of words in the valid chat record; Counting the number of chat record entries containing the word in the valid chat record, and using the number of chat record entries containing the word and the number of chat record entries in the valid chat record, calculating the inverse document frequency of the word in the online course chat record generated between the time when the chat record was last obtained and the current time; Calculating the word frequency-inverse document frequency of the words in the valid chat record according to the obtained word frequency and the inverse document frequency; The words in the valid chat records are processed using a word embedding model word2vec model to obtain word vectors of the words, and the weighted word vectors of the words are calculated using the word frequency-inverse document frequency and word vector of the words; Accumulate the weighted word vectors of the words constituting each chat record entry to obtain a first accumulated result after accumulation; Counting the number of words included in each chat record entry in the valid chat record, and calculating the average vector representation of each chat record entry by using the first accumulation result of each chat record entry and the number of words included in each chat record entry; Accumulating the average vector representations of all chat record entries in the valid chat record to obtain a second accumulated result, and performing an average calculation on the second accumulated result to obtain a topic vector representation of the chat content indicated by the valid chat record; Calculate the distance between the average vector representation of the chat record entries and the topic vector representation; Determine the chat record entries whose calculated distance is less than the distance threshold as spam chat records; The number of the water chat records is counted, and based on the number of the water chat records obtained by counting and the number of chat record entries in the valid chat records, the proportion of the water chat records in the valid chat records is calculated, and the proportion of the water chat records is determined as the classroom watering index.

2. The method according to claim 1, characterized in that The chat record carries the student ID of the student who generated the chat record; The total number of students in the online course and the online course chat records generated between the last time the chat records were obtained and the current time are used to obtain the current student's speaking ratio, including: Using the student IDs carried in the online course chat records generated between the last time the chat records were obtained and the current time, counting the number of students currently speaking; The speaking ratio of the current students is calculated by using the statistically obtained number of students currently speaking / the total number of students attending the online course.

3. The method according to claim 1, characterized in that Analyzing the online course chat records generated between the last time the chat records were obtained and the current time to determine the current student's emotional index in the online course, including: Input each chat record item in the valid chat record into the emotion classification model to obtain the emotion classification result of each chat record item; the emotion classification result includes: positive emotion, negative emotion and neutral emotion; Counting the number of first chat record entries with positive emotions, the number of second chat record entries with negative emotions, and the number of third chat record entries with neutral emotions respectively; Determine the emotion classification result corresponding to the largest number of items among the first number of items, the second number of items, and the third number of items as the current student's emotional tendency in the online class; The current student's emotional index in the online class is determined by the following formula: The current student's emotional index in the online class = (the number of second items - the number of first items) / (the number of first items + the number of second items + the number of third items).

4. The method according to claim 1, characterized in that: The teaching quality of the online course is evaluated by using the current student's speaking ratio, the current student's evaluation parameter for the online course, and the current student's classroom watering index, including: The evaluation index of the teaching quality of the online course is calculated by the following formula: Evaluation index of teaching quality = w1*current student speech ratio + w2*current student emotional index in online class + w3*classroom watering index Among them, w1, w2 and w3 are preset parameters.

5. A device for processing online course chat records, characterized in that: include: The first acquisition module is used to acquire the online course chat records generated between the time when the chat records were last acquired and the current time when the time length since the last acquisition of the online course chat records reaches a preset time length; A second acquisition module is used to acquire the online course participant information of the online course, wherein the online course participant information carries the total number of students taking the online course; The first processing module is used to obtain the speaking ratio of the current students by using the total number of students in the online course and the online course chat records generated between the time when the chat records were last obtained and the current time; The second processing module is used to analyze the online course chat records generated between the time when the chat records were last obtained and the current time, and determine the current student's emotional index in the online course and the current student's classroom water index; The third processing module is used to evaluate the teaching quality of the online course by using the current student's speaking ratio, the current student's emotional index in the online course, and the current student's classroom water index; The second processing module is used to analyze the online course chat records generated between the last time the chat records were obtained and the current time to determine the current student's class watering index, including: Filter out invalid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, obtain valid chat records in the online course chat records generated between the last time the chat records were obtained and the current time, and count the number of chat record entries in the valid chat records; When the number of the valid chat records is greater than or equal to the chat record threshold, performing a word segmentation operation on each chat record entry in the valid chat records to obtain words constituting the valid chat records; Counting the total number of words in the valid chat record and the number of occurrences of the words constituting the valid chat record in the valid chat record, and calculating the word frequency of the words in the valid chat record by using the number of occurrences of the words constituting the valid chat record in the valid chat record and the total number of words in the valid chat record; Counting the number of chat record entries containing the word in the valid chat record, and using the number of chat record entries containing the word and the number of chat record entries in the valid chat record, calculating the inverse document frequency of the word in the online course chat record generated between the time when the chat record was last obtained and the current time; Calculating the word frequency-inverse document frequency of the words in the valid chat record according to the obtained word frequency and the inverse document frequency; The words in the valid chat records are processed using a word embedding model word2vec model to obtain word vectors of the words, and the weighted word vectors of the words are calculated using the word frequency-inverse document frequency and word vector of the words; Accumulate the weighted word vectors of the words constituting each chat record entry to obtain a first accumulated result after accumulation; Counting the number of words included in each chat record entry in the valid chat record, and calculating the average vector representation of each chat record entry by using the first accumulation result of each chat record entry and the number of words included in each chat record entry; Accumulating the average vector representations of all chat record entries in the valid chat record to obtain a second accumulated result, and performing an average calculation on the second accumulated result to obtain a topic vector representation of the chat content indicated by the valid chat record; Calculate the distance between the average vector representation of the chat record entries and the topic vector representation; Determine the chat record entries whose calculated distance is less than the distance threshold as spam chat records; The number of the water chat records is counted, and based on the number of the water chat records obtained by counting and the number of chat record entries in the valid chat records, the proportion of the water chat records in the valid chat records is calculated, and the proportion of the water chat records is determined as the classroom watering index.

6. The device according to claim 5, characterized in that The chat record carries the student ID of the student who generated the chat record; The first processing module is specifically used for: Using the student IDs carried in the online course chat records generated between the last time the chat records were obtained and the current time, counting the number of students currently speaking; The speaking ratio of the current students is calculated by using the statistically obtained number of students currently speaking / the total number of students attending the online course.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are executed.

8. An electronic device, characterized in that: The electronic device includes a memory, a processor and one or more programs, wherein the one or more programs are stored in the memory and are configured so that the processor executes the steps of the method according to any one of claims 1 to 4.

Images