A learning task allocation control method and system

Abstract

The present invention provides a method and system for controlling the distribution of learning tasks, the method comprising: formulating corresponding learning tasks according to the learning progress score of the user; obtaining the usage status information uploaded by the learning terminal; the usage status information includes the resource data, identification information and user identity information corresponding to the learning terminal; generating a task push list for each user according to the usage status information; according to the task push list, pushing the learning tasks to the corresponding learning terminal in order from high to low push levels, until the push is terminated after receiving the response information of the learning terminal. The present invention arranges and generates learning tasks for different students in a targeted manner, improves the learning effect of the user in a personalized manner, and reduces the usability. In addition, when the existing teaching system distributes learning tasks, the learning tasks are pushed according to the priority, which reduces repeated pushes and improves the user experience.

Description

Technical Field

[0001] The present invention relates to the field of intelligent teaching technology, and in particular to a method and system for controlling the distribution of learning tasks. Background Art

[0002] With the development of computer networks, the education field has also been influenced by it and is increasingly moving towards online and distance learning, and teaching has moved from offline classrooms to online. In the current education and teaching process, teachers usually use the teaching system to assign some pre-class or post-class learning tasks in stages, such as pre-class preparation, post-class review, class assignments, and after-class assignments, etc., in order to achieve the best educational effect.

[0003] However, when the existing teaching system assigns learning tasks, it simply publishes the learning tasks specified by the teacher, which makes it difficult to arrange them in a targeted manner, and it is unable to effectively play an educational role, nor can it improve the user's learning effect in a personalized way, which reduces the usability. In addition, when the existing teaching system assigns learning tasks, there is no priority for pushing learning tasks, and it is easy to push them repeatedly, resulting in a poor user experience. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for controlling the distribution of learning tasks, so as to achieve targeted distribution and generation of learning tasks for different students, improve the learning effect of users in a personalized way, and reduce usability. In addition, when the existing teaching system distributes learning tasks, it pushes learning tasks according to priority, reduces repeated pushes, and improves the user experience.

[0005] The technical solution provided by the present invention is as follows:

[0006] The present invention provides a method for controlling the distribution of learning tasks, comprising the steps of:

[0007] Formulate corresponding learning tasks according to the user's learning progress score;

[0008] Acquire usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0009] Generate a task push list for each user based on the usage status information;

[0010] According to the task push list, the learning tasks are pushed to the corresponding learning terminals in order of push levels from high to low, until the push is terminated after receiving the response information from the learning terminal.

[0011] Furthermore, generating a task push list for each user according to the usage status information specifically includes the following steps:

[0012] Each resource data corresponding to each identification information is input into the resource allocation model to obtain the corresponding comparison result, and a corresponding task push list is generated according to the comparison result and its corresponding user identity information; the task push list includes each learning terminal push level corresponding to the current user identity information.

[0013] Furthermore, the step of inputting each resource data corresponding to each identification information into the resource allocation model to obtain a corresponding comparison result, and generating a corresponding task push list according to the comparison result and its corresponding user identity information specifically includes the following steps:

[0014] Input each resource data corresponding to the current identification information into the resource allocation model, and compare each resource data with the resource allocation model to see whether it satisfies the corresponding preset condition;

[0015] Generating a push level of the learning terminal corresponding to the current identification information according to the comparison result;

[0016] A task push list corresponding to each user is generated according to the user identity information, identification information and the corresponding push level.

[0017] Furthermore, the step of generating the push level of the learning terminal corresponding to the current identification information according to the comparison result specifically includes the following steps:

[0018] When all resource data respectively meet corresponding preset conditions, obtaining the usage frequency and user demand of the learning terminal corresponding to the current identification information, and determining the push level of the learning terminal corresponding to the current identification information according to the usage frequency and user demand;

[0019] When any resource data does not meet the corresponding preset conditions, a weight calculation is performed on each resource data corresponding to the current identification information, and the total weight value is obtained by summing up the weight values ​​of each resource data, and the total weight value is used as the push level corresponding to the current identification information.

[0020] Furthermore, formulating corresponding learning tasks according to the learning progress score of the user includes the following steps:

[0021] Analyze all the learning contents of the student and the score value corresponding to each learning content according to the learning progress score value;

[0022] Determine whether the score value corresponding to each learning content is greater than the corresponding set score;

[0023] The required learning contents with score values ​​less than the corresponding set score are screened to obtain a target learning set, and corresponding learning tasks are formulated according to the target learning set.

[0024] The present invention also provides a learning task distribution control system, comprising: a task distribution terminal and a learning terminal; the task distribution terminal comprises a generation module, an acquisition module, a processing module and a first communication module; the learning terminal comprises a second communication module;

[0025] The generation module is used to formulate corresponding learning tasks according to the learning progress score of the user;

[0026] The acquisition module is used to acquire the usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0027] The processing module is connected to the acquisition module and is used to generate a task push list for each user according to the usage status information;

[0028] The first communication module is connected to the generation module, the processing module and the second communication module, and pushes the learning tasks to the corresponding learning terminals in descending order of push levels according to the task push list, until the push is terminated after receiving the response information from the learning terminal.

[0029] Furthermore, the processing module is used to input each resource data corresponding to each identification information into the resource allocation model to obtain a corresponding comparison result, and generate a corresponding task push list according to the comparison result and its corresponding user identity information;

[0030] The task push list includes each learning terminal push level corresponding to the current user identity information.

[0031] Further, the processing module includes: a first judgment unit, a first generation unit, and a processing unit;

[0032] The first judgment unit inputs each resource data corresponding to the current identification information into the resource allocation model, and compares each resource data with the resource allocation model to see whether it satisfies the corresponding preset condition;

[0033] The first generating unit is connected to the first judging unit and is used to generate a push level of the learning terminal corresponding to the current identification information according to the comparison result;

[0034] The processing unit is connected to the first generating unit, and generates a task push list corresponding to each user according to the user identity information, identification information and the corresponding push level.

[0035] Further, the processing unit includes a first computing subunit and a second computing subunit;

[0036] The acquisition module is connected to the first judgment unit and is further used to acquire the usage frequency and user demand of the learning terminal corresponding to the current identification information when all resource data respectively meet the corresponding preset conditions;

[0037] The first calculation subunit is connected to the acquisition module and is further used to determine the push level of the learning terminal corresponding to the current identification information according to the usage frequency and user needs;

[0038] The second calculation sub-unit is connected to the first judgment unit, and is also used to perform weight calculation on each resource data corresponding to the current identification information when any resource data does not meet the corresponding preset conditions, and to obtain a total weight value by summing up the weight values ​​of each resource data, and to use the total weight value as the push level corresponding to the current identification information.

[0039] Further, the generation module includes: an analysis unit, a second judgment unit, and a second generation unit;

[0040] The analyzing unit is used to analyze all the learning contents of the student and the score value corresponding to each learning content according to the learning progress score value;

[0041] The second judging unit is connected to the analyzing unit and is used to judge whether the score value corresponding to each learning content is greater than the corresponding set score;

[0042] The second generating unit is connected to the judging unit and is used to filter the required learning contents whose scores are less than the corresponding set scores to obtain a target learning set, and formulate corresponding learning tasks according to the target learning set.

[0043] The method and system for controlling the distribution of learning tasks provided by the present invention can generate learning tasks for different students in a targeted manner, improve the learning effect of users in a personalized manner, and reduce usability. In addition, when the existing teaching system distributes learning tasks, it pushes learning tasks according to priority, reduces repeated pushes, and improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The following will explain the preferred implementation mode in a clear and understandable manner with reference to the accompanying drawings, and further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of a learning task allocation control method and system.

[0045] Figure 1 is a flow chart of an embodiment of a method for controlling the distribution of learning tasks of the present invention;

[0046] Figure 2 is a flow chart of another embodiment of a method for controlling the distribution of learning tasks of the present invention;

[0047] Figure 3 is a flow chart of another embodiment of a method for controlling the distribution of learning tasks of the present invention;

[0048] Figure 4 is a flow chart of another embodiment of a method for controlling the distribution of learning tasks of the present invention;

[0049] Figure 5 is a flow chart of another embodiment of a method for controlling the distribution of learning tasks of the present invention;

[0050] Figure 6 It is a structural diagram of an embodiment of a distribution control system for learning tasks of the present invention. DETAILED DESCRIPTION

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings and other implementation methods can be obtained based on these drawings without creative work.

[0052] In order to simplify the drawings, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to simplify the drawings and facilitate understanding, in some figures, only one of the parts with the same structure or function is schematically drawn or marked. In this article, "one" not only means "only one", but also means "more than one".

[0053] One embodiment of the present invention, as Figure 1 As shown, a method for controlling the distribution of learning tasks includes:

[0054] S1000 formulates corresponding learning tasks according to the user's learning progress score;

[0055] S2000 obtains usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0056] S3000 generates a task push list for each user according to the usage status information;

[0057] S4000 pushes the learning tasks to the corresponding learning terminals according to the task push list in descending order of push levels until the push is terminated after receiving response information from the learning terminal.

[0058] Specifically, in this embodiment, the task allocation terminal obtains the learning progress score of each user, and then formulates a personalized learning task for each user based on the learning progress score of each user. The target learning terminal monitors its own usage status information in real time and uploads the usage status information to the task allocation terminal. After the task allocation terminal obtains the usage status information, it generates a task push list corresponding to each user based on the usage status information, and then the task allocation terminal pushes the learning tasks to the corresponding learning terminals in sequence according to the order of the target learning terminals in the task push list.

[0059] Among them, the learning task assigners include teachers, parents, etc., and the task assignment terminals include mobile phones, computers, tablets, etc. The learning terminals include smart desk lamps (desk lamps with any one or more of a camera, a microphone, a speaker, and also a wireless communication module), tablets, mobile phones, smart watches (watches with any one or more of a camera, a microphone, a speaker, and also a wireless communication module), etc.

[0060] Through this embodiment, the task distribution terminal can formulate targeted learning tasks for different users according to the different learning progress score values ​​of each user, can effectively play an educational role, and can help users learn in a targeted and differentiated manner according to the learning tasks, which can improve the learning effect of users and improve usability. The task distribution terminal can generate a task push list based on the usage status information, and then push the learning tasks to the corresponding learning terminals in order of push level according to the task push list, avoiding the simultaneous distribution of learning tasks to all learning terminals of a user, reducing the probability of repeated push of learning tasks, and reducing unnecessary push waste.

[0061] One embodiment of the present invention, as Figure 2 As shown, a method for controlling the distribution of learning tasks includes:

[0062] S1000 formulates corresponding learning tasks according to the user's learning progress score;

[0063] S2000 obtains usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0064] S3100 inputs each resource data corresponding to each identification information into the resource allocation model to obtain a corresponding comparison result, and generates a corresponding task push list according to the comparison result and the corresponding user identity information; the task push list includes each learning terminal push level corresponding to the current user identity information;

[0065] S4000 pushes the learning tasks to the corresponding learning terminals according to the task push list in descending order of push levels until the push is terminated after receiving response information from the learning terminal.

[0066] Specifically, the parts of this embodiment that are the same as those of the above embodiment will not be described one by one here. The upload period of each learning terminal uploading its own usage status information to the assigned task terminal can be set according to the user's own needs and habits. Resource data includes but is not limited to remaining power data, remaining memory data, remaining GPU data, remaining CPU data, and network data.

[0067] After the task assignment terminal obtains the usage status information uploaded by the learning terminal, it saves the user identity information and identification information corresponding to the usage status information to different folders, and the user identity information folder includes several identification information folders, each of which includes resource data. For example, the user identity information of a user A is ID-1, and he uses tablet P1 and smart desk lamp T1 for learning. The identification information of tablet P1 is MA1C1, and the identification information of smart desk lamp T1 is MA1C2. Then the tablet P1 uploads its own usage status information A1 (the usage status information A1 includes resource data ZA1, identification information MA1C1 and the user's user identity information ID-1) to the task allocation terminal, and the smart desk lamp T1 uploads its own usage status information A2 (the usage status information A2 includes resource data ZA2, identification information MA1C2 and the user's user identity information ID-1) to the task allocation terminal. After the task allocation terminal obtains the usage status information uploaded by the tablet P1 and the smart desk lamp T1, since the usage status information A1 and the usage status information A2 are analyzed to belong to the same user A, a large folder D1 is established for the identity information of user A. User A uses the tablet P1 and the smart desk lamp T1 for learning, and in the large file D1, subfolders named MA1C1 and MA1C2 are established according to the identification information of the learning terminal, wherein the resource data ZA1 is stored in the subfolder MA1C1, and the resource data ZA2 is stored in the subfolder MA1C2.

[0068] After the task allocation terminal classifies and stores the acquired usage status information, each resource data corresponding to each identification information is input into the pre-trained resource allocation model, and the resource allocation model analyzes and outputs the corresponding comparison results. Since the resource data and the identification information are related to each other, and the identification information and the user identity information are related to each other, the comparison results corresponding to the resource data can be associated and bound with the user identity information corresponding to the resource data. Therefore, when the resource allocation model analyzes and obtains the corresponding comparison results, a comparison task push list can be generated. The task push list includes the push order of all learning terminals of all users.

[0069] Exemplarily, user A uses tablet P1 (identification information is MAC1) and smart desk lamp T1 (identification information is MAC2) to learn. Tablet P1 uploads its own usage status information A1 to the task allocation terminal, and smart desk lamp T1 uploads its own usage status information A2 to the task allocation terminal. User B uses tablet P2 (identification information is MAC3) and smart desk lamp T2 (identification information is MAC4) to learn. Tablet P2 uploads its own usage status information A3 to the task allocation terminal, and smart desk lamp T2 uploads its own usage status information A4 to the task allocation terminal. The task allocation terminal inputs each resource data corresponding to each identification information into the resource allocation model to obtain the corresponding comparison result, and then generates the task push list L1 corresponding to user A and the task push list L2 corresponding to user B according to the comparison result and its corresponding user identity information. Assume that the task push list L1 is: the push level of tablet P1 is greater than the push level of smart desk lamp T1, and the task push list L2 is: the push level of tablet P2 is less than the push level of smart desk lamp T2. Then, after the task allocation terminal generates learning task C1 for user A, it first pushes learning task C1 to tablet P1, and then pushes learning task C1 to smart desk lamp T1. After the task allocation terminal generates learning task C2 for user B, it first pushes learning task C2 to smart desk lamp T2, and then pushes learning task C2 to tablet P2. If learning task C1 and learning task C2 are generated at the same time, then the task allocation terminal can simultaneously push learning task C1 to tablet P1 and push learning task C2 to smart desk lamp T2, and then push learning task C1 to smart desk lamp T1 and push learning task C2 to tablet P2.

[0070] Through this embodiment, the task allocation terminal can generate a task push list according to the usage status information, and then push the learning tasks to the corresponding learning terminals in order of push levels according to the task push list, avoiding the synchronous distribution of learning tasks to all learning terminals of a user, reducing the probability of repeated pushing of learning tasks, and reducing unnecessary push waste. In addition, distributed pushing of learning tasks according to push levels can also reduce the task volume of centralized distribution of learning tasks by the task allocation terminal, solving the problem of resource waste caused by centralized distribution of learning tasks by the task allocation terminal, or the problem of learning task issuance being stuck due to centralized distribution, avoiding resource waste while improving the effectiveness of learning task distribution and thus improving the user experience.

[0071] One embodiment of the present invention, as Figure 3 As shown, a method for controlling the distribution of learning tasks includes:

[0072] S1000 formulates corresponding learning tasks according to the user's learning progress score;

[0073] S2000 obtains usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0074] S3110 inputs each resource data corresponding to the current identification information into a resource allocation model, and compares each resource data with the resource allocation model to see whether it satisfies its corresponding preset condition;

[0075] S3120 generating a push level of the learning terminal corresponding to the current identification information according to the comparison result;

[0076] S3130 generating a task push list corresponding to each user according to the user identity information, identification information and the corresponding push level;

[0077] S4000 pushes the learning tasks to the corresponding learning terminals according to the task push list in descending order of push levels until the push is terminated after receiving response information from the learning terminal.

[0078] Specifically, the parts of this embodiment that are the same as the above-mentioned embodiments will not be described one by one here. The task allocation terminal inputs all the resource data corresponding to the current identification information obtained into the pre-trained resource allocation model, and the resource allocation model compares whether each resource data meets its corresponding preset conditions. After the resource allocation model outputs the corresponding comparison result, the task allocation terminal generates a push level for the learning terminal corresponding to the current identification information based on the comparison result of each resource data corresponding to the current identification information. This is repeated, and each resource data corresponding to each identification information is input into the resource allocation model in turn, and the resource allocation model outputs the comparison result of each resource data corresponding to each identification information respectively. In this way, the task allocation terminal can analyze the push level of each learning terminal based on the usage status information uploaded by all learning terminals, and then generate a task push list corresponding to each user.

[0079] One embodiment of the present invention, as Figure 4 As shown, a method for controlling the distribution of learning tasks includes:

[0080] S1000 formulates corresponding learning tasks according to the user's learning progress score;

[0081] S2000 obtains usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0082] S3110 inputs each resource data corresponding to the current identification information into a resource allocation model, and compares each resource data with the resource allocation model to see whether it satisfies its corresponding preset condition;

[0083] S3121 When all resource data respectively meet corresponding preset conditions, obtain the usage frequency and user demand of the learning terminal corresponding to the current identification information, and determine the push level of the learning terminal corresponding to the current identification information according to the usage frequency and user demand;

[0084] S3122 When any resource data does not meet the corresponding preset condition, weight calculation is performed on each resource data corresponding to the current identification information, and the total weight value is calculated by summing up the weight value of each resource data, and the total weight value is used as the push level corresponding to the current identification information;

[0085] S3130 generating a task push list corresponding to each user according to the user identity information, identification information and the corresponding push level;

[0086] S4000 pushes the learning tasks to the corresponding learning terminals according to the task push list in descending order of push levels until the push is terminated after receiving response information from the learning terminal.

[0087] Specifically, the parts of this embodiment that are the same as the above embodiments will not be repeated here one by one. The task allocation terminal obtains the information reception response rate and task execution rate of all learning terminals under different sample resource data states. The sample resource data is trained to obtain the corresponding resource allocation model, and the resource allocation model is trained to obtain the resource allocation standards corresponding to different resource data. The resource allocation standards corresponding to each resource data are: the remaining power data needs to be greater than U%, the remaining memory data needs to be greater than V%, the remaining GPU data needs to be greater than W%, the remaining CPU data needs to be greater than M%, and the network data needs to be greater than N%.

[0088] The resource allocation model is a neural network model, and the sample resource data used when training the resource allocation model includes remaining power data samples, remaining memory data samples, remaining CPU data samples, remaining GPU data samples and network data samples, and the output samples include resource allocation standard samples. The present invention does not limit the training process of the resource allocation model. Schematically, the terminal operating system obtains the current remaining power data as "50%" and the remaining memory data as "1.5GB". After inputting the above data into the resource allocation model, the resource allocation standard output by the resource allocation model is obtained.

[0089] When all resource data meet the corresponding preset conditions respectively, the push level of the learning terminal corresponding to each identification information is determined according to the usage record and user needs. Exemplarily, it is assumed that the resource allocation standard is that the remaining power data needs to be greater than 50%, the remaining memory data needs to be greater than 50%, and the remaining CPU data needs to be greater than 40%. In addition, the weight coefficients corresponding to the remaining power data, the remaining memory data, and the remaining CPU data are 0.6, 0.2, and 0.2, respectively. If user C uses smart watch S1 (identification information is MAC5) and smart desk lamp T3 (identification information is MAC6) for learning, smart watch S1 uploads its own usage status information A5 to the allocation task terminal (the remaining power data in the resource data is 70%, the remaining memory data is 80%, and the remaining CPU data is 65%), and the smart desk lamp T3 uploads its own usage status information A6 to the allocation task terminal (the remaining power data in the resource data is 60%, the remaining memory data is 60%, and the remaining CPU data is 60%). Then the task allocation terminal can compare the remaining power data corresponding to the identification information MAC5 and the identification information MAC6 through the resource allocation model to obtain the corresponding preset power condition threshold, the remaining memory data corresponding to the identification information MAC5 and the identification information MAC6 all meet the corresponding preset memory condition threshold, and the remaining CPU data corresponding to the identification information MAC5 and the identification information MAC6 all meet the corresponding preset CPU condition threshold. Therefore, the task allocation terminal determines that all resource data corresponding to the smart watch S1 and the smart desk lamp T3 meet the corresponding preset conditions respectively. At this time, the usage record corresponding to the current identification information of the task allocation terminal is obtained, and then the usage frequency and user demand of the learning terminal corresponding to the current identification information are obtained, and the push level of the learning terminal corresponding to the current identification information is determined according to the usage frequency and user demand. Among them, the usage record corresponding to the current identification information counts the number of times the current identification information is used, and the more times it is used, the greater the frequency of use. If the user considers increasing the usage rate of other learning terminals and reducing the idle rate of the learning terminal, the learning terminal with a lower usage frequency has a higher corresponding push level. If the user considers avoiding unskilled learning operations and reducing learning efficiency based on usage habits, the learning terminal with a higher usage frequency has a higher corresponding push level.

[0090] When any resource data does not meet the corresponding preset conditions, a weight calculation is performed on each resource data corresponding to the current identification information to obtain the weight value corresponding to each resource data, and the total weight value is calculated by summing up the weight value of each resource data, and the total weight value is used as the push level corresponding to the current identification information. Exemplarily, it is assumed that the resource allocation standard is that the remaining power data needs to be greater than 50%, the remaining memory data needs to be greater than 50%, and the remaining CPU data needs to be greater than 40%. If user C uses smart watch S1 (identification information is MAC5) and smart desk lamp T3 (identification information is MAC6) for learning, smart watch S1 uploads its own usage status information A5 to the allocation task terminal (the remaining power data in the resource data is 40%, the remaining memory data is 80%, and the remaining CPU data is 65%), and smart desk lamp T3 uploads its own usage status information A6 to the allocation task terminal (the remaining power data in the resource data is 70%, the remaining memory data is 60%, and the remaining CPU data is 25%). Then the task allocation terminal can compare the resource allocation model to find that the remaining power data corresponding to the identification information MAC5 does not meet the corresponding preset power condition threshold, the remaining memory data corresponding to the identification information MAC5 meets the corresponding preset memory condition threshold, and the remaining CPU data corresponding to the identification information MAC5 meets the corresponding preset CPU condition threshold. The remaining power data corresponding to the identification information MAC6 does not meet the corresponding preset power condition threshold, the remaining memory data corresponding to the identification information MAC6 meets the corresponding preset memory condition threshold, and the remaining CPU data corresponding to the identification information MAC6 does not meet the corresponding preset CPU condition threshold. Therefore, the task allocation terminal determines that the resource data corresponding to the smart watch S1 and the smart desk lamp T3 meet different types of preset conditions, but the number of items is the same. At this time, the task allocation terminal calculates the total weight value K1 corresponding to the identification information MAC5 = 0.6 × 40% + 0.2 × 80% + 0.2 × 65% = 0.53, and the total weight value K2 corresponding to the identification information MAC6 = 0.6 × 70% + 0.2 × 60% + 0.2 × 25% = 0.59. Since the total weight value is used as the push level, and K2>K1, the push level of the smart lamp T3 is greater than the push level of the smart watch S1. After the task allocation terminal generates the learning task of user C, it first pushes the learning task C3 to the smart lamp T3, and then pushes the learning task C3 to the smart watch S1.

[0091] Through this embodiment, the push level of the learning terminal corresponding to the current identification information can be determined by calculating the differences in different comparison results. In this way, when the number and type of resource data that meet the preset conditions are the same, the learning terminal can receive the learning tasks issued by the task allocation terminal in a timely manner and execute the corresponding learning tasks. At the same time, the push level can be determined according to the user's usage records and user needs, thereby meeting the user's personalized needs. When at least one of the number and type of resource data that meet the preset conditions is different, a weight calculation is performed to determine the push level, which can meet the purpose of the learning terminal receiving the learning tasks issued by the task allocation terminal in a timely manner.

[0092] One embodiment of the present invention, as Figure 5 As shown, a method for controlling the distribution of learning tasks includes:

[0093] S1100 obtains all the learning contents of the student and the score value corresponding to each learning content according to the learning progress score value;

[0094] S1200 determines whether the score value corresponding to each learning content is greater than the corresponding set score;

[0095] S1300: screening the required learning content with a score value less than the corresponding set score to obtain a target learning set, and formulating a corresponding learning task according to the target learning set;

[0096] S2000 obtains usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal;

[0097] S3000 generates a task push list for each user according to the usage status information;

[0098] S4000 pushes the learning tasks to the corresponding learning terminals according to the task push list in descending order of push levels until the push is terminated after receiving response information from the learning terminal.

[0099] Specifically, the task allocation terminal obtains all the student's learning content and the score value corresponding to each learning content based on the learning progress score analysis. Since the student's learning content can be one or more, the task allocation terminal determines whether the score value corresponding to the current learning content is greater than its corresponding set score. After judging the current learning content, if the number of learning contents is greater than one, it switches to the next learning content to continue judging until all learning content judgments are completed. All judgment results are recorded, and all learning content with scores less than their corresponding set scores are screened out to obtain the target learning set, and then learning tasks are formulated according to the target learning set.

[0100] Exemplarily, the task allocation terminal analyzes the score of a certain student A in mathematics based on the learning progress score and obtains that the score is 0.86 and the score is 0.66 in English. Assuming that the set scores of mathematics, English, chemistry and biology are 0.9, 0.9, 0.8 and 0.8 respectively, then the comparison shows that the score of mathematics, English and biology is less than the corresponding set score. Therefore, the target learning set includes mathematics, English and biology. The learning task formulated according to the target learning set is mathematics + English + biology learning task. The setting of other set scores is also within the protection scope of the present invention and will not be repeated here.

[0101] Preferably, the required learning content with a score value less than the corresponding set score is screened, and the difference between the score value of the required learning content and its corresponding set score is calculated. According to the difference, the corresponding learning task is formulated in order of size, so that the difference is proportional to the learning time. That is, the learning content with a lower difference has a shorter learning time in the learning task, and conversely, the learning content with a higher difference has a longer learning time in the learning task. Exemplarily, by comparative calculation, it can be calculated that the difference between the score values ​​of mathematics subjects, English subjects, and biology subjects and their corresponding set scores is 0.04, 0.34, and 0.02, respectively. Therefore, it can be analyzed that the English subject must strengthen the learning intensity, and the mathematics subject and the biology subject are second. Therefore, the learning tasks formulated for student A are T1, T2, and T3 for mathematics subjects, English subjects, and biology subjects, respectively, and T2>T1>T3.

[0102] Through this embodiment, the target learning set is obtained by comparing the score value of each learning content with the set score, and the learning task is formulated according to the target learning set. The score value of each learning content can be calculated in a targeted manner according to the student's learning content and learning situation, so as to obtain the student's learning progress score value, which is convenient for subsequent formulation of targeted learning tasks for different students according to the different learning progress score values ​​of each student, can effectively play an educational role, and carry out targeted and differentiated intensive training to improve students' learning efficiency and greatly improve students' learning effects.

[0103] Preferably, the learning content and learning status of the current user are obtained; the learning status includes the completion time and accuracy rate corresponding to the learning content. The completion time and accuracy rate are weighted according to the weight value in the evaluation standard to obtain the score value corresponding to the learning content, and the learning content and its corresponding score value are summarized to obtain the learning progress score value corresponding to the current user.

[0104] Specifically, the completion time is the time taken to complete the learning content divided by the prescribed time. The learning content of each user is recorded, and the user's daily learning results are scored. The completion time and accuracy of each learning content are calculated. The learning content and learning situation can be obtained manually or automatically. The manual acquisition method includes the learning task assignor manually entering the user's learning content and learning situation into the task assignment terminal. There are many automatic acquisition methods, such as all the user's learning terminals (learning machines, smart desk lamps, tablets, mobile phones, smart watches, etc.) and so on to record the user's learning content, and then the learning terminal corrects and scores the user's daily learning results to obtain the learning situation, and finally the learning terminal uploads the learning content and learning situation to the task assignment terminal of the learning task assignor. Any method of obtaining the user's learning content and learning situation is within the protection scope of the present invention, and will not be repeated here. The evaluation criteria include a weight value for completion time and a weight value for accuracy pre-set by the learning task assigner, and the weight value corresponding to the completion time of each learning content may be the same or different, and the weight value corresponding to the accuracy of each learning content may be the same or different.

[0105] The task assignment terminal obtains all the learning contents of the current user and the learning status of each learning content. Then, the task assignment terminal calculates the weights of the completion time and accuracy of the current learning content according to the pre-set evaluation criteria to obtain the score value corresponding to the current learning content. The task assignment terminal calculates the score value corresponding to each learning content, and then summarizes all the learning contents of the current user and their corresponding scores to obtain the learning progress score value of the current user.

[0106] In addition, the task assignment terminal pushes the learning task to the learning terminal with the highest push level according to the task push list. When the response information from the highest-level learning terminal is received, the learning task is stopped. When the response information from the highest-level learning terminal is not received, the learning task is pushed to the learning terminal of the next push level according to the task push list. The push is terminated after any learning terminal of the push level in the task push list feeds back its response information to the task assignment terminal.

[0107] Through this embodiment, it is possible to calculate the score value of each learning content in a targeted manner according to the user's learning content and learning situation, thereby obtaining the user's learning progress score value, which is convenient for subsequent formulation of targeted learning tasks for different users based on the different learning progress score values ​​of each user, can effectively play an educational role, and carry out targeted and differentiated intensive training to improve the user's learning efficiency and greatly improve the user's learning effect.

[0108] One embodiment of the present invention, as Figure 6 As shown, a learning task distribution control system includes: a task distribution terminal 1 and a learning terminal 2; the task distribution terminal 1 includes a generation module 11, an acquisition module 14, a processing module 12 and a first communication module 13; the learning terminal 2 includes a second communication module 21;

[0109] The generating module 11 is used to formulate corresponding learning tasks according to the learning progress score of the user;

[0110] The acquisition module 14 is used to acquire the usage status information uploaded by the learning terminal 2; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal 2;

[0111] The processing module 12 is connected to the acquisition module 14 and is used to generate a task push list for each user according to the usage status information;

[0112] The first communication module 13 is connected to the generation module 11, the processing module 12 and the second communication module 21, and pushes the learning tasks to the corresponding learning terminal 2 in order from high to low according to the task push list, until the push is terminated after receiving the response information from the learning terminal 2.

[0113] Specifically, in this embodiment, the task allocation terminal 1 obtains the learning progress score of each user, and then formulates a personalized learning task for each user based on the learning progress score of each user. The target learning terminal 2 monitors its own usage status information in real time and uploads the usage status information to the task allocation terminal 1. After the task allocation terminal 1 obtains the usage status information, it generates a task push list corresponding to each user based on the usage status information, and then the task allocation terminal 1 pushes the learning tasks to the corresponding learning terminal 2 in sequence according to the order of the target learning terminal 2 in the task push list.

[0114] Among them, the learning task assigner includes teachers, parents, etc., and the task assignment terminal 1 includes a mobile phone, a computer, a tablet, etc. The learning terminal 2 includes a smart desk lamp (a desk lamp with any one or more of a camera, a microphone, a speaker, and also includes a wireless communication module), a tablet, a mobile phone, a smart watch (a watch with any one or more of a camera, a microphone, a speaker, and also includes a wireless communication module), etc.

[0115] Through this embodiment, the task distribution terminal 1 can formulate targeted learning tasks for different users according to the different learning progress score values ​​of each user, can effectively play an educational role, and can help users learn in a targeted and differentiated manner according to the learning tasks, which can improve the learning effect of users and improve usability. The task distribution terminal 1 can generate a task push list based on the usage status information, and then push the learning tasks to the corresponding learning terminals 2 in order of push level according to the task push list, avoiding the simultaneous distribution of learning tasks to all learning terminals 2 of a user, reducing the probability of repeated push of learning tasks, and reducing unnecessary push waste.

[0116] Based on the above embodiment, it includes:

[0117] The processing module 12 is used to input each resource data corresponding to each identification information into the resource allocation model to obtain the corresponding comparison result, and generate the corresponding task push list according to the comparison result and the corresponding user identity information;

[0118] The task push list includes the push levels of each learning terminal 2 corresponding to the current user identity information.

[0119] Specifically, the parts of this embodiment that are the same as those of the above embodiment will not be described one by one here. The upload period of each learning terminal 2 uploading its own usage status information to the assigned task terminal 1 can be set according to the user's own needs and habits. Resource data includes but is not limited to remaining power data, remaining memory data, remaining GPU data, remaining CPU data, and network data.

[0120] After the task assignment terminal 1 obtains the usage status information uploaded by the learning terminal 2, it saves the user identity information and identification information corresponding to the usage status information to different folders, and the user identity information folder includes several identification information folders, each of which includes resource data. For example, the user identity information of a user A is ID-1, and he uses tablet P1 and smart desk lamp T1 for learning. The identification information of tablet P1 is MA1C1, and the identification information of smart desk lamp T1 is MA1C2. Then the tablet P1 uploads its own usage status information A1 (the usage status information A1 includes resource data ZA1, identification information MA1C1 and the user's user identity information ID-1) to the task allocation terminal 1, and the smart desk lamp T1 uploads its own usage status information A2 (the usage status information A2 includes resource data ZA2, identification information MA1C2 and the user's user identity information ID-1) to the task allocation terminal 1. After the task allocation terminal 1 obtains the usage status information uploaded by the tablet P1 and the smart desk lamp T1, since the usage status information A1 and the usage status information A2 are analyzed to belong to the same user A, a large folder D1 is established for the identity information of user A. User A uses the tablet P1 and the smart desk lamp T1 for learning, and in the large file D1, subfolders named MA1C1 and MA1C2 are established according to the identification information of the learning terminal 2, wherein the resource data ZA1 is stored in the subfolder MA1C1, and the resource data ZA2 is stored in the subfolder MA1C2.

[0121] After the task allocation terminal 1 classifies and stores the acquired usage status information, each resource data corresponding to each identification information is input into the pre-trained resource allocation model, and the resource allocation model analyzes and outputs the corresponding comparison result. Since the resource data and the identification information are related to each other, and the identification information and the user identity information are related to each other, the comparison result corresponding to the resource data can be associated and bound with the user identity information corresponding to the resource data. Therefore, when the resource allocation model analyzes and obtains the corresponding comparison result, a comparison task push list can be generated. The task push list includes the push order of all learning terminals 2 of all users.

[0122] Exemplarily, user A uses tablet P1 (identification information is MAC1) and smart desk lamp T1 (identification information is MAC2) to learn. Tablet P1 uploads its own usage status information A1 to task allocation terminal 1, and smart desk lamp T1 uploads its own usage status information A2 to task allocation terminal 1. User B uses tablet P2 (identification information is MAC3) and smart desk lamp T2 (identification information is MAC4) to learn. Tablet P2 uploads its own usage status information A3 to task allocation terminal 1, and smart desk lamp T2 uploads its own usage status information A4 to task allocation terminal 1. Task allocation terminal 1 inputs each resource data corresponding to each identification information into the resource allocation model to obtain the corresponding comparison result, and then generates a task push list L1 corresponding to user A and a task push list L2 corresponding to user B based on the comparison result and its corresponding user identity information. Assume that task push list L1 is: the push level of tablet P1 is greater than the push level of smart desk lamp T1, and task push list L2 is: the push level of tablet P2 is less than the push level of smart desk lamp T2. Then, after the task allocation terminal 1 generates the learning task C1 for user A, it first pushes the learning task C1 to the tablet P1, and then pushes the learning task C1 to the smart desk lamp T1. After the task allocation terminal 1 generates the learning task C2 for user B, it first pushes the learning task C2 to the smart desk lamp T2, and then pushes the learning task C2 to the tablet P2. If learning tasks C1 and C2 are generated at the same time, then the task allocation terminal 1 can simultaneously push the learning task C1 to the tablet P1 first, and push the learning task C2 to the smart desk lamp T2, and then push the learning task C1 to the smart desk lamp T1, and push the learning task C2 to the tablet P2.

[0123] Through this embodiment, the task allocation terminal 1 can generate a task push list according to the usage status information, and then push the learning tasks to the corresponding learning terminals 2 in order of push levels according to the task push list, avoiding the synchronous distribution of learning tasks to all learning terminals 2 of a user, reducing the probability of repeated pushing of learning tasks, and reducing unnecessary push waste. In addition, distributed pushing of learning tasks according to push levels can also reduce the task volume of centralized distribution of learning tasks by the task allocation terminal 1, solving the problem of resource waste caused by centralized distribution of learning tasks by the task allocation terminal 1, or the problem of learning task issuance being stuck due to centralized distribution, avoiding resource waste while improving the effectiveness of learning task distribution and thus improving the user experience.

[0124] Based on the above embodiment, the processing module 12 includes: a first judgment unit, a first generation unit, and a processing unit;

[0125] The first judgment unit inputs each resource data corresponding to the current identification information into the resource allocation model, and compares each resource data with the resource allocation model to see whether it satisfies the corresponding preset condition;

[0126] The first generating unit is connected to the first judging unit and is used to generate a push level of the learning terminal 2 corresponding to the current identification information according to the comparison result;

[0127] The processing unit is connected to the first generating unit, and generates a task push list corresponding to each user according to the user identity information, identification information and the corresponding push level.

[0128] Specifically, the parts of this embodiment that are the same as the above-mentioned embodiments will not be described one by one here. The task allocation terminal 1 inputs all the resource data corresponding to the current identification information obtained into the pre-trained resource allocation model, and the resource allocation model compares whether each resource data meets its corresponding preset conditions. After the resource allocation model outputs the corresponding comparison result, the task allocation terminal 1 generates the push level of the learning terminal 2 corresponding to the current identification information based on the comparison result of each resource data corresponding to the current identification information. This is repeated, and each resource data corresponding to each identification information is input into the resource allocation model in turn, and the resource allocation model outputs the comparison result of each resource data corresponding to each identification information. In this way, the task allocation terminal 1 can analyze the push level of each learning terminal 2 based on the usage status information uploaded by all learning terminals 2, and then generate a task push list corresponding to each user.

[0129] Based on the aforementioned embodiment, the processing unit includes a first computing subunit and a second computing subunit;

[0130] The acquisition module 14 is connected to the first judgment unit and is also used to acquire the usage frequency and user demand of the learning terminal 2 corresponding to the current identification information when all resource data respectively meet the corresponding preset conditions;

[0131] The first calculation subunit is connected to the acquisition module 14, and is further used to determine the push level of the learning terminal 2 corresponding to the current identification information according to the usage frequency and user needs;

[0132] The second calculation sub-unit is connected to the first judgment unit, and is also used to perform weight calculation on each resource data corresponding to the current identification information when any resource data does not meet the corresponding preset conditions, and to obtain a total weight value by summing up the weight values ​​of each resource data, and to use the total weight value as the push level corresponding to the current identification information.

[0133] Specifically, the parts of this embodiment that are the same as the above embodiments will not be repeated here one by one. The task allocation terminal 1 obtains the information reception response rate and task execution rate of all learning terminals 2 under different sample resource data states. The sample resource data is trained to obtain the corresponding resource allocation model, and the resource allocation model is trained to obtain the resource allocation standards corresponding to different resource data. The resource allocation standards corresponding to each resource data are: the remaining power data needs to be greater than U%, the remaining memory data needs to be greater than V%, the remaining GPU data needs to be greater than W%, the remaining CPU data needs to be greater than M%, and the network data needs to be greater than N%.

[0134] The resource allocation model is a neural network model, and the sample resource data used when training the resource allocation model includes remaining power data samples, remaining memory data samples, remaining CPU data samples, remaining GPU data samples and network data samples, and the output samples include resource allocation standard samples. The present invention does not limit the training process of the resource allocation model. Schematically, the terminal operating system obtains the current remaining power data as "50%" and the remaining memory data as "1.5GB". After inputting the above data into the resource allocation model, the resource allocation standard output by the resource allocation model is obtained.

[0135] When all resource data meet the corresponding preset conditions, the push level of each identification information corresponding to the learning terminal 2 is determined according to the usage record and user needs. For example, it is assumed that the resource allocation standard is that the remaining power data needs to be greater than 50%, the remaining memory data needs to be greater than 50%, and the remaining CPU data needs to be greater than 40%. In addition, the weight coefficients corresponding to the remaining power data, the remaining memory data, and the remaining CPU data are 0.6, 0.2, and 0.2, respectively. If user C uses smart watch S1 (identification information is MAC5) and smart desk lamp T3 (identification information is MAC6) for learning, smart watch S1 uploads its own usage status information A5 to the allocation task terminal 1 (the remaining power data in the resource data is 70%, the remaining memory data is 80%, and the remaining CPU data is 65%), and the smart desk lamp T3 uploads its own usage status information A6 to the allocation task terminal 1 (the remaining power data in the resource data is 60%, the remaining memory data is 60%, and the remaining CPU data is 60%). Then the task allocation terminal 1 can compare the remaining power data corresponding to the identification information MAC5 and the identification information MAC6 through the resource allocation model to obtain that the remaining power data corresponding to the identification information MAC5 and the identification information MAC6 all meet the corresponding preset power condition threshold, the remaining memory data corresponding to the identification information MAC5 and the identification information MAC6 all meet the corresponding preset memory condition threshold, and the remaining CPU data corresponding to the identification information MAC5 and the identification information MAC6 all meet the corresponding preset CPU condition threshold. Therefore, the task allocation terminal 1 determines that all resource data corresponding to the smart watch S1 and the smart desk lamp T3 meet the corresponding preset conditions respectively. At this time, the usage record corresponding to the current identification information of the task allocation terminal 1 is then obtained, and the usage frequency and user needs of the learning terminal 2 corresponding to the current identification information are obtained. According to the usage frequency and user needs, the push level of the learning terminal 2 corresponding to the current identification information is determined. Among them, the usage record corresponding to the current identification information counts the number of times the current identification information is used, and the more times it is used, the greater the frequency of use. If the user considers increasing the usage rate of other learning terminals 2 and reducing the idle rate of learning terminal 2, the learning terminal 2 with a lower usage frequency has a higher corresponding push level. If the user considers based on usage habits to avoid unskilled learning operations and reduce learning efficiency, the learning terminal 2 with a higher usage frequency has a higher corresponding push level.

[0136] When any resource data does not meet the corresponding preset conditions, a weight calculation is performed on each resource data corresponding to the current identification information to obtain the weight value corresponding to each resource data, and the total weight value is calculated by summing up the weight value of each resource data, and the total weight value is used as the push level corresponding to the current identification information. Exemplarily, it is assumed that the resource allocation standard is that the remaining power data needs to be greater than 50%, the remaining memory data needs to be greater than 50%, and the remaining CPU data needs to be greater than 40%. If user C uses smart watch S1 (identification information is MAC5) and smart desk lamp T3 (identification information is MAC6) for learning, smart watch S1 uploads its own usage status information A5 to the allocation task terminal 1 (the remaining power data in the resource data is 40%, the remaining memory data is 80%, and the remaining CPU data is 65%), and smart desk lamp T3 uploads its own usage status information A6 to the allocation task terminal 1 (the remaining power data in the resource data is 70%, the remaining memory data is 60%, and the remaining CPU data is 25%). Then the allocation task terminal 1 can compare the resource allocation model to obtain that the remaining power data corresponding to the identification information MAC5 does not meet the corresponding preset power condition threshold, the remaining memory data corresponding to the identification information MAC5 meets the corresponding preset memory condition threshold, and the remaining CPU data corresponding to the identification information MAC5 meets the corresponding preset CPU condition threshold. The remaining power data corresponding to the identification information MAC6 does not meet the corresponding preset power condition threshold, the remaining memory data corresponding to the identification information MAC6 meets the corresponding preset memory condition threshold, and the remaining CPU data corresponding to the identification information MAC6 does not meet the corresponding preset CPU condition threshold. Therefore, the allocation task terminal 1 determines that the resource data corresponding to the smart watch S1 and the smart desk lamp T3 meet different types of preset conditions, but the number of items is the same. At this time, the task allocation terminal 1 calculates the total weight value K1 corresponding to the identification information MAC5 = 0.6 × 40% + 0.2 × 80% + 0.2 × 65% = 0.53, and the total weight value K2 corresponding to the identification information MAC6 = 0.6 × 70% + 0.2 × 60% + 0.2 × 25% = 0.59. Since the total weight value is used as the push level, and K2>K1, the push level of the smart lamp T3 is greater than the push level of the smart watch S1. After the task allocation terminal 1 generates the learning task of user C, it first pushes the learning task C3 to the smart lamp T3, and then pushes the learning task C3 to the smart watch S1.

[0137] Through this embodiment, the push level of the learning terminal 2 corresponding to the current identification information can be determined by calculating the differences in different comparison results. In this way, when the number and type of resource data that meet the preset conditions are the same, the learning terminal 2 can receive the learning tasks issued by the task allocation terminal 1 in a timely manner and execute the corresponding learning tasks. At the same time, the push level can be determined according to the user's usage records and user needs, thereby meeting the user's personalized needs. When at least one of the number and type of resource data that meet the preset conditions is different, a weight calculation is performed to determine the push level, which can meet the purpose of the learning terminal 2 receiving the learning tasks issued by the task allocation terminal 1 in a timely manner.

[0138] Based on the above embodiment, the generation module 11 includes: an analysis unit, a second judgment unit, and a second generation unit;

[0139] The analyzing unit is used to analyze all the learning contents of the student and the score value corresponding to each learning content according to the learning progress score value;

[0140] The second judging unit is connected to the analyzing unit and is used to judge whether the score value corresponding to each learning content is greater than the corresponding set score;

[0141] The second generating unit is connected to the judging unit and is used to filter the required learning contents whose scores are less than the corresponding set scores to obtain a target learning set, and formulate corresponding learning tasks according to the target learning set.

[0142] Specifically, the task allocation terminal 1 obtains all the student's learning contents and the score values ​​corresponding to each learning content based on the learning progress score analysis. Since the student's learning content can be one or more, the task allocation terminal 1 determines whether the score value corresponding to the current learning content is greater than its corresponding set score. After judging the current learning content, if the number of learning contents is greater than one, switch to the next learning content to continue judging until all learning contents are judged. All judgment results are recorded, and all learning contents with score values ​​less than their corresponding set scores are screened out to obtain the target learning set, and then learning tasks are formulated according to the target learning set.

[0143] For example, the task assignment terminal 1 analyzes the score of a certain student A in mathematics based on the learning progress score and obtains that the score is 0.86 and the score is 0.66 in English. Assuming that the set scores of mathematics, English, chemistry and biology are 0.9, 0.9, 0.8 and 0.8 respectively, then the comparison shows that the score of mathematics, English and biology is less than the corresponding set score. Therefore, the target learning set includes mathematics, English and biology. The learning task formulated according to the target learning set is mathematics + English + biology learning task. The setting of other set scores is also within the protection scope of the present invention and will not be repeated here.

[0144] Preferably, the required learning content with a score value less than the corresponding set score is screened, and the difference between the score value of the required learning content and its corresponding set score is calculated. According to the difference, the corresponding learning task is formulated in order of size, so that the difference is proportional to the learning time. That is, the learning content with a lower difference has a shorter learning time in the learning task, and conversely, the learning content with a higher difference has a longer learning time in the learning task. Exemplarily, by comparative calculation, it can be calculated that the difference between the score values ​​of mathematics subjects, English subjects, and biology subjects and their corresponding set scores is 0.04, 0.34, and 0.02, respectively. Therefore, it can be analyzed that the English subject must strengthen the learning intensity, and the mathematics subject and the biology subject are second. Therefore, the learning tasks formulated for student A are T1, T2, and T3 for mathematics subjects, English subjects, and biology subjects, respectively, and T2>T1>T3.

[0145] Through this embodiment, the target learning set is obtained by comparing the score value of each learning content with the set score, and the learning task is formulated according to the target learning set. The score value of each learning content can be calculated in a targeted manner according to the student's learning content and learning situation, so as to obtain the student's learning progress score value, which is convenient for subsequent formulation of targeted learning tasks for different students according to the different learning progress score values ​​of each student, can effectively play an educational role, and carry out targeted and differentiated intensive training to improve students' learning efficiency and greatly improve students' learning effects.

[0146] Preferably, the learning content and learning status of the current user are obtained; the learning status includes the completion time and accuracy rate corresponding to the learning content. The completion time and accuracy rate are weighted according to the weight value in the evaluation standard to obtain the score value corresponding to the learning content. The learning content and its corresponding score value are summarized to obtain the learning progress score value corresponding to the current user.

[0147] Specifically, the completion time is the time taken to complete the learning content divided by the prescribed time. The learning content of each user is recorded, and the user's daily learning results are scored. The completion time and accuracy of each learning content are calculated. The learning content and learning situation can be obtained manually or automatically. The manual acquisition method includes the learning task assignor manually entering the user's learning content and learning situation into the task assignment terminal 1. There are many automatic acquisition methods, such as all the user's learning terminals 2 (learning machines, smart desk lamps, tablets, mobile phones, smart watches, etc.) and the like to record the user's learning content, and then the learning terminal 2 corrects and scores the user's daily learning results to obtain the learning situation, and finally the learning terminal 2 uploads the learning content and learning situation to the task assignment terminal 1 of the learning task assignor. Any method of obtaining the user's learning content and learning situation is within the protection scope of the present invention, and will not be repeated here. The evaluation criteria include a weight value for completion time and a weight value for accuracy pre-set by the learning task assigner, and the weight value corresponding to the completion time of each learning content may be the same or different, and the weight value corresponding to the accuracy of each learning content may be the same or different.

[0148] The task assignment terminal 1 obtains all the learning contents of the current user and the learning status of each learning content. Then, the task assignment terminal 1 performs weight calculations on the completion time and accuracy corresponding to the current learning content according to the pre-set evaluation criteria to obtain the score value corresponding to the current learning content. The task assignment terminal 1 calculates the score value corresponding to each learning content, and then summarizes all the learning contents of the current user and their corresponding score values ​​to obtain the learning progress score value of the current user.

[0149] In addition, the task assignment terminal 1 pushes the learning task to the learning terminal 2 with the highest push level according to the task push list. When the response information is received from the learning terminal 2 with the highest level, the learning task is stopped. When the response information is not received from the learning terminal 2 with the highest level, the learning task is pushed to the learning terminal 2 with the next push level according to the task push list, until any learning terminal 2 with a push level in the task push list feeds back its response information to the task assignment terminal 1 and the push is terminated.

[0150] Through this embodiment, it is possible to calculate the score value of each learning content in a targeted manner according to the user's learning content and learning situation, thereby obtaining the user's learning progress score value, which is convenient for subsequent formulation of targeted learning tasks for different users based on the different learning progress score values ​​of each user, can effectively play an educational role, and carry out targeted and differentiated intensive training to improve the user's learning efficiency and greatly improve the user's learning effect.

[0151] It should be noted that the above embodiments can be freely combined as needed. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention.

Claims

1. A method for controlling the distribution of learning tasks, characterized in that: Includes steps: Formulate corresponding learning tasks according to the user's learning progress score; Acquire usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal; the resource data is associated with the identification information, and the identification information is associated with the user identity information; Generate a task push list for each user according to the usage status information; the task push list includes the push level of each learning terminal corresponding to the current user identity information; According to the task push list, the learning tasks are pushed to the corresponding learning terminals in the order of the push levels from high to low, until the push is terminated after receiving the response information from the learning terminal; The step of generating a task push list for each user according to the usage status information comprises the following steps: Input each resource data corresponding to each identification information into the resource allocation model to obtain the corresponding comparison result, and generate the corresponding task push list according to the comparison result and the corresponding user identity information; Also includes: When receiving the response information fed back by the highest-ranking learning terminal in the task push list, stop pushing the learning task; When no response information is received from the highest-level learning terminal in the task push list, the learning task is pushed to the learning terminal of the next push level according to the task push list, until a learning terminal of any push level in the task push list feeds back a response information, and the push is terminated.

2. The method for controlling the distribution of learning tasks according to claim 1, characterized in that: The step of inputting each resource data corresponding to each identification information into the resource allocation model to obtain a corresponding comparison result, and generating a corresponding task push list according to the comparison result and its corresponding user identity information specifically includes the following steps: Input each resource data corresponding to the current identification information into the resource allocation model, and compare each resource data with the resource allocation model to see whether it satisfies the corresponding preset condition; Generating a push level of the learning terminal corresponding to the current identification information according to the comparison result; A task push list corresponding to each user is generated according to the user identity information, identification information and the corresponding push level.

3. The method for controlling the distribution of learning tasks according to claim 2, characterized in that: The step of generating the push level of the learning terminal corresponding to the current identification information according to the comparison result specifically comprises the following steps: When all resource data respectively meet corresponding preset conditions, obtaining the usage frequency and user demand of the learning terminal corresponding to the current identification information, and determining the push level of the learning terminal corresponding to the current identification information according to the usage frequency and user demand; When any resource data does not meet the corresponding preset conditions, a weight calculation is performed on each resource data corresponding to the current identification information, and the total weight value is obtained by summing up the weight values ​​of each resource data, and the total weight value is used as the push level corresponding to the current identification information.

4. The method for controlling the distribution of learning tasks according to any one of claims 1 to 3, characterized in that: The step of formulating corresponding learning tasks according to the learning progress score of the user comprises the following steps: Analyze all the learning contents of the student and the score value corresponding to each learning content according to the learning progress score value; Determine whether the score value corresponding to each learning content is greater than the corresponding set score; The required learning contents with score values ​​less than the corresponding set score are screened to obtain a target learning set, and corresponding learning tasks are formulated according to the target learning set.

5. A distribution control system for learning tasks, characterized in that: include: Assigning task terminal and learning terminal; the assignment task terminal comprises a generating module, an acquiring module, a processing module and a first communication module; The learning terminal includes a second communication module; The generation module is used to formulate corresponding learning tasks according to the learning progress score of the user; The acquisition module is used to acquire the usage status information uploaded by the learning terminal; the usage status information includes resource data, identification information, and user identity information corresponding to the learning terminal; the resource data and the identification information are mutually associated, and the identification information and the user identity information are mutually associated; The processing module is connected to the acquisition module and is used to generate a task push list for each user according to the usage status information; the task push list includes the push level of each learning terminal corresponding to the current user identity information; The first communication module is connected to the generation module, the processing module and the second communication module, and pushes the learning tasks to the corresponding learning terminals in the order of the push levels from high to low according to the task push list, until the push is terminated after receiving the response information of the learning terminal; The processing module is used to input each resource data corresponding to each identification information into the resource allocation model to obtain the corresponding comparison result, and generate the corresponding task push list according to the comparison result and the corresponding user identity information; The task distribution terminal is further used to push the learning task to the learning terminal with the highest push level according to the task push list, and stop pushing the learning task when receiving the response information fed back by the learning terminal with the highest level; The task allocating terminal is also used to push the learning task to the learning terminal of the next push level according to the task push list when no response information is received from the highest-level learning terminal, until the learning terminal of any push level in the task push list feeds back response information to the task allocating terminal, and the push is terminated.

6. The learning task distribution control system according to claim 5, characterized in that: The processing module includes: a first judgment unit, a first generation unit, and a processing unit; The first judgment unit inputs each resource data corresponding to the current identification information into the resource allocation model, and compares each resource data with the resource allocation model to see whether it satisfies the corresponding preset condition; The first generating unit is connected to the first judging unit and is used to generate a push level of the learning terminal corresponding to the current identification information according to the comparison result; The processing unit is connected to the first generating unit, and generates a task push list corresponding to each user according to the user identity information, identification information and the corresponding push level.

7. The learning task distribution control system according to claim 6, characterized in that: The processing unit includes a first computing subunit and a second computing subunit; The acquisition module is connected to the first judgment unit and is further used to acquire the usage frequency and user demand of the learning terminal corresponding to the current identification information when all resource data respectively meet the corresponding preset conditions; The first calculation subunit is connected to the acquisition module and is further used to determine the push level of the learning terminal corresponding to the current identification information according to the usage frequency and user needs; The second calculation sub-unit is connected to the first judgment unit, and is also used to perform weight calculation on each resource data corresponding to the current identification information when any resource data does not meet the corresponding preset conditions, and to obtain a total weight value by summing up the weight values ​​of each resource data, and to use the total weight value as the push level corresponding to the current identification information.

8. The learning task distribution control system according to any one of claims 6-7, characterized in that: The generation module includes: an analysis unit, a second judgment unit, and a second generation unit; The analyzing unit is used to analyze all the learning contents of the student and the score value corresponding to each learning content according to the learning progress score value; The second judging unit is connected to the analyzing unit and is used to judge whether the score value corresponding to each learning content is greater than the corresponding set score; The second generating unit is connected to the judging unit and is used to filter the required learning contents whose scores are less than the corresponding set scores to obtain a target learning set, and formulate corresponding learning tasks according to the target learning set.

Images