A video live-streaming interactive method and system for investment advisory education

Abstract

This invention provides a video live-streaming interactive method and system for investment advisory teaching, belonging to the field of data processing technology. Specifically, it includes: interactively processing questions according to a recommended processing order; determining the matching between unresolved questions and questions from current users based on unresolved questions; when it is determined that the recommended processing order needs to be optimized based on the matching, acquiring new question data in real time; and determining the adjustment result of the recommended processing order for unresolved questions based on the new question data and the distribution data of unresolved users, thereby improving the efficiency and reliability of answer processing.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and in particular relates to a video live streaming interactive method and system for investment advisory teaching. Background Technology

[0002] During live streams, investment advisors often need to interact with viewers and provide targeted answers to their questions. However, when there are a large number of questions, investment advisors often cannot identify user questions in a timely and effective manner, leading to frequent screen clutter and making it even more difficult to meet the required efficiency in answering questions.

[0003] To address the aforementioned technical problems, existing solutions often involve parsing user data and classifying the issues based on the parsing results, then providing targeted responses. A similar technical solution is presented in invention patent application CN202010898365.6, "A Method for Prompting Information, a Computing Device, and a Storage Medium." However, this technical solution suffers from the following technical defects:

[0004] Existing technical solutions do not consider spamming users when performing interactive processing; these are users who repeatedly refresh the screen to ask questions before the questions are answered. This inevitably leads to other users' questions being buried, making it difficult to meet the requirements for efficiency and real-time performance of interactive processing. Therefore, how to use the identification and processing results of spamming users based on question type to determine differentiated interactive processing strategies and reduce the number of spamming questions has become an urgent technical problem to be solved.

[0005] To address the aforementioned technical issues, this application provides a video live-streaming interactive method and system for investment advisory education. Summary of the Invention

[0006] To achieve the objectives of this invention, the following technical solution is adopted:

[0007] Specifically, this application provides a video live-streaming interactive method for investment advisory education, which includes:

[0008] S1 uses the analysis results of the question data during the live video broadcast of investment advisory teaching to determine that when the distribution of the question type meets the requirements, it uses the screen-filling user data of the question type and the question time of the screen-filling users to determine the recommended processing order of the question type.

[0009] S3 recommends the processing order of problems during the live video broadcast based on the recommended processing order. Based on unresolved problems, it determines the matching situation between unresolved problems and the problems of the current users who are flooding the screen. When it is determined that the recommended processing order needs to be optimized based on the matching situation, it proceeds to the next step.

[0010] S4 acquires new problem data in real time, and uses the new problem data and the distribution data of users with unresolved problems to determine the adjustment result of the recommended processing order of unresolved problems.

[0011] The beneficial effects of this invention are as follows:

[0012] By matching unresolved issues with the current flood of questions from users, it is determined whether the recommended processing order needs to be optimized. This avoids the technical problem of mismatch between unresolved issues and the current flood of questions caused by using the recommended processing order for unresolved issues for a long time. By analyzing the matching of the current flood of questions, the recommended processing order can be dynamically adjusted, further reducing the risk of flooding the screen with questions from different users, and improving the timeliness and reliability of interactive processing.

[0013] By using data on newly added questions and the distribution data of users with unresolved questions, the recommended processing order for unresolved questions is determined. This takes into account the number of new questions, as well as the distribution and dispersion of users with both new and unresolved questions. This allows for the determination of the interference risk from users who flood the screen based on the number and distribution of new questions. Consequently, differentiated adjustments can be made based on the differences in interference risk, which not only reduces the difficulty of adjustment but also reduces the risk of users flooding the screen interfering with users' questions.

[0014] Furthermore, the type of question is determined based on the stock corresponding to the question, specifically classifying questions about the same stock into the same question type.

[0015] Optionally, the type of question is determined based on the parsing results of the question's keywords, specifically grouping questions with the same keywords into the same question type.

[0016] Furthermore, the discreteness of the problem distribution is determined based on the number of problem types and the number of problems of different types.

[0017] Furthermore, determining that the discrete distribution meets the requirements specifically includes:

[0018] The number of problem types is determined by the discrete distribution of problem types;

[0019] Based on the number of types, determine whether the discrete distribution meets the requirements.

[0020] Furthermore, the method for determining the adjustment result of the recommended processing order for the unresolved issues is as follows:

[0021] Based on the newly added question data, determine the number of new question types and the number of users asking questions in each of the different new question types;

[0022] Based on the newly added question data and the distribution data of users with unresolved questions, determine the number of users asking questions in the newly added question types and the change in the number of users asking questions in the unresolved questions.

[0023] Based on the number of newly added question types, the number of users asking questions within each of the newly added question types, and the change in the number of users asking unresolved questions, the adjustment result of the recommended processing order for the unresolved questions is determined.

[0024] Secondly, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described video live-streaming interactive method for investment advisory teaching when running the computer program.

[0025] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0026] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0027] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0028] Figure 1 This is a flowchart of a video live-streaming interactive method for investment advisory education;

[0029] Figure 2 This is a flowchart for determining whether the discrete distribution meets the requirements;

[0030] Figure 3 This is a flowchart illustrating the method for determining the recommended processing order of the problem;

[0031] Figure 4 It is a flowchart for determining the optimization process that requires a recommended processing order;

[0032] Figure 5It is a framework diagram of a computer system. Detailed Implementation

[0033] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0034] In this application, by determining the recommended processing order for different types of questions during the live video broadcast based on the number of users flooding the screen with questions, the investment advisors can answer and process questions according to the recommended order. This reduces the number of users flooding the screen, allowing investment advisors to more accurately identify different types of questions in real time. This enables them to answer the questions of interest to the current users in a timely manner, while also meeting the question-answering needs of users flooding the screen, thus reducing interference from users flooding the screen.

[0035] Example 1

[0036] like Figure 1 As shown, this application provides a video live-streaming interactive method for investment advisory teaching, specifically including:

[0037] S1 uses the analysis results of the question data during the live video broadcast of investment advisory teaching to determine that when the distribution of the question type meets the requirements, it uses the screen-filling user data of the question type and the question time of the screen-filling users to determine the recommended processing order of the question type.

[0038] Specifically, when the number of question types exceeds a preset threshold, it indicates that different users are concerned with different question types. Therefore, based on this, it is determined that the discrete distribution does not meet the requirements.

[0039] Furthermore, the type of question is determined based on the stock corresponding to the question, specifically classifying questions about the same stock into the same question type.

[0040] Optionally, the type of question is determined based on the parsing results of the question's keywords, specifically grouping questions with the same keywords into the same question type.

[0041] Furthermore, the discreteness of the problem distribution is determined based on the number of problem types and the number of problems of different types.

[0042] Specifically, such as Figure 2As shown, determining that the discrete distribution meets the requirements specifically includes:

[0043] The number of problem types is determined by the discrete distribution of problem types;

[0044] Based on the number of types, determine whether the discrete distribution meets the requirements.

[0045] It is understandable that when the number of types is large, specifically when the number of types exceeds the preset threshold, it indicates that different users are concerned with different types of issues. Therefore, based on this, it is determined that the discrete distribution does not meet the requirements.

[0046] In one possible embodiment, if the number of types is greater than 60, it is determined that the discrete distribution does not meet the requirements.

[0047] In one possible embodiment, the threshold for the number of types is determined based on the number of users interacting during the live stream. The more users there are, the greater the probability that user questions will be buried when there is a flood of comments, so the threshold for the number of types is smaller. In one possible embodiment, the threshold can be determined by the range of the number of users interacting: 100 when the number is between 0 and 1000, 80 when the number is between 1000 and 10000, and 70 in other cases.

[0048] Furthermore, when the classification discrete situation does not meet the requirements, the solution is processed according to the type of question with the most users who post the question in real time. When there are no users posting the question, the solution is processed according to the type of question with the number of users who asked the question in descending order.

[0049] Optionally, determining that the discreteness of the distribution meets the requirements specifically includes:

[0050] The number of problem types is determined by the discrete distribution of problem types;

[0051] The effective question types are determined based on the number of users associated with each question type.

[0052] Based on the number of valid problem types, determine whether the discrete distribution meets the requirements.

[0053] It is understood that when the number of valid question types is greater than the preset threshold for the number of valid question types, it is determined that the distribution dispersion does not meet the requirements. The valid question type is determined by the number of users who asked the question of the question type. Question types with more than 5 users who asked the question of the question type are considered valid question types.

[0054] In one possible embodiment, the recommended processing order for each type of question is determined from largest to smallest based on the number of users posting about each type of question in the most recent 5 minutes.

[0055] Furthermore, the "spam user" refers to a user who does not meet the requirement of asking the same type of question a number of times within a preset time period. In one possible embodiment, a user who has asked the same type of question more than 3 times in the most recent 5 minutes will be considered a spam user.

[0056] It should be noted that the "spam user data" refers to the number of users who spam the screen in the aforementioned types of questions.

[0057] Specifically, such as Figure 3 As shown, the method for determining the recommended processing order for the problem is as follows:

[0058] Based on the composition of the users who flood the screen in the aforementioned type of question, determine the number of users who flood the screen in the aforementioned type of question;

[0059] Based on the analysis results of the question time of the users who flooded the screen, it was determined that there were questions from users who flooded the screen in different time units within the preset time period;

[0060] Based on the presence of users flooding the screen within different time periods, determine the recommended processing order for the aforementioned types of problems.

[0061] It is understood that the value of the unit time period is between 10 seconds and 30 seconds, and can be set according to actual needs. The preset time period is the most recent five minutes.

[0062] Furthermore, based on the number of users posting questions within different time periods, a recommended processing order for the aforementioned types of questions is determined, specifically including:

[0063] The time period in which users flood the screen with information about this type of problem is used as the matching time period for this type of problem.

[0064] Based on the number of matching time periods, the recommended processing order for different types of problems is determined from largest to smallest.

[0065] S2 recommends the processing order of problems during the live video broadcast based on the recommended processing order. Based on unresolved problems, it determines the matching situation between unresolved problems and the problems of the current users who are flooding the screen. When it is determined that the recommended processing order needs to be optimized based on the matching situation, it proceeds to the next step.

[0066] Furthermore, the recommended processing order for handling issues during the live video broadcast, based on the aforementioned recommended processing order, specifically includes:

[0067] Based on the recommended processing order, the investment advisor is advised on the processing order for different types of questions. The investment advisor then answers the questions based on the recommended processing order or the questions asked by interested users.

[0068] Specifically, such as Figure 4 As shown, the optimization process that requires a recommended processing order includes:

[0069] Based on the matching of different unresolved issues with the current spam users' questions, determine that the questions asked within the most recent unit of time belong to the unresolved spam users and use them as the matching spam users;

[0070] The problem of spamming is identified by the distribution data of different unresolved issues among users who are spamming the screen within the most recent unit of time.

[0071] Based on the number of screen-filling issues, determine whether the recommended processing order needs to be optimized.

[0072] It should be noted that the "spam issue" refers to unresolved issues where the number of users matching the spam issue is too large within the most recent unit of time, that is, unresolved issues where the number of users matching the spam issue exceeds the preset threshold for matching spam users, or unresolved issues where users matching the spam issue exist in different time periods within the most recent unit of time.

[0073] In one possible embodiment, unresolved issues that match the percentage of users who posted the message within the most recent unit of time are greater than 0.1 are defined as posting issues. In other words, unresolved issues that match the percentage of users who posted the message within the most recent 2 minutes are greater than 0.1 are defined as postsing issues.

[0074] It is understandable that when there are a large number of issues, i.e., in one possible embodiment, when there are more than 5 issues, optimizing the recommended processing order would inevitably lead to excessively long problem resolution times and overwhelm the problem identification of other users. Therefore, the original recommended processing order is still followed.

[0075] S3 acquires new problem data in real time, and uses the new problem data and the distribution data of users with unresolved problems to determine the adjustment result of the recommended processing order of unresolved problems.

[0076] It is understood that the newly added question data includes the number of new question types and the number of users asking questions in different new question types. Specifically, it is determined based on the questioning results of users within the most recent preset time interval, and specifically based on the questioning results of users within the most recent 2 minutes.

[0077] Furthermore, the method for determining the adjustment result of the recommended processing order for the unresolved issues is as follows:

[0078] Based on the newly added question data, determine the number of new question types and the number of users asking questions in each of the different new question types;

[0079] Based on the newly added question data and the distribution data of users with unresolved questions, determine the number of users asking questions in the newly added question types and the change in the number of users asking questions in the unresolved questions.

[0080] Based on the number of newly added question types, the number of users asking questions within each of the newly added question types, and the change in the number of users asking unresolved questions, the adjustment result of the recommended processing order for the unresolved questions is determined.

[0081] Understandably, when the number of newly added question types is too large, that is, when there are newly added question types within a unit of time, i.e., when there are newly added question types every second or when the number of newly added question types in the most recent minute is greater than 20, in order to avoid interference from users who flood the screen in identifying the newly added question types, when there are question types that have been flooded by users, i.e., for question types that have been flooded by users in the most recent 15 seconds, the answer processing will directly be performed for question types that have been flooded by users.

[0082] Additionally, it should be noted that when the number of newly added question types is not excessive, it is necessary to further determine the number of users asking questions within each of the newly added question types and the change in the number of users asking unresolved questions. When the number of users asking questions within each of the different newly added question types and the change in the number of users asking unresolved questions are both less than a preset user number threshold, in one possible embodiment, it is within 5. Since the distribution of different question types is too discrete, in order to avoid interference from users spamming the screen in identifying the types of newly added questions, when there is a question type with users spamming the screen, that is, for question types with users spamming the screen in the last 15 seconds, the answering processing for question types with users spamming the screen is directly performed.

[0083] Furthermore, when the number of users asking questions in different types of new questions and the number of users asking unresolved questions are not both less than a preset user number threshold, it is then determined whether the recommended processing order for unresolved questions needs to be adjusted based on the composition data of users who flood the screen within the most recent preset time period. Specifically, if the proportion of time spent by users flooding the screen within the most recent preset time period is greater than a preset proportion threshold, in one possible embodiment, if users flood the screen for more than half of the time within the most recent minute, then the recommended processing order is readjusted based on the composition of users flooding the screen in different types of questions and the analysis results of the question asking time of the users flooding the screen. In other cases, there is no need to adjust the recommended processing order for the time being.

[0084] Optionally, the method for determining the adjustment result of the recommended processing order for unresolved issues is as follows:

[0085] Based on the newly added question data, determine the number of new question types and the number of users asking questions in each of the different new question types;

[0086] It is understandable that when the number of newly added question types is too large in the above steps, that is, when there are newly added question types within a unit of time, that is, when there are newly added question types every second or when the number of newly added question types in the most recent minute is greater than 20, in order to avoid interference from users who flood the screen to identify the newly added question types, when there are question types that have been flooded by users, that is, for question types that have been flooded by users in the most recent 15 seconds, the answer processing for question types that have been flooded by users will be directly performed.

[0087] Based on the newly added question data and the distribution data of users with unresolved questions, determine the number of users asking questions in the newly added question type and the change in the number of users asking questions in the unresolved questions. Based on the change in the number of users asking questions and the number of users asking questions, determine the discrete question type.

[0088] In one possible embodiment, the distributed discrete question type is the type of unresolved questions with a variable number less than a preset user number threshold and newly added unresolved questions with a number of users asking questions less than the preset user number threshold.

[0089] Understandably, if all newly added questions are of the distributed discrete question type, then to avoid interference from users who flood the screen in identifying the type of the newly added questions, when there is a question type that has been flooded by users, that is, a question type that has been flooded by users in the last 15 seconds, then the answering process will directly be performed for the question type that has been flooded by users.

[0090] Additionally, it should be noted that if the types of newly added questions do not all belong to the distributed discrete question type, the number of distributed discrete question types is obtained. When the number of distributed discrete question types does not meet the requirements, i.e., it is greater than the preset threshold for the number of distributed discrete question types, in order to avoid interference from users who flood the screen in identifying the type of newly added questions, if there is a type of question that has been flooded by users, i.e., a type of question that has been flooded by users in the last 15 seconds, the answer processing for the type of question that has been flooded by users will be directly performed.

[0091] Based on the number of newly added problem types and the distribution of discrete problem types, the adjustment result of the recommended processing order for the unresolved problems is determined.

[0092] Optionally, if the number of newly added question types is less than the preset threshold for the number of newly added types, and the number of discrete question types is less than the preset threshold for the number of discrete types, then there is no need to adjust the recommended processing order for the time being.

[0093] Additionally, it should be noted that if the number of newly added question types is not less than a preset threshold for the number of newly added types, or if the number of discretely distributed question types is not less than a preset threshold for the number of discrete types, and if the number of users asking questions in different newly added question types and the number of users asking unresolved questions are not both less than a preset threshold for the number of users, then it is determined whether the recommended processing order for unresolved questions needs to be adjusted based on the composition data of users who flood the screen within the most recent preset time period. Specifically, if the proportion of time spent by users who flood the screen within the most recent preset time period is greater than a preset proportion threshold, in one possible embodiment, if users who flood the screen exist for more than half of the time in the most recent minute, then the recommended processing order is readjusted based on the composition of users who flood the screen in different types of questions and the analysis results of the question asking time of the users who flood the screen. In other cases, there is no need to adjust the recommended processing order for the time being.

[0094] Example 2

[0095] Secondly, such as Figure 5 As shown, the present invention provides a computer system, including: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described video live-streaming interactive method for investment advisory teaching when running the computer program.

[0096] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0097] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0098] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A video live-streaming interactive method for investment advisory teaching, characterized in that, Specifically, it includes: By analyzing the problem data during live video teaching, and determining that the distribution of problem types meets the requirements, the recommended processing order for the problem types is determined by using the data of users who flood the screen with questions for the aforementioned problem types and the questioning time of those users. The recommended processing order is used to recommend the processing order of problems during the live video broadcast. Based on unresolved problems, the matching situation between unresolved problems and the problems of the current users who are flooding the screen is determined. When it is determined that the recommended processing order needs to be optimized based on the matching situation, the next step is taken. Real-time acquisition of new problem data, and determination of the adjustment result of the recommended processing order of unresolved problems based on the new problem data and the distribution data of users with unresolved problems; The method for determining the recommended processing order for the aforementioned problem is as follows: Based on the composition of the users who flood the screen in the aforementioned type of question, determine the number of users who flood the screen in the aforementioned type of question; Based on the analysis results of the question time of the users who flooded the screen, it was determined that there were questions from users who flooded the screen in different time units within the preset time period; Based on the presence of users flooding the screen within different time periods, determine the recommended processing order for the aforementioned types of problems; The method for determining the adjustment result of the recommended processing order for the unresolved issues is as follows: Based on the newly added question data, determine the number of new question types and the number of users asking questions in each of the different new question types; Based on the newly added question data and the distribution data of users with unresolved questions, determine the number of users asking questions in the newly added question types and the change in the number of users asking questions in the unresolved questions. Based on the number of newly added question types, the number of users asking questions within each of the newly added question types, and the change in the number of users asking unresolved questions, the adjustment result of the recommended processing order for the unresolved questions is determined.

2. The video live-streaming interactive method for investment advisory teaching as described in claim 1, characterized in that, The type of question is determined based on the stock corresponding to the question.

3. The video live-streaming interactive method for investment advisory teaching as described in claim 1, characterized in that, The discreteness of the distribution of the problems is determined based on the number of problem types and the number of problems of different types.

4. The video live-streaming interactive method for investment advisory teaching as described in claim 1, characterized in that, Determining that the discrete distribution meets the requirements specifically includes: The number of problem types is determined by the discrete distribution of problem types; Based on the number of types, determine whether the discrete distribution meets the requirements.

5. The video live-streaming interactive method for investment advisory teaching as described in claim 1, characterized in that, When the discrete distribution does not meet the requirements, the solution is processed based on the type of question with the largest number of users posting on the screen in real time. When there are no users posting on the screen, the solution is processed based on the type of question, from largest to smallest, according to the number of users asking the question.

6. The video live-streaming interactive method for investment advisory teaching as described in claim 1, characterized in that, The recommended processing order for handling issues during live video streaming, based on the aforementioned recommended processing order, specifically includes: Based on the recommended processing order, the investment advisor is advised on the order in which different types of questions should be processed.

7. The video live-streaming interactive method for investment advisory teaching as described in claim 1, characterized in that, The optimization process that requires a recommended processing order includes: Based on the matching of different unresolved issues with the current spam users' questions, determine that the questions asked within the most recent unit of time belong to the unresolved spam users and use them as the matching spam users; The problem of spamming is identified by the distribution data of different unresolved issues among users who are spamming the screen within the most recent unit of time. Based on the number of screen-filling issues, determine whether the recommended processing order needs to be optimized.

8. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a video live-streaming interactive method for investment advisory teaching as described in any one of claims 1-7.

Images