Intelligent question searching and self-adaptive recommendation system

Abstract

The invention relates to the technical field of question self-adaptive recommendation, in particular to an intelligent question searching and self-adaptive recommendation system. According to the system, related courses are recommended to a user by counting the question searching information during question searching, recommendation can be more accurately carried out in combination with user behaviors, and the number proportion of pushed test questions of a single subject is adjusted according to the number of types of knowledge points of each subject; after the number proportion of the pushed test questions of the single subject is adjusted, the number proportion of the pushed test questions of other subjects is adjusted in a self-adaptive mode, and therefore the test questions are recommended more effectively; meanwhile, whether recommendation of the test questions is qualified or not is determined according to the answer information of the recommended test questions answered by the user, and the corresponding adjustment instruction is generated based on the disqualification reasons, so that the effectiveness of the self-adaptive recommended test questions can be more accurately determined, and more effective adjustment can be performed for the disqualification reasons; and the learning efficiency of the user is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of adaptive question recommendation, and in particular to an intelligent question search and adaptive recommendation system. Background Art

[0002] Intelligent question search and adaptive recommendation systems can "precisely match needs" and "dynamically adapt to changes", which can save time and thus improve learning efficiency; it can also optimize resource allocation and improve educational equity; at the same time, it can promote the deep integration of AI and education, and provide infrastructure for future education models (such as lifelong learning and skills reshaping).

[0003] Chinese Patent Publication No.: CN109063182B discloses a content recommendation method and electronic device based on voice search, which includes: extracting a target question from an input search voice; determining whether answer information matching the target question is searched; if the answer information matching the target question is not searched, determining the target subject to which the target question belongs based on keywords identified from the target question; determining the target content with the highest matching degree with the target question from all teaching contents corresponding to the target subject; and outputting the target content.

[0004] It can be seen that the existing technology has the following problems: the existing technology fails to determine whether the test questions are qualified based on the answer information of the user's recommended test questions, and fails to make adjustments based on the reasons for failure, so the effectiveness of the adaptively recommended test questions cannot be determined, which leads to low learning efficiency of the user. Summary of the Invention

[0005] To this end, the present invention provides an intelligent question search and adaptive recommendation system to overcome the problem in the prior art that it is unable to determine whether a test question is qualified based on the answer information of the user's recommended test question, and is also unable to make adjustments based on the reasons for failure, thereby failing to determine the effectiveness of the adaptively recommended test questions, while reducing the push efficiency, and thus leading to lower learning efficiency for users.

[0006] To achieve the above objectives, the present invention provides an intelligent question search and adaptive recommendation system, comprising: A recognition module for recognizing a question input by a user; An output module, connected to the recognition module, for acquiring and outputting answers corresponding to the questions through big data; A statistics module, connected to the output module, for recording and counting question search information during question search, wherein the question search information includes subjects and knowledge points; A push module, connected to the statistics module, for pushing relevant test questions to the user based on the search question information; A recording module, connected to the push module, for recording the user's answer information when taking the test questions, wherein the answer information includes the answering time and score rate; an analysis module connected to the recording module, configured to determine whether the pushed test questions are qualified based on the obtained answer information, and to generate corresponding adjustment instructions based on the reasons for failure, wherein the adjustment instructions include adjusting the proportion of qualified subjects and the total number of pushed questions; An adjustment module is connected to the analysis module and is used to adjust the corresponding parameter to a corresponding value based on the received adjustment instruction.

[0007] Furthermore, the push module is also used to mark the proportion of each subject type that searches for questions within a preset time period as the proportion of push quantities of each subject during the push process; the push module is also used to correct the proportion of push quantities of each subject according to the number of knowledge point types in each subject; the push module is also used to increase the proportion of push quantities of each subject based on the number of knowledge point types, and the number of knowledge point types is proportional to the increase in the proportion of push quantities.

[0008] Furthermore, the push module is also used to adjust the push quantity ratio of each subject in sequence based on the adjusted push quantity ratio of a single subject to ensure that the sum of the push quantity ratios of each subject is 1; the push module is also used to determine the adjustment order of the push quantity ratio of each subject based on the ascending number of knowledge point types contained in all search questions of each subject; the push module is also provided with a critical push quantity ratio, and the push quantity ratio of each subject after adjustment is greater than or equal to the critical push quantity ratio.

[0009] Furthermore, the analysis module is also used to determine whether the push of test questions is qualified based on the accuracy rate of a single subject, and to determine the reason for the unqualified push of test questions based on the average answering time of the user or based on the variance of the accuracy rate of a single knowledge point, wherein the accuracy rate of a single knowledge point is the user's answer accuracy rate for all questions under the subject containing the same knowledge point.

[0010] Furthermore, the analysis module is also used to generate a corresponding processing method based on the comparison result of the user's average answering time and the preset answering time, including issuing a notification to adjust the push quantity ratio, or adjusting the total number of pushed questions based on the difference between the average answering time and the preset answering time.

[0011] Furthermore, the analysis module is also used to reduce the total number of pushed questions based on the difference between the average answering time and the preset answering time, and the difference is inversely proportional to the reduction in the total number of pushed questions.

[0012] Furthermore, the analysis module is also used to generate a corresponding processing method based on the comparison result of the variance of the accuracy of a single knowledge point and the preset variance, including determining the reason why the pushed questions are unqualified based on the proportion of qualified subjects, or adjusting the number of related questions of the knowledge points based on the accuracy of each knowledge point, wherein the qualified subjects are subjects whose variance of the accuracy of a single knowledge point is less than or equal to the preset variance.

[0013] Furthermore, the analysis module is also used to generate a corresponding processing method based on the comparison result of the proportion of qualified subjects and the preset proportion, including adjusting the number of pushed qualified subjects based on the absolute value of the slope of the forgetting curve predicted by the LSTM network, or adjusting the total number of pushed questions based on the difference between the proportion of qualified subjects and the preset proportion.

[0014] Furthermore, the analysis module is also used to reduce the push quantity of the qualified subjects according to the absolute value of the slope of the forgetting curve predicted by the LSTM network, and the absolute value of the slope is inversely proportional to the reduction degree of the push quantity of the qualified subjects.

[0015] Furthermore, the analysis module is also used to reduce the total number of pushed questions based on the difference between the proportion of qualified subjects and the preset proportion, and the difference is proportional to the reduction in the total number of pushed questions.

[0016] Compared with the prior art, the beneficial effect of the present invention is that the system recommends relevant courses to users by collecting statistics on search information during question search, and can make recommendations more accurately in combination with user behavior, and adjust the proportion of the number of pushed test questions for a single subject according to the number of types of knowledge points in each subject, and adaptively adjust the proportion of the number of pushed test questions for other subjects after adjusting the proportion of the number of pushed test questions for a single subject, thereby more effectively recommending test questions; at the same time, the system determines whether the recommendation of the test question is qualified based on the answer information of the user to the recommended test question, and generates corresponding adjustment instructions based on the reason for failure, which can more accurately determine the effectiveness of the adaptively recommended test question, and make more effective adjustments to the reason for failure, thereby further improving the user's learning efficiency.

[0017] Furthermore, the present invention also adjusts the push quantity ratio of each subject based on the difference between the number of knowledge point types of each subject and the preset number, which can more accurately adjust the push quantity ratio of each subject, thereby being able to recommend test questions to users more accurately, thereby further improving the user's learning efficiency.

[0018] Furthermore, the present invention also adjusts the push quantity ratio of each subject in sequence based on the adjusted push quantity ratio of a single subject, and determines the adjustment order of the push quantity ratio of each subject in ascending order according to the number of knowledge point types, so that the push quantity ratio of other subjects can be adjusted more accurately after the push quantity ratio of a single subject is adjusted.

[0019] Furthermore, the present invention also determines whether the push of test questions is qualified based on the accuracy of a single subject, which can more quickly determine whether the test questions are qualified, thereby more effectively determining whether the push is valid, thereby further improving the user's learning efficiency.

[0020] Furthermore, the present invention also makes a secondary judgment on whether the pushed test questions are qualified based on the comparison result of the user's average answering time and the preset answering time, which can more accurately determine whether the pushed test questions are qualified, thereby further improving the user's learning efficiency.

[0021] Furthermore, the present invention also reduces the total number of pushed questions based on the difference between the user's average answering time and the preset answering time, and can more accurately adjust the total number of pushed questions, thereby further improving the push efficiency and further improving the user's learning efficiency.

[0022] Furthermore, based on the comparison results of the variance of the accuracy of a single knowledge point and the preset variance, the present invention can more accurately determine the reasons for the failure of the pushed questions according to the mastery level of each knowledge point, thereby further improving the efficiency of pushing questions and further improving the learning efficiency of users.

[0023] Furthermore, the present invention also determines the reason for unqualified push based on the comparison result of the proportion of qualified subjects and the preset proportion, thereby judging the reason for unqualified pushed questions according to the user's mastery of each subject, and subsequently adjusting the pushed questions more accurately according to the reason, thereby further improving the user's learning efficiency.

[0024] Furthermore, the present invention also adjusts the push quantity of the qualified subjects based on the absolute value of the slope of the forgetting curve predicted by the LSTM network, and can gradually reduce the push quantity of the qualified subjects according to the user's memory situation, so that the push quantity of the qualified subjects can be adjusted more accurately, thereby further improving the user's learning efficiency.

[0025] Furthermore, the present invention also adjusts the total number of pushed questions based on the difference between the proportion of qualified subjects and the preset proportion, which can more accurately adjust the total number of pushed questions, thereby more effectively recommending according to the user's situation, thereby further improving the user's learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1This is a schematic diagram of the structure of the intelligent question search and adaptive recommendation system according to an embodiment of the present invention; Figure 2 A flowchart of the steps for implementing the intelligent question search and adaptive recommendation system according to an embodiment of the present invention; Figure 3 This is a flowchart of the steps for determining the comparison result of the accuracy rate of a single subject with the preset accuracy rate according to an embodiment of the present invention; Figure 4 This is a flowchart of the steps for determining the comparison result of the accuracy variance of a single knowledge point with a preset variance according to an embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0028] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0029] It should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0030] See also Figure 1 As shown, it is a structural diagram of the intelligent question search and adaptive recommendation system according to an embodiment of the present invention.

[0031] The system includes an identification module, an output module, a statistics module, a push module, a recording module, an analysis module and an adjustment module.

[0032] The recognition module is used to recognize the topic input by the user; The output module is connected to the recognition module and is used to obtain and output answers corresponding to the questions through big data; The statistical module is connected to the output module and is used to record and count the question search information when searching for questions, wherein the question search information includes subjects and knowledge points; The push module is connected to the statistics module and is used to push relevant test questions to the user based on the search question information; The recording module is connected to the push module and is used to record the user's answer information when taking the test questions, wherein the answer information includes the answering time and score rate; The analysis module is connected to the recording module and is used to determine whether the pushed test questions are qualified based on the obtained answer information, and generate corresponding adjustment instructions based on the reasons for failure, wherein the adjustment instructions include adjusting the proportion of qualified subjects and adjusting the total number of pushed questions; The adjustment module is connected to the analysis module, and is configured to adjust a corresponding parameter to a corresponding value based on the received adjustment instruction.

[0033] Specifically, in this embodiment, all recommended questions are multiple-choice questions. After the user inputs the question in the recognition module by taking a photo, text or voice, the output module in the system will output the answer corresponding to the question according to the question input by the user; at the same time, the statistics module will count and record based on the search record and the subject and knowledge point corresponding to the question, and use the push module to push relevant test questions to the user, so that the user can consolidate the learning of the knowledge point through multiple exercises; afterward, the recording module will record the user's answer information after pushing the question to the user according to the push module, such as the user's answer time and score rate; the analysis module will determine whether the recommendation of the test question is qualified based on the user's answer information, and determine the reason if it is unqualified, and generate corresponding adjustment instructions according to the reason; finally, the adjustment module will adjust the corresponding parameters based on the adjustment instructions determined according to the reason.

[0034] See also Figure 2 As shown, it is a flowchart of the steps of implementing the intelligent question search and adaptive recommendation system according to an embodiment of the present invention.

[0035] The implementation process based on intelligent question search and adaptive recommendation system includes: S1, identifying the question input by the user through the recognition module; S2, obtaining and outputting the answer corresponding to the question through big data via an output module connected to the recognition module; S3, recording and counting question search information during question search by a statistics module connected to the output module, wherein the question search information includes subjects and knowledge points; S4, pushing relevant test questions to the user based on the search question information through a push module connected to the statistics module; S5, recording the user's answer information when taking the test questions through a recording module connected to the push module, wherein the answer information includes the answering time and score rate; S6, determining, by an analysis module connected to the recording module, whether the pushed test questions are qualified based on the acquired answer information, and generating corresponding adjustment instructions based on the reasons for failure, wherein the adjustment instructions include adjusting the proportion of qualified subjects and adjusting the total number of pushed questions; S7: adjusting the corresponding parameter to the corresponding value based on the received adjustment instruction through the adjustment module connected to the analysis module.

[0036] Specifically, the push module in the embodiment of the present invention is also used to mark the proportion of each subject type that searches for questions within a preset time period as the push quantity proportion of each subject during the push process; the push module is also used to correct the push quantity proportion of each subject according to the number of knowledge point types in each subject; the push module is also used to increase the push quantity proportion of each subject based on the difference between the number of knowledge point types and the preset number, and the difference is proportional to the increase in the push quantity proportion.

[0037] Specifically, in this embodiment, the push quantity ratio of subjects whose number of knowledge point types is higher than the preset number is adjusted, wherein the preset difference G0=2. The specific process of comparing the difference G between the number of knowledge point types and the preset number with the preset difference G0 is as follows: If the difference G is less than or equal to the preset difference G0, the push quantity ratio of each subject is adjusted to 1.2 times the original push quantity ratio. It should be noted that the adjusted push quantity ratio is rounded upwards to an integer; If the difference G is less than or equal to the preset difference G0, the push quantity ratio of each subject is adjusted to 1.4 times the original push quantity ratio. It should be noted that the adjusted push quantity ratio is rounded up to an integer.

[0038] Specifically, the push module described in the embodiment of the present invention is also used to adjust the push quantity ratio of each subject in sequence based on the adjusted push quantity ratio of a single subject to ensure that the sum of the push quantity ratios of each subject is 1; the push module is also used to determine the adjustment order of the push quantity ratio of each subject based on the ascending number of knowledge point types contained in all search questions of each subject; the push module is also provided with a critical push quantity ratio, and the push quantity ratio of each subject after adjustment is greater than or equal to the critical push quantity ratio.

[0039] Specifically, in this embodiment, when adjusting the push quantity ratio of a single subject, if the push quantity ratio of the adjusted subject is less than the critical push quantity ratio, the push quantity ratio of the subject is adjusted to the critical push quantity ratio, and the push quantity ratio of the next subject is adjusted according to the determined adjustment order to ensure that the sum of the push quantity ratios of each subject is 1.

[0040] See also Figure 3 , which is a flowchart of the steps for determining the accuracy of a single subject based on the comparison result with the preset accuracy rate according to an embodiment of the present invention. The analysis module of the embodiment of the present invention is also used to determine whether the push of a test question is qualified based on the accuracy rate of the single subject, and to determine the reason for the failure of the push of a test question based on the average answering time of the user or the variance of the accuracy rate of a single knowledge point, wherein the accuracy rate of a single knowledge point is the accuracy rate of the user's answer to all questions in the subject that contain the same knowledge point.

[0041] Specifically, in this embodiment, the pushed questions are all multiple-choice questions. The accuracy of a single subject can be divided into a first preset accuracy rate L1 and a second preset accuracy rate L2. In the set accuracy rate standard, the first preset accuracy rate L1=60%, and the second preset accuracy rate L2=85%. It should be noted that, in other embodiments, the values ​​of L1 and L2 can also be determined based on the needs of adaptive recommendation; the comparison process based on the accuracy rate L with L1 and L2 is as follows: If the accuracy rate L is less than or equal to the first preset accuracy rate L1, it indicates that the user has a low level of mastery of the subject, and the push of the test questions is determined to be qualified; If the accuracy rate L is greater than the first preset accuracy rate L1 and less than the second preset accuracy rate L2, it means that it is impossible to determine whether other factors cause this result at this time, and the reason for the failure of the test question push is determined based on the user's average answering time P; If the accuracy rate L is greater than or equal to the second preset accuracy rate L2, it means that the user has a good grasp of the subject and the push of the test questions is judged to be unqualified. The reason for the unqualified push of the test questions is determined based on the variance Q of the accuracy rate of a single knowledge point.

[0042] Specifically, the analysis module described in the embodiment of the present invention is also used to generate a corresponding processing method based on the comparison result of the user's average answering time and the preset answering time, including issuing a notification to adjust the push quantity ratio, or adjusting the total number of pushed questions based on the difference between the average answering time and the preset answering time.

[0043] Specifically, in this embodiment, the preset answering time P0=1min, and the comparison process based on the average answering time P and the preset answering time P0 is as follows: If the average answering time P is greater than the preset answering time P0, it means that the user has not fully mastered the subject, and a notification is issued to adjust the push quantity ratio; If the average answering time P is less than or equal to the preset answering time P0, it means that the user has mastered the subject, and the total number of pushed questions is adjusted based on the difference R between the average answering time and the preset answering time.

[0044] Specifically, the analysis module in the embodiment of the present invention is also used to reduce the total number of pushed questions based on the difference between the average answering time and the preset answering time, and the difference is inversely proportional to the reduction in the total number of pushed questions.

[0045] Specifically, in this embodiment, the preset difference R0 between the average answering time and the preset answering time is 10s, and the comparison process based on the difference R and the preset difference R0 is as follows: If the difference R is less than or equal to the preset difference R0, the total number of pushed topics is adjusted to 0.6 times the original total number of pushed topics. It should be noted that the adjusted total number of pushed topics is rounded up; If the difference R is greater than the preset difference R0, the total number of pushed topics is adjusted to 0.9 times the original total number of pushed topics. It should be noted that the adjusted total number of pushed topics is rounded up.

[0046] See also Figure 4 As shown, it is a flowchart of the steps of determining the results of comparing the variance of the accuracy rate of a single knowledge point with a preset variance according to an embodiment of the present invention. The analysis module of the embodiment of the present invention is also used to generate corresponding processing methods based on the comparison results of the variance of the accuracy rate of a single knowledge point with the preset variance, including determining the reason for the failure of the pushed questions based on the proportion of qualified subjects, or adjusting the number of related questions of the knowledge point based on the accuracy rate of each knowledge point, wherein the qualified subjects are subjects with a variance of the accuracy rate of a single knowledge point less than or equal to the preset variance.

[0047] Specifically, in this embodiment, the preset variance Q0 based on the accuracy of a single knowledge point is 0.95, and the comparison process of the variance Q based on the accuracy of a single knowledge point and the preset variance Q0 is as follows: If the variance Q of the accuracy of a single knowledge point is less than or equal to the preset variance Q0, it means that the user has mastered all the knowledge points of the subject, then the subject is marked as a qualified subject, and the reason for the unqualified pushed questions is determined based on the proportion T of qualified subjects; If the variance Q of the accuracy of a single knowledge point is greater than the preset variance Q0, it means that the user has not mastered some knowledge points in the pushed subject, and the number of questions related to the knowledge point is adjusted based on the accuracy U of each knowledge point.

[0048] Specifically, in this embodiment, the specific process of adjusting the number of related questions of each knowledge point based on the accuracy rate of each knowledge point is as follows: under the premise of ensuring that the proportion of subjects and the total number of pushed questions do not change, the preset accuracy rate U0 of each knowledge point is set to 90%. The specific process of comparing the accuracy rate U of each knowledge point with the preset accuracy rate U0 is as follows: If the accuracy rate U is greater than or equal to the preset accuracy rate U0, the pushed questions related to the knowledge point are deleted; If the accuracy rate U is less than the preset accuracy rate U0, the number of pushed questions related to the knowledge point is increased.

[0049] Specifically, the analysis module described in the embodiment of the present invention is also used to generate a corresponding processing method based on the comparison result of the proportion of qualified subjects and the preset proportion, including adjusting the number of pushed qualified subjects based on the absolute value of the slope of the forgetting curve predicted by the LSTM network, or adjusting the total number of pushed questions based on the difference between the proportion of qualified subjects and the preset proportion.

[0050] Specifically, in this embodiment, the preset proportion of qualified subjects T0=0.8, and the comparison process based on the qualified subject proportion T and the preset proportion T0 is as follows: If the proportion T of qualified subjects is less than or equal to the preset proportion T0, the number of qualified subjects pushed is adjusted based on the absolute value H of the slope of the forgetting curve predicted by the LSTM network; If the proportion T of qualified subjects is greater than the preset proportion T0, it means that the user has a basic understanding of the pushed questions, and the total number of pushed questions is adjusted based on the difference I between the proportion of qualified subjects and the preset proportion.

[0051] Specifically, the analysis module of the embodiment of the present invention is also used to reduce the push quantity of the qualified subjects based on the absolute value of the slope of the forgetting curve predicted by the LSTM network, and the absolute value of the slope is inversely proportional to the reduction in the push quantity of the qualified subjects.

[0052] Specifically, in this embodiment, the preset absolute value H0 of the slope of the forgetting curve predicted by the LSTM network is 1.2. The comparison process of the absolute value H of the slope of the forgetting curve predicted by the LSTM network and the preset absolute value H0 is as follows: If the absolute value H of the slope of the forgetting curve predicted by the LSTM network is less than or equal to the preset absolute value H0, the push quantity of qualified subjects is adjusted to 0.5 times the original push quantity. It should be noted that the adjusted push quantity of qualified subjects is rounded up; If the absolute value H of the slope of the forgetting curve predicted by the LSTM network is greater than the preset absolute value H0, the push quantity of qualified subjects will be adjusted to 0.9 times the original push quantity. It should be noted that the adjusted push quantity of qualified subjects is rounded up.

[0053] Specifically, the analysis module described in the embodiment of the present invention is also used to reduce the total number of pushed questions based on the difference between the proportion of qualified subjects and the preset proportion, and the difference is proportional to the reduction in the total number of pushed questions.

[0054] Specifically, in this embodiment, the preset difference I0 between the proportion of qualified subjects and the preset proportion is 0.1, and the comparison process based on the difference I between the proportion of qualified subjects and the preset proportion and the preset difference I0 is as follows: If the difference between the proportion of qualified subjects and the preset proportion is less than or equal to the preset difference I0, the total number of pushed questions will be adjusted to 0.9 times the total number of originally pushed questions. It should be noted that the total number of pushed questions after adjustment will be rounded up; If the difference I between the proportion of qualified subjects and the preset proportion is greater than the preset difference I0, the total number of pushed questions will be adjusted to 0.7 times the total number of original pushed questions. It should be noted that the adjusted total number of pushed questions will be rounded up.

[0055] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention. Example 1

[0056] In this embodiment, when the push quantity ratio of a subject increases, the specific process of adjusting the push quantity ratio of other subjects is as follows: assuming that there are three subjects, namely Chinese, mathematics and English, and the number of knowledge points involved in each subject is specifically the number of knowledge points involved in Chinese > the number of knowledge points involved in English > the number of knowledge points involved in mathematics. After adjusting the push quantity ratio of Chinese from the initial value of 30% to 50%, the push quantity ratio of mathematics is adjusted first. The initial value of the push quantity ratio of mathematics is 25%. Generally speaking, the push quantity ratio of mathematics should be adjusted from 25% to 5%. However, since the critical ratio is set to 10%, the push quantity ratio of mathematics is adjusted to 10%; finally, the push quantity ratio of English is adjusted from the initial value of 45% to 40%.

[0057] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0058] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. An intelligent question search and adaptive recommendation system, characterized by: include: A recognition module for recognizing a question input by a user; An output module, connected to the recognition module, for acquiring and outputting answers corresponding to the questions through big data; A statistics module, connected to the output module, for recording and counting question search information during question search, wherein the question search information includes subjects and knowledge points; A push module, connected to the statistics module, for pushing relevant test questions to the user based on the search question information; A recording module, connected to the push module, for recording the user's answer information when taking the test questions, wherein the answer information includes the answering time and score rate; an analysis module connected to the recording module, configured to determine whether the pushed test questions are qualified based on the obtained answer information, and to generate corresponding adjustment instructions based on the reasons for failure, wherein the adjustment instructions include adjusting the proportion of qualified subjects and the total number of pushed questions; An adjustment module is connected to the analysis module and is used to adjust the corresponding parameter to a corresponding value based on the received adjustment instruction.

2. The intelligent question search and adaptive recommendation system according to claim 1, characterized in that: The push module is further used to mark the proportion of each subject type searched within a preset time as the proportion of push quantity of each subject in the push process; The push module is further configured to modify the push quantity ratio of each subject according to the number of knowledge point types in each subject; The push module is further configured to increase the push quantity ratio of each subject based on the difference between the number of the knowledge point types and a preset number, and the difference is proportional to the increase in the push quantity ratio.

3. The intelligent question search and adaptive recommendation system according to claim 2, characterized in that: The push module is further configured to sequentially adjust the push quantity ratio of each subject based on the adjusted push quantity ratio of the single subject to ensure that the sum of the push quantity ratios of each subject is 1; The push module is further configured to determine an adjustment order of the push quantity proportion of each subject based on the number of knowledge point types included in all search questions of each subject in ascending order; The push module is further provided with a critical push quantity ratio, and the push quantity ratio of each of the subjects after adjustment is greater than or equal to the critical push quantity ratio.

4. The intelligent question search and adaptive recommendation system according to claim 1, characterized in that: The analysis module is also used to determine whether the push of test questions is qualified based on the accuracy rate of a single subject, and to determine the reason for the unqualified push of test questions based on the average answering time of the user or the variance of the accuracy rate of a single knowledge point, wherein the accuracy rate of a single knowledge point is the accuracy rate of the user's answers to all questions under the subject that contain the same knowledge point.

5. The intelligent question search and adaptive recommendation system according to claim 4, characterized in that: The analysis module is also used to generate a corresponding processing method based on the comparison result of the user's average answering time and the preset answering time, including issuing a notification to adjust the push quantity ratio, or adjusting the total number of pushed questions based on the difference between the average answering time and the preset answering time.

6. The intelligent question search and adaptive recommendation system according to claim 5, characterized in that: The analysis module is further configured to reduce the total number of pushed questions based on the difference between the average answering time and the preset answering time, and the difference is inversely proportional to the extent of the reduction in the total number of pushed questions.

7. The intelligent question search and adaptive recommendation system according to claim 4, characterized in that: The analysis module is also used to generate a corresponding processing method based on the comparison result of the variance of the accuracy rate of a single knowledge point and the preset variance, including determining the reason why the pushed questions are unqualified based on the proportion of qualified subjects, or adjusting the number of related questions of the knowledge points based on the accuracy rate of each knowledge point, wherein the qualified subjects are subjects whose variance of the accuracy rate of a single knowledge point is less than or equal to the preset variance.

8. The intelligent question search and adaptive recommendation system according to claim 7, characterized in that: The analysis module is also used to generate a corresponding processing method based on the comparison result of the proportion of qualified subjects and the preset proportion, including adjusting the number of pushed qualified subjects based on the absolute value of the slope of the forgetting curve predicted by the LSTM network, or adjusting the total number of pushed questions based on the difference between the proportion of qualified subjects and the preset proportion.

9. The intelligent question search and adaptive recommendation system according to claim 7, characterized in that: The analysis module is also used to reduce the number of pushes for the qualified subjects based on the absolute value of the slope of the forgetting curve predicted by the LSTM network, and the absolute value of the slope is inversely proportional to the degree of reduction in the number of pushes for the qualified subjects.

10. The intelligent question search and adaptive recommendation system according to claim 7, characterized in that: The analysis module is further configured to reduce the total number of pushed topics based on the difference between the proportion of qualified subjects and a preset proportion, and the difference is proportional to the extent of the reduction in the total number of pushed topics.

Images