Legal teaching scheme recommendation system and method based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a law teaching scheme recommendation system and method based on artificial intelligence, and the method comprises the steps: obtaining intelligent teaching data coverage information through a distributed cloud platform, and generating a semantic tree; according to the difference of the random learning data, obtaining the validity of the random learning state in the same learning state to the student; analyzing the validity of the same learning state pair, and obtaining a candidate correlation degree; filtering candidate association degrees of two random concerned students and all other students, and outputting candidate students; analyzing candidate association degrees among all random candidate students, outputting a target association degree, and filtering and outputting reference students of the random students; analyzing the intelligent teaching data of the reference students of the to-be-served students, generating a plurality of service strategies of the to-be-served students, and completing the intelligent service of the intelligent teaching strategies. According to the invention, the teaching scheme adopted according to the actual situation is provided for the current student to realize the recommendation of the teaching scheme, and the individual demands of the student are fully met.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based legal teaching program recommendation system and method. Background Art

[0002] The traditional teaching model is subject to geographical and spatial restrictions. Under these restrictions, teaching resources are unbalanced and even have relatively large gaps, which affects the teaching quality to a certain extent.

[0003] When using big data analysis and artificial intelligence technology to make intelligent recommendations for teaching plans, it is often possible to compare the various situations of existing students with the student information stored in the artificial intelligence to obtain the similarity between the current student and the stored student information, and apply the teaching plan adopted by the student with the highest similarity to the current student to achieve the recommendation of teaching plans. However, this may result in the teaching plans always being a few fixed plans and failing to meet the personalized needs of students. Summary of the Invention

[0004] To achieve the above objectives, this application provides the following technical strategies:

[0005] According to a first aspect of the present invention, the present invention claims protection for a method for recommending a legal teaching program based on artificial intelligence, the method comprising the following steps:

[0006] Obtaining intelligent teaching data coverage information and generating a semantic tree through a distributed cloud platform, wherein the intelligent teaching data coverage information should at least include: learning data and intelligent teaching data of multiple students, wherein the learning data includes multiple learning states and related feedback enthusiasm, and the students include students to be served. Two students with a relationship in the semantic tree are students of interest;

[0007] According to the difference in learning data of two random students of interest, the effectiveness of a random learning state in the same learning state of the two students of interest is obtained for the students; the effectiveness of the same learning state of the two students of interest is analyzed for the two students of interest, and candidate correlations of the two students of interest are obtained; the candidate correlations of the two random students of interest and all other students are filtered, and candidate students of the two students of interest are output; the candidate correlations between all candidate students of the two random students of interest are analyzed, and the target correlation of the two students of interest is output, and the reference students of the random students are filtered and output;

[0008] Analyze the intelligent teaching data of the reference students of the students to be served and generate multiple service strategies for the students to be served;

[0009] Analyze multiple service strategies for students to be served and complete intelligent services of intelligent teaching strategies.

[0010] Furthermore, the method of obtaining the effectiveness of a random learning state for the same learning state of the two randomly focused students based on the difference in learning data of the two randomly focused students includes the following specific methods:

[0011] The two random students of interest are recorded as Student A and Student B;

[0012] ;

[0013] in, For students A and B who have the same learning status The effectiveness of a learning state for student A; The number of students followed by student A; For student A, the first Feedback on the learning status of the students For student A The first focus is on the students A and B in the same learning state. Feedback positivity of a learning status.

[0014] Furthermore, the analyzing of the effectiveness of the same learning status of two students of interest on the two students of interest and obtaining the candidate correlation degree of the two students of interest includes the following specific methods:

[0015] Get the number of identical learning states in the learning data of two random students;

[0016] The method for obtaining the candidate correlation between two random students is:

[0017] ;

[0018] in, is the candidate correlation between student A and student B; The number of learning states that are the same between student A and student B; 、 For students A and B who have the same learning status The effectiveness of a learning state for student A and student B; 、 For students A and B, the first The feedback positivity of each learning state, T is the preset first indicator.

[0019] Furthermore, the method of filtering the candidate correlations between two random students of interest and all other students and outputting the candidate students of the two students of interest includes:

[0020] Obtain candidate correlations between two random students of interest and all other students, and record students whose candidate correlations with the two students of interest are greater than a preset second indicator as candidate students of the two students of interest.

[0021] Furthermore, the analysis of the candidate correlation between all candidate students of two random focused students, outputting the target correlation between the two focused students, and filtering and outputting the reference students of the random students includes the following specific methods:

[0022] The method for obtaining the target correlation between two random students is:

[0023] ;

[0024] in, is the goal relevance between student A and student B; is the candidate correlation between student A and student B; is the number of candidate students for student A, is the number of candidate students for student B, For student A candidate student and student B's The candidate relevance of each candidate student; is the normalization function;

[0025] Among all the students followed by the random student, the students whose target correlation with the student is greater than a preset second indicator are recorded as reference students of the student.

[0026] Furthermore, the method of analyzing the intelligent teaching data of the reference students of the students to be served and generating multiple service strategies for the students to be served includes the following specific methods:

[0027] Obtaining intelligent teaching data of all reference students of the student to be served, wherein the intelligent teaching data includes intelligent teaching quality, intelligent teaching quality level, and costs related to the intelligent teaching quality level;

[0028] Obtain the applicable enthusiasm of random intelligent teaching quality for serving students; obtain the applicable level of random intelligent teaching quality for serving students;

[0029] Based on the applicability of intelligent teaching quality to serving students, all intelligent teaching qualities are ranked from large to small. The quality of intelligent teaching and the related applicability level are recorded as service strategy one;

[0030] Obtain the order in which each intelligent teaching quality is recalled and the order in which each intelligent teaching quality level is recalled;

[0031] Sort the quality of each intelligent teaching by the order in which it is recalled from low to high, and sort the quality of each intelligent teaching by the order in which it is recalled by the highest The quality of intelligent teaching and service strategy at the end of Recall the quality of intelligent teaching and output service strategy 2;

[0032] Based on the order in which each intelligent teaching quality level is recalled, the order in which each intelligent teaching quality level is recalled is ranked from low to high. Recall the applicable level of intelligent teaching quality related to service strategy one and output service strategy three;

[0033] described 、 、 The fourth indicator, the fifth indicator and the sixth indicator are preset.

[0034] Furthermore, the specific method for obtaining the applicability of the random intelligent teaching quality to the service students is as follows:

[0035] For random intelligent teaching quality, obtain the sum of the target correlations between all students who adopt the intelligent teaching quality among the reference students of the to-be-served student and student A, and multiply it by the number of students who adopt the intelligent teaching quality among the reference students of the to-be-served student, and output the applicability of the intelligent teaching quality to the to-be-served student.

[0036] Furthermore, the specific method for obtaining the applicable level of the random intelligent teaching quality to the students served is:

[0037] ;

[0038] in, For the The applicable level of intelligent teaching quality to serve students; The first one is selected from the reference students for the students to be served. Number of students with different intelligent teaching qualities; The first among the reference students for the students to be served The target correlation between individual students and the students to be served, The first among the reference students for the students to be served The intelligent teaching quality level of the hth type of intelligent teaching quality adopted by each student; is the floor symbol.

[0039] Furthermore, the specific method for obtaining the order in which each intelligent teaching quality is recalled and the order in which each intelligent teaching quality level is recalled is:

[0040] The order in which each intelligent teaching quality is recalled is obtained based on the cost of the applicability level of the random intelligent teaching quality to the students it serves and the applicability enthusiasm of the intelligent teaching quality to the students it serves; the cost of the applicability level of the random intelligent teaching quality to the students it serves is positively correlated with the order in which the intelligent teaching quality is recalled, while the applicability enthusiasm of the intelligent teaching quality to the students it serves is inversely correlated with the order in which the intelligent teaching quality is recalled;

[0041] The order in which each intelligent teaching quality level is recalled is obtained based on the cost of the random intelligent teaching quality level of the random intelligent teaching quality and the applicability and enthusiasm of the intelligent teaching quality for serving students. The cost of the random intelligent teaching quality level of the random intelligent teaching quality is positively correlated with the order in which the intelligent teaching quality levels are recalled, while the applicability and enthusiasm of the intelligent teaching quality for serving students is inversely correlated with the order in which the intelligent teaching quality levels are recalled.

[0042] According to the second aspect of the present invention, the present invention seeks protection for a legal teaching program recommendation system based on artificial intelligence, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method when executing the computer program.

[0043] The present application relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based legal teaching program recommendation system and method, which obtains intelligent teaching data coverage information and generates a semantic tree through a distributed cloud platform; obtains the effectiveness of random learning states for students in the same learning state based on the difference in random learning data; analyzes the effectiveness of the same learning state to obtain candidate correlations; filters the candidate correlations of two random students of interest and all other students, and outputs candidate students; analyzes the candidate correlations between all random candidate students, outputs the target correlations, and filters and outputs the reference students of the random students; analyzes the intelligent teaching data of the reference students of the students to be served, generates multiple service strategies for the students to be served, and completes the intelligent service of the intelligent teaching strategy. The present invention provides the teaching plan adopted according to the actual situation to the current students to achieve the recommendation of the teaching plan, which can fully meet the personalized needs of the students. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a workflow diagram of a method for recommending legal teaching programs based on artificial intelligence, as claimed in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical strategies in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0046] The terms "first," "second," and "third" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features indicated. Therefore, a feature specified as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically specified. All directional indications in the embodiments of this application (such as up, down, left, right, front, back, etc.) are intended only to illustrate the relative positional relationships and movement of components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly. Furthermore, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device comprising a series of steps or units is not limited to the listed steps or units and may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or device.

[0047] References to "embodiments" herein mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0048] See also Figure 1 , which shows a workflow diagram of a method for recommending legal teaching plans based on artificial intelligence provided by one embodiment of the present invention, the method comprising the following steps:

[0049] Step S001: Obtain intelligent teaching data coverage information through the distributed cloud platform and generate a semantic tree.

[0050] Specifically, in order to implement the artificial intelligence-based legal teaching solution recommendation method proposed in this embodiment, it is first necessary to obtain intelligent teaching data coverage information and generate a semantic tree. The specific process is as follows:

[0051] Through the distributed cloud platform, intelligent teaching data coverage information is obtained from multiple data sources and uploaded to the database in a unified manner, and a semantic tree is generated for the intelligent teaching coverage information.

[0052] The intelligent teaching data coverage information should at least include: learning data and intelligent teaching data of multiple students; the learning data includes multiple learning states and related feedback enthusiasm, and the intelligent teaching data includes the intelligent teaching quality selected by students, the related intelligent teaching quality level and the related cost.

[0053] It should be noted that the students in the semantic tree include students waiting to be served.

[0054] At this point, the semantic tree of the intelligent teaching data coverage information is output through the above method.

[0055] Step S002: Based on the difference in learning data of two random students of interest, obtain the effectiveness of the random learning state in the same learning state of the two students of interest to the students; analyze the effectiveness of the same learning state of the two students of interest to the two students of interest, and obtain the candidate correlation of the two students of interest; filter the candidate correlation between the two random students of interest and all other students, and output the candidate students of the two students of interest; analyze the candidate correlation between all candidate students of the two random students of interest, output the target correlation of the two students of interest, and filter and output the reference students of the random students.

[0056] It should be noted that to obtain intelligent teaching strategies for the students to be served, students with similar feedback from the students to be served should be filtered out from the semantic tree. By using the intelligent teaching strategies selected by these students to provide services to the students to be served, a more appropriate and effective treatment effect can be achieved. Therefore, it is necessary to first obtain reference students for the students to be served. The basis for obtaining reference students is the correlation and association between the students to be served and the students to be served in the semantic tree.

[0057] Therefore, candidates are filtered based on whether there is a relationship with the students to be served in the semantic tree, and then the correlation between the students to be served and the students to be served is analyzed.

[0058] Specifically, in step 2.1, based on the difference in learning data of two random students of interest, the effectiveness of the random learning state on the students in the same learning state of the two students of interest is obtained.

[0059] It should be noted that the students of interest are two students who have a relationship in the semantic tree.

[0060] It should be noted that when comparing the candidacy of the current student with that of the students in the database, it is not reasonable to treat all learning states as parallel features and give them the same weight. Therefore, it is necessary to determine the weight that each different learning state should have when calculating the candidacy based on the frequency of occurrence of each learning state and the feedback positivity of the learning state. The more students a certain learning state appears in, the weaker its effectiveness for the students of interest, and the lower the weight that this learning state should have when calculating the candidacy; if a certain learning state appears in a random student, the positivity value is quite different from that of other students, which proves that the learning state is more effective for the current student, and the higher the weight that this learning state should have when calculating the candidacy.

[0061] As an example, two random students of interest are recorded as student A and student B;

[0062] ;

[0063] in, For students A and B who are in the same learning state The effectiveness of a learning state for student A; The number of students followed by student A; For student A, the first Feedback on the learning status of the students For student A The first focus is on the students A and B in the same learning state. Feedback positivity of a learning status.

[0064] It should be noted that, for two random students with the same random learning status, the greater the difference between the feedback positivity of the random student among the two students and the feedback positivity of the learning status of other students of the student, the more effective the learning status is for the students.

[0065] Step 2.2: Analyze the effectiveness of the same learning status of two focused students on the two focused students, and obtain the candidate relevance of the two focused students.

[0066] It should be noted that when calculating the candidate correlation between two students, the number of the same learning status of the two students should be confirmed first. If there is no same learning status, it means that there is no candidate between the two students. On the basis of having the same learning status, the more the same learning status is and the more positive the feedback of each learning status is, the higher the candidate correlation between the two students. In addition, when calculating the candidate correlation, the effectiveness of each learning status for the student being compared needs to be taken into account, so as to more accurately describe the candidate correlation between the two students.

[0067] As an embodiment, a method for obtaining the candidate correlation degree of two random students of interest is as follows:

[0068] Get the number of identical learning states in the learning data of two random students;

[0069] ;

[0070] in, is the candidate correlation between student A and student B; The number of learning states that are the same between student A and student B; 、 For students A and B who are in the same learning state The effectiveness of a learning state for student A and student B; 、 For students A and B, the first The feedback positivity of each learning state, T is the preset first indicator.

[0071] It should be noted that The difference between the feedback positivity of student A and student B on the same learning status. The greater the difference, the lower the correlation between the two students. Then it is the candidate degree of feedback positivity of student A and student B for the same learning status. The smaller the difference in feedback positivity, the greater the correlation of feedback positivity. ;

[0072] For all the same learning states of students A and B, the effectiveness of each learning state for students A and B is used as the weight, and the correlation degree of the feedback positivity of each same learning state of students A and B is weighted and summed, and then multiplied by the number of the same learning states of students A and B, the overall candidate correlation degree of students A and B is output.

[0073] It should be noted that the first indicator is preset based on experience The denominator is set to 0.1 to avoid the situation where the denominator in the formula is 0. It can be adjusted according to actual conditions and is not specifically limited in this embodiment.

[0074] Step 2.3: Filter the candidate correlations between two random students of interest and all other students, and output the candidate students of the two students of interest.

[0075] Obtain candidate correlations between two random students of interest and all other students, and record students whose candidate correlations with the two students of interest are greater than a preset second indicator as candidate students of the two students of interest.

[0076] It should be noted that the second index is preset to 0.7 based on experience and can be adjusted according to actual conditions. This embodiment does not impose any specific limitation.

[0077] Step 2.4, analyzing the candidate correlation between all candidate students of two random focused students, outputting the target correlation between the two focused students, and filtering and outputting the reference students of the random students.

[0078] It should be noted that for two relatively good candidates, the higher the candidate correlation between them and the other students who are candidates for these two students, the higher the target correlation between these two students should be. Therefore, the correlation between the two students can be modified based on the candidate correlation between their respective candidate students, and the reference students of the random student can be obtained.

[0079] As an embodiment, a method for obtaining the target correlation between two random students is as follows:

[0080] ;

[0081] in, is the goal relevance between student A and student B; is the candidate correlation between student A and student B; is the number of candidate students for student A, is the number of candidate students for student B, For student A candidate student and student B's The candidate relevance of each candidate student.

[0082] It should be noted that To express the correlation between the candidate students of the two focused students, the candidate correlation degrees between the candidate students of the two focused students are added together. The more candidates the candidate students of the two focused students are, the more candidates the two focused students are.

[0083] Among all the students followed by the random student, the students whose target correlation with the student is greater than a preset third indicator are recorded as reference students of the student.

[0084] It should be noted that the reference students are students with a high degree of correlation with the students to be served, and the intelligent teaching strategy of the students to be served can be determined based on the intelligent teaching strategy of the reference students.

[0085] At this point, the reference student of the random student is output through the above method.

[0086] Step S003: Analyze the intelligent teaching data of the reference students of the students to be served, and generate multiple service strategies for the students to be served.

[0087] It's important to note that when selecting intelligent teaching strategies for prospective students, the target candidate scores of the prospective students and reference students should be considered, along with various intelligent teaching qualities and their associated intelligent teaching quality levels, to determine the most appropriate service strategy for the prospective students. Furthermore, economic factors should be considered, with costs factored in. A new service strategy should be developed by selecting the most appropriate and cost-effective intelligent teaching quality and level.

[0088] Specifically, in step 3.1, based on the target correlation between the reference students of the to-be-served students and the to-be-served students, and the number of students among the reference students who adopt each intelligent teaching quality, the applicability of the random intelligent teaching quality to the to-be-served students is obtained.

[0089] Obtaining intelligent teaching data of all reference students of the student to be served, wherein the intelligent teaching data includes intelligent teaching quality, intelligent teaching quality level, and costs related to the intelligent teaching quality level;

[0090] For random intelligent teaching quality, obtain the sum of the target correlations between all students who adopt the intelligent teaching quality among the reference students of the to-be-served student and student A, and multiply it by the number of students who adopt the intelligent teaching quality among the reference students of the to-be-served student, and output the applicability of the intelligent teaching quality to the to-be-served student.

[0091] Step 3.2: Generate service strategy 1 based on the target correlation between the reference students of the students to be served and the students to be served, the number of students using each intelligent teaching quality among the reference students, and the level of each intelligent teaching quality used.

[0092] It should be noted that the level analysis of the intelligent teaching quality adopted by the reference students of the students to be served shows the level of intelligent teaching quality that should be adopted by the students to be served. Therefore, for random intelligent teaching quality, the average level of the intelligent teaching quality adopted by the reference students is the service level of the students to be served, and the more applicable it is to the students to be served.

[0093] As an embodiment, a specific method for obtaining the applicable level of random intelligent teaching quality for serving students is as follows:

[0094] ;

[0095] in, For the The applicable level of intelligent teaching quality to serve students; The first one is selected from the reference students for the students to be served. Number of students with different intelligent teaching qualities; The first among the reference students for the students to be served The target correlation between individual students and the students to be served, The first among the reference students for the students to be served The intelligent teaching quality level of the hth type of intelligent teaching quality adopted by each student; is the floor symbol.

[0096] It should be noted that The goal correlation between the reference students and the students to be served is used as the weight, and the level of random intelligent teaching quality selected by all reference students is weighted averaged. The intelligent teaching quality level selected by the reference students with a greater goal correlation with the students to be served has a higher reference value, and the result is rounded down, so as to output the applicable level of random intelligent teaching quality for the students to be served.

[0097] Based on the applicability of intelligent teaching quality to serving students, all intelligent teaching qualities are ranked from large to small. The quality of intelligent teaching and the related applicability level are recorded as service strategy one.

[0098] described This is the preset fourth indicator.

[0099] It should be noted that the fourth indicator is preset to 5 based on experience and can be adjusted according to actual conditions. This embodiment does not impose any specific limitation.

[0100] Step 3.3: Based on the cost of the applicable level of random intelligent teaching quality for the service students and the applicable enthusiasm of the intelligent teaching quality for the service students, service strategy 1 is recalled to generate service strategy 2.

[0101] The order in which each intelligent teaching quality is recalled is obtained based on the cost of the applicability level of the random intelligent teaching quality for serving students and the applicability enthusiasm of the intelligent teaching quality for serving students. The cost of the applicability level of the random intelligent teaching quality for serving students is positively correlated with the order in which the intelligent teaching quality is recalled, while the applicability enthusiasm of the intelligent teaching quality for serving students is inversely correlated with the order in which the intelligent teaching quality is recalled.

[0102] Sort the quality of each intelligent teaching by the order in which it is recalled from low to high, and sort the quality of each intelligent teaching by the order in which it is recalled by the highest The quality of intelligent teaching and service strategy at the end of Recall the quality of intelligent teaching and output service strategy 2.

[0103] described Preset the fifth indicator.

[0104] It should be noted that the fifth indicator is preset to 3 based on experience and can be adjusted according to actual conditions. This embodiment does not impose any specific limitation.

[0105] Step 3.4: Based on the cost of the random intelligent teaching quality level of the random intelligent teaching quality and the applicability of the intelligent teaching quality to the service students, service strategy one is recalled to generate service strategy three.

[0106] The order in which each intelligent teaching quality level is recalled is obtained based on the cost of the random intelligent teaching quality level of the random intelligent teaching quality and the applicability and enthusiasm of the intelligent teaching quality for serving students. The cost of the random intelligent teaching quality level of the random intelligent teaching quality is positively correlated with the order in which the intelligent teaching quality levels are recalled, while the applicability and enthusiasm of the intelligent teaching quality for serving students is inversely correlated with the order in which the intelligent teaching quality levels are recalled.

[0107] Based on the order in which each intelligent teaching quality level is recalled, the order in which each intelligent teaching quality level is recalled is ranked from low to high. Recall the applicable levels of intelligent teaching quality related to service strategy one and output service strategy three.

[0108] described Preset the sixth indicator.

[0109] It should be noted that the sixth indicator is preset to 3 based on experience and can be adjusted according to actual conditions. This embodiment does not impose any specific limitation.

[0110] At this point, multiple service strategies for the students to be served are output through the above method.

[0111] Step S004: Analyze multiple service strategies for students to be served and complete intelligent services of intelligent teaching strategies.

[0112] Specifically, the applicability of the intelligent teaching quality in multiple service strategies, the applicability level of each intelligent teaching quality and the cost are presented to the students to be served in the form of a visual graph with reference to the students' intelligent teaching data, and the intelligent teaching strategy is determined with the goal.

[0113] It should be noted that entering the target intelligent teaching strategy for the students to be served into the semantic tree can help the system to improve and upgrade itself, so that subsequent students can output more comprehensive and applicable intelligent teaching strategies.

[0114] Through the above steps, the recommendation of legal teaching plan based on artificial intelligence is completed.

[0115] An embodiment of the present invention provides an artificial intelligence-based legal teaching program recommendation system, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any one of the steps of the artificial intelligence-based legal teaching program recommendation method.

[0116] This embodiment obtains students related to the student to be served in the semantic tree, determines reference students for the student to be served based on the correlation of feedback positivity among students in the same learning status as the student to be served, and then determines the intelligent teaching quality of the student to be served based on the intelligent teaching data of the reference students. Taking cost into consideration, the system then uses the more appropriate and less expensive intelligent teaching quality for the service. This method filters out the most relevant students in the student's status, fully considers their intelligent teaching data, and obtains the most appropriate intelligent teaching quality and related level. It also provides multiple service strategies, taking into account students' financial factors where applicable, allowing students to have a wider range of choices, a larger reference range, and greater flexibility.

[0117] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0118] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made through the content of the description and drawings of this application, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of this application.

[0119] The above detailed description of the specific embodiments of the invention is intended only as an example, and the present application is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions of the invention are also within the scope of the present application. Therefore, equivalent changes, modifications, and improvements made without departing from the spirit and scope of the present application should be included within the scope of the present application.

Claims

1. A method for recommending legal teaching programs based on artificial intelligence, characterized in that: The method comprises the following steps: Obtaining intelligent teaching data coverage information and generating a semantic tree through a distributed cloud platform, wherein the intelligent teaching data coverage information should at least include: learning data and intelligent teaching data of multiple students, wherein the learning data includes multiple learning states and related feedback enthusiasm, and the students include students to be served. Two students with a relationship in the semantic tree are students of interest; According to the difference in learning data of two random students of interest, the effectiveness of a random learning state in the same learning state of the two students of interest is obtained for the students; the effectiveness of the same learning state of the two students of interest is analyzed for the two students of interest, and candidate correlations of the two students of interest are obtained; the candidate correlations of the two random students of interest and all other students are filtered, and candidate students of the two students of interest are output; the candidate correlations between all candidate students of the two random students of interest are analyzed, and the target correlation of the two students of interest is output, and the reference students of the random students are filtered and output; Analyze the intelligent teaching data of the reference students of the students to be served and generate multiple service strategies for the students to be served; Analyze multiple service strategies for students to be served and complete intelligent services of intelligent teaching strategies.

2. The method for recommending legal teaching plans based on artificial intelligence according to claim 1, characterized in that: The specific method of obtaining the effectiveness of a random learning state for the same learning state of the two randomly focused students based on the difference in learning data of the two randomly focused students is as follows: The two random students of interest are recorded as Student A and Student B; ； in, For students A and B who have the same learning status The effectiveness of a learning state for student A; The number of students followed by student A; For student A, the first Feedback on the learning status of the students For student A The first focus is on the students A and B in the same learning state. Feedback positivity of a learning status.

3. The artificial intelligence-based legal teaching program recommendation method according to claim 1, characterized in that: The specific method of analyzing the effectiveness of the same learning status of two students of interest on the two students of interest and obtaining the candidate correlation degree of the two students of interest is as follows: Get the number of identical learning states in the learning data of two random students; The method for obtaining the candidate correlation between two random students is: ； in, is the candidate correlation between student A and student B; The number of learning states that are the same between student A and student B; 、 For students A and B who have the same learning status The effectiveness of a learning state for student A and student B; 、 For students A and B, the first The feedback positivity of each learning state, T is the preset first indicator.

4. The artificial intelligence-based legal teaching program recommendation method according to claim 1, characterized in that: The method of filtering the candidate correlations of two random students of interest and all other students and outputting the candidate students of the two students of interest includes: Obtain candidate correlations between two random students of interest and all other students, and record students whose candidate correlations with the two students of interest are greater than a preset second indicator as candidate students of the two students of interest.

5. The artificial intelligence-based legal teaching program recommendation method according to claim 1, characterized in that: The specific method of analyzing the candidate correlation between all candidate students of two random focused students, outputting the target correlation between the two focused students, and filtering and outputting the reference students of the random students is as follows: The method for obtaining the target correlation between two random students is: ； in, is the goal relevance between student A and student B; is the candidate correlation between student A and student B; is the number of candidate students for student A, is the number of candidate students for student B, For student A candidate student and student B's The candidate relevance of each candidate student; is the normalization function; Among all the students followed by the random student, the students whose target correlation with the student is greater than a preset second indicator are recorded as reference students of the student.

6. The artificial intelligence-based legal teaching program recommendation method according to claim 1, characterized in that: The specific method of analyzing the intelligent teaching data of the reference students of the students to be served and generating multiple service strategies for the students to be served includes: Obtaining intelligent teaching data of all reference students of the student to be served, wherein the intelligent teaching data includes intelligent teaching quality, intelligent teaching quality level, and costs related to the intelligent teaching quality level; Obtain the applicable enthusiasm of random intelligent teaching quality for serving students; obtain the applicable level of random intelligent teaching quality for serving students; Based on the applicability of intelligent teaching quality to serving students, all intelligent teaching qualities are ranked from large to small. The quality of intelligent teaching and the related applicability level are recorded as service strategy one; Obtain the order in which each intelligent teaching quality is recalled and the order in which each intelligent teaching quality level is recalled; Sort the quality of each intelligent teaching by the order in which it is recalled from low to high, and sort the quality of each intelligent teaching by the order in which it is recalled by the highest The quality of intelligent teaching and service strategy at the end of Recall the quality of intelligent teaching and output service strategy 2; Based on the order in which each intelligent teaching quality level is recalled, the order in which each intelligent teaching quality level is recalled is ranked from low to high. Recall the applicable level of intelligent teaching quality related to service strategy one and output service strategy three; described 、 、 The fourth indicator, the fifth indicator and the sixth indicator are preset.

7. The artificial intelligence-based legal teaching program recommendation method according to claim 6, characterized in that: The specific method for obtaining the applicability of the random intelligent teaching quality to the service students is as follows: For random intelligent teaching quality, obtain the sum of the target correlations between all students who adopt the intelligent teaching quality among the reference students of the to-be-served student and student A, and multiply it by the number of students who adopt the intelligent teaching quality among the reference students of the to-be-served student, and output the applicability of the intelligent teaching quality to the to-be-served student.

8. The artificial intelligence-based legal teaching program recommendation method according to claim 6, characterized in that: The specific method for obtaining the applicable level of the random intelligent teaching quality to the students served is: ； in, For the The applicable level of intelligent teaching quality to serve students; The first one is selected from the reference students for the students to be served. Number of students with different intelligent teaching qualities; The first among the reference students for the students to be served The target correlation between individual students and the students to be served, The first among the reference students for the students to be served The intelligent teaching quality level of the hth type of intelligent teaching quality adopted by each student; is the floor symbol.

9. The artificial intelligence-based legal teaching program recommendation method according to claim 6, characterized in that: The specific method for obtaining the order in which each intelligent teaching quality is recalled and the order in which each intelligent teaching quality level is recalled is: The order in which each intelligent teaching quality is recalled is obtained based on the cost of the applicability level of the random intelligent teaching quality to the students it serves and the applicability enthusiasm of the intelligent teaching quality to the students it serves; the cost of the applicability level of the random intelligent teaching quality to the students it serves is positively correlated with the order in which the intelligent teaching quality is recalled, while the applicability enthusiasm of the intelligent teaching quality to the students it serves is inversely correlated with the order in which the intelligent teaching quality is recalled; The order in which each intelligent teaching quality level is recalled is obtained based on the cost of the random intelligent teaching quality level of the random intelligent teaching quality and the applicability and enthusiasm of the intelligent teaching quality for serving students. The cost of the random intelligent teaching quality level of the random intelligent teaching quality is positively correlated with the order in which the intelligent teaching quality levels are recalled, while the applicability and enthusiasm of the intelligent teaching quality for serving students is inversely correlated with the order in which the intelligent teaching quality levels are recalled.

10. A legal teaching program recommendation system based on artificial intelligence, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images