Learning supervising and urging method, electronic equipment and computer readable storage medium

Abstract

The invention discloses a learning supervising and urging method, electronic equipment and a computer readable storage medium. The learning supervising and urging method applied to a server comprises the steps that learning states of a user in multiple dimensions are acquired, and the multiple dimensions comprise the user, friends of the user and classes where the user is located; determining a plurality of supervision labels of the user according to the learning states of the plurality of dimensions; inputting the plurality of study supervision labels and the first cue word into a preset generation model to carry out study supervision information generation operation so as to obtain a plurality of pieces of study supervision information; and issuing the multiple pieces of study supervision information in sequence so as to supervise and urge the user to learn. By utilizing the scheme disclosed by the invention, the enthusiasm of the user to participate in learning can be stimulated, and the user is helped to relieve unwanted learning mood, so that the user is guided to learn in class, and the supervising and urging effect is improved.

Description

Technical Field

[0001] The present disclosure generally relates to the field of Internet technology. More specifically, the present disclosure relates to a method for urging learning applied to a server, an electronic device, and a computer-readable storage medium. Further, the present disclosure also relates to a method for urging learning applied to a client, an electronic device, and a computer-readable storage medium. Background Art

[0002] In online education and training, how to urge users to learn and improve their attendance rate has always been a pain point for learning platforms. After purchasing a course on a learning platform, users usually forget to study or do not want to study, which results in them not being able to attend the course in time according to the course schedule. This not only affects the user's course learning effect, but also increases the difficulty for the platform to provide operational services to users.

[0003] In response to the above situation where users are unable to attend classes on time, existing supervision schemes usually push boring reminder information to users at fixed time periods based on whether the user has completed the study. Since the supervision conditions and forms are too simple, this supervision scheme cannot effectively stimulate the user's enthusiasm for learning and guide the user to attend classes, resulting in poor supervision effects. At the same time, repetitive and boring reminder information may also make users feel bored, which in turn reduces their positive attitude towards learning.

[0004] In view of this, there is an urgent need to provide a solution to urge users to attend classes, so as to stimulate users' enthusiasm for learning, help users relieve their unwillingness to learn, and improve the supervision effect. Summary of the invention

[0005] In order to at least solve one or more of the technical problems mentioned above, the present disclosure proposes solutions for urging users to attend classes in the following aspects.

[0006] In the first aspect, the present disclosure provides a method for supervising learning applied to a server, comprising: obtaining a user's learning status in multiple dimensions, wherein the multiple dimensions include the user himself, the user's friends and / or the user's class; determining a plurality of supervisor tags of the user according to the learning status in the multiple dimensions; inputting the plurality of supervisor tags and a first prompt word into a preset generation model to perform a supervisor information generation operation to obtain a plurality of supervisor information; and issuing the plurality of supervisor information in sequence to supervise the user's learning.

[0007] In some embodiments, the learning status includes the user's own learning status, the user's friend's learning status and / or the user's class learning status; the supervisor tag includes the user's own supervisor tag, the user's friend's supervisor tag and / or the user's class supervisor tag; the supervisor information includes the supervisor location and supervisor content; the supervisor location includes desktop components and / or desktop icons, and the supervisor content includes text and / or pictures.

[0008] In some embodiments, issuing the multiple inspector information in sequence includes: determining the inspector weight of each inspector information, and sorting the multiple inspector information according to the inspector weight to obtain an inspector information sequence; matching the inspector information sequence with a preset inspector plan to obtain an inspector information distribution list; and issuing the multiple inspector information in sequence according to the inspector information distribution list.

[0009] In some embodiments, determining the inspector weight of each inspector information includes: obtaining the user's historical click data for historical inspector information; inputting the historical click data and the second prompt word into a preset judgment model to perform an inspector preference judgment operation to obtain the user's inspector preference, wherein the inspector preference includes inspector location preference and inspector content preference; and inputting the multiple inspector information, inspector preferences and the third prompt word into the preset judgment model to perform an inspector weight judgment operation to obtain the inspector weight of each inspector information.

[0010] In some embodiments, the preset inspector plan is used to identify the correspondence between inspector time and inspector weight; matching the inspector information sequence and the preset inspector plan to obtain an inspector information distribution list includes: matching the inspector information sequence and the preset inspector plan according to the inspector weight to determine the inspector time of each inspector information in the inspector information sequence; sorting the multiple inspector information according to the inspector time to obtain an inspector information distribution list.

[0011] In the second aspect, the present disclosure provides a method for supervising learning applied to a client, comprising: receiving supervisor information issued according to the method described in the first aspect and its multiple embodiments; displaying the supervisor information to supervise the user's learning.

[0012] In some embodiments, the inspector information includes the inspector's position and inspector's content; the displaying of the inspector information to urge the user to learn includes: parsing the inspector information to obtain the current inspector's position and the current inspector's content; and displaying the current inspector's content at the current inspector's position to urge the user to learn.

[0013] In some embodiments, the inspector's position includes a desktop component and / or a desktop icon, the inspector's content includes text and / or pictures, and displaying the current inspector's content at the current inspector's position includes: obtaining a preset template style for the current inspector's position; adjusting the style of the text according to the text style in the preset template style, and / or adjusting the style of the picture according to the picture style in the preset template style to obtain text and / or pictures that conform to the preset template style; and displaying text and / or pictures that conform to the preset template style at the current inspector's position according to the position layout in the preset template style.

[0014] In a third aspect, the present disclosure provides an electronic device comprising: a processor; and a memory storing program instructions for promoting learning on a server side or on a client side, wherein when the program instructions are executed by the processor, the method and its multiple embodiments described in the first aspect or the second aspect are implemented.

[0015] In the third aspect, the present disclosure provides a computer-readable storage medium having stored thereon program instructions for supervised learning applied to a server or for supervised learning applied to a client. When the program instructions are executed by a processor, the method described in the first aspect or the second aspect and its multiple embodiments are implemented.

[0016] Through the supervision learning method provided above, when the user is unable to attend class on time, the learning status of the user, the user's friends, and the user's class in multiple dimensions can be analyzed, and a plurality of different supervisor information can be generated using the preset generation model. The active learning status of the user's friends and the user's class can stimulate the user's enthusiasm for participating in learning, help the user relieve the emotion of not wanting to learn, thereby guiding the user to attend class and improve the supervision effect. At the same time, the preset generation model can be used to generate richer and more interesting supervisor information, which has better appeal to users and can increase the possibility of supervisor information reaching users, thereby improving the influence and supervision effect of supervisor information. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] By reading the detailed description below with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0018] Figure 1 An exemplary flow chart of a supervised learning method applied to a server according to some embodiments of the present disclosure is shown;

[0019] Figure 2An exemplary flow chart showing a supervised learning method applied to a server according to other embodiments of the present disclosure is shown;

[0020] Figure 3 An exemplary flow chart of a supervised learning method applied to a client according to an embodiment of the present disclosure is shown;

[0021] Figure 4 An exemplary effect diagram showing the contents of the supervisor on the desktop icon according to the embodiment of the present disclosure is shown;

[0022] Figure 5 An exemplary effect diagram showing the contents of the supervisor on the desktop component according to the embodiment of the present disclosure is shown;

[0023] Figure 6 An exemplary structural block diagram of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present disclosure.

[0025] It should be understood that when the terms "first", "second", "third" and "fourth" are used in the claims, the specification and the drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present disclosure indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0026] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0027] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0028] The specific implementation of the present disclosure is described in detail below with reference to the accompanying drawings.

[0029] Figure 1 1 is an exemplary flow chart showing a supervised learning method 100 applied to a server according to some embodiments of the present disclosure. It is understood that the server refers to a computer or server responsible for background tasks such as processing client requests, executing business logic, and managing databases in online learning. Therefore, the method 100 can be executed by any appropriate device with data processing capabilities, such as, but not limited to, computers and servers.

[0030] It is understandable that in order to avoid causing trouble to the user and save processing resources, method 100 usually does not urge the user to study when the user has completed the course, but urges the user to study when it is found that the user has not completed the course. Specifically, before executing the following steps S101 to S104, method 100 can first determine whether the user has not completed the course by checking the user's learning record. Thereafter, if the user has not completed the course, the following steps S101 to S104 can be continued to be executed to urge the user to study.

[0031] It is also understandable that after the user purchases the course, the online learning platform will not unlock all courses at once, but will unlock courses in sequence according to the course schedule. Therefore, the method 100 checks the user's learning record to determine whether the user has unfinished courses, that is, whether the user has unfinished unlocked courses.

[0032] like Figure 1 As shown, at step S101, method 100 can obtain the learning status of multiple dimensions of the user. The multiple dimensions of the user may include the user himself, the user's friends and / or the user's class, and may also include the user's age group and / or the user's region (for example, province, city, district and county), etc. Correspondingly, the learning status of multiple dimensions may include the user's own learning status, the user's friends' learning status and / or the user's class learning status, and may also include the user's age group learning status and / or the user's region learning status, etc.

[0033] In the scheme disclosed herein, user friends can be other users who have established friendships with the user on the online learning platform, or user friends that the online learning platform learns from social software after obtaining the user's social software access rights. The class that the user belongs to refers to the class formed by the online learning platform based on the course time and / or course content purchased by the user. The age group of the user refers to the segmentation defined by the online learning platform based on the age information provided by the user. The region where the user is located refers to the region defined by the online learning platform based on the address information provided by the user.

[0034] In the scheme disclosed herein, the learning status is used to describe the user's learning status of unlocked courses, for example, the number of unlocked courses that have been completed and / or the number of unlocked courses that have not been completed. Generally speaking, the user's learning status of unlocked courses can be obtained by viewing the user's learning record, and then the user's own learning status can be determined. Furthermore, the user's own learning status may include that the number of unlocked courses that the user has completed is 0, the number of unlocked courses that the user has completed is less than the total number of unlocked courses and the number of unlocked courses that have not been completed is greater than 1, the number of unlocked courses that the user has not completed is 1, and so on.

[0035] In the scheme disclosed herein, the purpose of obtaining the learning status of the user's friends, the learning status of the user's class, the learning status of the user's age group, and the learning status of the user's region is to use the status of other users completing their learning to positively motivate the user, or to use the status of other users not completing their learning to negatively stimulate the user. Based on this, the learning status of the user's friends, the learning status of the user's class, the learning status of the user's age group, and the learning status of the user's region can be determined based on whether other users have completed the unlocked course learning. Therefore, the learning status of the user's friends can also include completing all unlocked course learning and not completing the unlocked course learning.

[0036] The learning status of the user's class can be represented by the percentage of the number of users in the class who have completed the unlocked course and / or the number of users who have not completed the unlocked course, for example, all other users in the class have completed the unlocked course, more than a first threshold (for example, 90%) of other users in the class have completed the unlocked course, more than a second threshold (for example, 50%) of other users in the class have completed the unlocked course, and less than a third threshold (for example, 5%) of other users in the class have not completed the unlocked course, and so on.

[0037] Similarly, the learning status of the user's age group can be represented by the percentage of the number of users in the age group who have completed the unlocked course learning and / or the number of users who have not completed the unlocked course learning. The learning status of the user's region can be represented by the percentage of the number of users in the region who have completed the unlocked course learning and / or the number of users who have not completed the unlocked course learning. It can be understood that the above-mentioned percentages of 90%, 50% and 5% are merely exemplary and illustrative, and not restrictive. Those skilled in the art can select specific values ​​or value ranges of the first threshold, the second threshold and the third threshold according to actual needs.

[0038] Next, at step S102, method 100 may determine multiple supervisor tags of the user according to the learning status of multiple dimensions. In this embodiment, the supervisor tags may include the user's own supervisor tag, the user's friend supervisor tag, and the user's class supervisor tag, and may also include the user's age group supervisor tag and the user's region supervisor tag, etc.

[0039] The user's own supervisor label can include not started learning, interrupted learning, and continuous learning, etc. Specifically, when the number of unlocked courses that the user has completed learning is 0, the user's own supervisor label can be determined as not started learning; when the number of unlocked courses that the user has completed learning is less than the total number of unlocked courses and the number of unlocked courses that have not been completed is greater than 1, the user's own supervisor label can be determined as interrupted learning; when the number of unlocked courses that the user has not completed learning is 1, the user's own supervisor label can be determined as continuous learning.

[0040] The user friend supervisor label can include the user friend completed learning and the user friend incomplete learning. Specifically, when the user friend's learning status is completed all unlocked courses, the user friend supervisor label can be determined as the user friend completed learning; when the user friend's learning status is incomplete unlocked courses, the user friend supervisor label can be determined as the user friend incomplete learning.

[0041] The supervisor label of the user's class can include the whole class completed learning, the whole class completed learning exceeding the first threshold, the whole class completed learning exceeding the second threshold, and the whole class failed to complete learning with less than the third threshold. Specifically, when other users in the class have completed the unlocked course learning, it can be determined that the supervisor label of the user's class has completed learning; when other users in the class have completed the unlocked course learning exceeding the first threshold, it can be determined that the supervisor label of the user's class has completed learning with more than the first threshold; when other users in the class have completed the unlocked course learning exceeding the second threshold, it can be determined that the supervisor label of the user's class has completed learning with more than the second threshold; when other users in the class have failed to complete the unlocked course learning with less than the third threshold, it can be determined that the supervisor label of the user's class has failed to complete learning with less than the third threshold. Similarly, the supervisor label of the user's age group and the supervisor label of the user's region can also be determined based on the learning status of the user's age group and the learning status of the user's region.

[0042] Next, at step S103, the method 100 may input a plurality of inspector labels and a first prompt word into a preset generation model to perform an inspector information generation operation to obtain a plurality of inspector information.

[0043] In the scheme disclosed herein, the preset generation model may be a natural language processing model Chat GPT, which may perform inspector information generation operations under the guidance of multiple inspector labels and a first prompt word. Guided by multiple inspector labels and a first prompt word, the preset generation model may generate inspector information that is more in line with the actual status of the user. Typically, for one inspector label, the preset generation model may generate one inspector information accordingly. The inspector information may include the inspector position and inspector content, wherein the inspector position may indicate the display position of the inspector content on the client, and the inspector content may indicate the specific content that needs to be displayed at the inspector position.

[0044] As those skilled in the art know, existing supervision schemes mainly display supervisor information through three methods: text messages, message push, and public account template messages. However, all three methods rely on opening third-party applications, and the third-party applications can only receive supervisor information after obtaining system authorization. The process of reaching supervisor information is highly complex and prone to information loss. In addition, for users, faced with massive text message prompts, push message prompts, and public account template messages sent by different applications, the information density is too high, which can easily lead to information neglect or even information blocking.

[0045] In order to reduce information loss and shielding, in the scheme disclosed in the present invention, the inspector location may include desktop components and / or desktop icons. Here, the desktop component will be displayed on the client as long as the user adds it on the desktop of the client, and the desktop icon will be displayed on the client as long as the user downloads the application. As a result, users no longer need to click additionally to enter the application, they only need to turn on their mobile phones / tablets to receive inspector information, which helps to reduce information loss and shielding problems caused by the high complexity of the contact process. At the same time, compared to the traditional push logic that actively disturbs users, the inspector content disclosed in the present invention is displayed on desktop components and / or desktop icons, which relies on users to actively discover and generate interest, will not make users feel bored, and avoids affecting users' positive attitudes.

[0046] In addition, the existing supervision schemes are limited by the display method. The supervisory content is mainly in text form, and the number of words is limited. The content template is fixed, so it is not effective to attract users to participate in course learning. In the scheme disclosed in the present invention, the supervisory content can include text and / or pictures, and the pictures can be static pictures or dynamic pictures. Compared with pure text, the combination of pictures and text can provide more information and enhance the interest of supervisory information. Especially when the user is a child, the interest of supervisory information is more helpful to attract users to participate in course learning.

[0047] In the solution disclosed herein, the first prompt word may include supervisor location prompt information and supervisor content prompt information. The supervisor location prompt information is used to give a prompt to the preset generation model regarding the display location of the supervisor content on the client. For example, the supervisor location prompt information may be displayed through a desktop component or a desktop icon.

[0048] Similarly, the supervisor content prompt information is used to give prompts to the preset generation model regarding the generation logic of the supervisor content and its display form on the client. For example, the display form can be text, picture, or a combination of text and picture. The generation logic is used to indicate the logical relationship between the supervisor content and the supervisor tag, for example, the supervisor content is generated based on the user's own supervisor tag and the user's friend's supervisor tag; the supervisor content is generated based on the user's own supervisor tag and the user's class supervisor tag; the supervisor content is generated based on the user's own supervisor tag, the user's friend's supervisor tag, and the user's class supervisor tag, and so on.

[0049] As an example, when the user's own supervisor tag is "Not Started Learning" and the user's friend's supervisor tag is "Friend Completed Learning", the supervisor content generated may be "Friend XX has completed learning". As another example, when the user's own supervisor tag is "Not Started Learning" and the user's class's supervisor tag is "The whole class has completed learning", the supervisor content generated may be "You are the only one who has not yet learned in the class".

[0050] Finally, at step S104, method 100 may send out multiple supervisor information in sequence to urge the user to study.

[0051] In the scheme disclosed herein, multiple times (which may be referred to as supervisory times) at which supervisory information can be issued may be pre-set to obtain a preset supervisory plan. In other words, the preset supervisory plan may include multiple supervisory times. Thus, method 100 may issue different supervisory information to the user's client at different supervisory times to urge the user to study. In actual operation, method 100 may randomly match different supervisory times in the preset supervisory plan for each supervisory information.

[0052] In actual operation, in order to avoid adversely affecting the user experience of using the online learning platform and to ensure the normal display of the inspector information, the above steps S101 to S103 can be performed during the idle period to obtain multiple inspector information, and multiple inspector information can be issued in sequence during the user active period to ensure that the multiple inspector information issued in sequence can reach the user. It is understandable that those skilled in the art can select idle periods and user active periods according to actual needs, and this disclosure does not make specific limitations on this. For example, the idle period can be selected as 23:00 on the same day to 3:00 the next day, and the user active period can be selected from after 3:00 the next day to before 23:00 the next day. This not only ensures the normal display of the inspector information, but also allows the inspector information to be updated daily to ensure the timeliness of the inspector information.

[0053] Furthermore, multiple times at which supervisor information can be issued can be selected during the user's active period to obtain a preset supervisor plan. Thus, different supervisor information can be issued at different supervisor times according to the preset supervisor plan. As an example, 6:00, 9:00, 12:00, 15:00, 17:00, 20:00, and 21:00 can be selected as multiple supervisor times in the preset supervisor plan.

[0054] Combination of the above Figure 1 A method 100 for supervising learning applied to a server is described. Through this method, when a user forgets to study due to being busy or does not want to study due to fear of difficulty, the learning status of multiple dimensions such as the user himself, the user's friends, and the user's class can be analyzed, and a plurality of different supervisor information can be generated using a preset generation model. The active learning status of the user's friends and the user's class can stimulate the user's enthusiasm for participating in learning and help the user alleviate the emotion of not wanting to learn. It realizes the supervision of learning around the two major scenarios of forgetting to go to class and not wanting to go to class, which helps to improve the supervision effect. At the same time, the preset generation model can be used to generate richer and more interesting supervisor information, which has better appeal to users and can increase the possibility of supervisor information reaching users, thereby improving the influence and supervision effect of supervisor information.

[0055] In practical applications, considering that different inspector information has different appeal to users, different inspector weights can be set for each inspector information, and then the order of issuing multiple inspector information can be determined according to the inspector weight. Figure 2 The illustrated supervision learning method 200 explains the process of sequentially sending a plurality of supervisor information.

[0056] Figure 2 FIG. 2 shows an exemplary flow chart of a method 200 for urging learning applied to a server according to some other embodiments of the present disclosure. Figure 2 At step S201, method 200 can obtain the learning status of multiple dimensions of the user. It should be noted that, in this embodiment, the content of step S201 is consistent with step S101 in the previous embodiment, and will not be repeated here.

[0057] Next, at step S202, method 200 can obtain multiple supervisor tags of the user according to the learning status of multiple dimensions. It should be noted that, in this embodiment, the content of step S202 is consistent with step S102 in the previous embodiment, and will not be repeated here.

[0058] Next, at step S203, method 200 may input multiple supervisor labels or first prompt words into a preset generation model to perform supervisor information generation operations to obtain multiple supervisor information. It should be noted that, in this embodiment, the content of step S203 is consistent with step S103 in the previous embodiment, and will not be repeated here.

[0059] Next, at step S204, method 200 may determine the inspector weight of each inspector information, and sort the plurality of inspector information according to the inspector weight to obtain an inspector information sequence.

[0060] In the scheme disclosed herein, the inspector weight of each inspector information can be determined based on the user's inspector preference. Usually, the user's inspector preference can include inspector position preference and inspector content preference. In actual operation, the user's inspector preference can be determined by the user's operation data (for example, historical click data) on historical inspector information. Here, the inspector position preference can identify the inspector position that is most attractive to the user. The inspector content preference can indicate the inspector content that is most attractive to the user. The inspector position and inspector content that are most attractive to the user can be the inspector position and inspector content with the most historical clicks.

[0061] Based on this, when determining the inspector weight of each inspector information, method 200 may first obtain the user's historical click data for historical inspector information. Then, the historical click data and the second prompt word may be input into a preset judgment model to perform an inspector preference judgment operation to obtain the user's inspector preference. Next, multiple inspector information, inspector preferences, and the third prompt word may be input into the preset judgment model to perform an inspector weight judgment operation to obtain the inspector weight of each inspector information.

[0062] In the scheme disclosed herein, the preset judgment model can be a natural language processing model Chat GPT. The second prompt word is used to guide the model to perform an inspector preference judgment operation based on the user's historical click data to obtain the user's inspector preference. The third prompt word is used to guide the model to perform an inspector weight judgment operation based on multiple inspector information and inspector preferences to obtain the inspector weight of each inspector information. Generally, the higher the similarity between the inspector position and inspector content in the inspector information and the inspector preference, the higher the inspector weight of the inspector information. That is, the stronger the appeal to the user, the higher the weight of the inspector information.

[0063] Next, at step S205, the method 200 may match the supervisor information sequence with the preset supervisor plan to obtain a supervisor information distribution list. In the supervisor information distribution list, each supervisor information may be arranged in order of supervisor time from early to late.

[0064] When matching the supervisor information sequence with the preset supervisor plan, the supervisor information with a greater supervisor weight can be matched with an earlier supervisor time in the preset supervisor plan, so as to attract users to participate in learning as early as possible. Furthermore, considering that users usually participate in online learning in their free time after study or work, different supervisor weights can be set for each supervisor time in the preset supervisor plan. Thus, the preset supervisor plan can include multiple supervisor times, multiple supervisor weights, and the corresponding relationship between them.

[0065] Based on this, when matching the inspector information sequence and the preset inspector plan, the inspector information sequence and the preset inspector plan can be matched according to the inspector weight to determine the inspector time of each inspector information in the inspector information sequence. In practical applications, different inspector weights are set for each inspector time in the preset inspector plan. A higher inspector weight can be set for the inspector time corresponding to the user's free time, and vice versa, a lower inspector weight can be set for the inspector time corresponding to the user's study and work, so that users can participate in online learning in a timely manner after seeing the inspector information, which helps to increase the influence of the inspector information.

[0066] It should be noted that the above-mentioned supervisory time is used to indicate the time point or time period for sending supervisory information. When the supervisory time is a time point, the server can send supervisory information when the time point is reached. When the supervisory time is a time period, the server can send supervisory information at any time point within the time period.

[0067] In an implementation scenario, the configuration of the preset supervisor plan can be completed by the operator through the configuration tool. Generally, the operator can configure the same preset supervisor plan for all users. Preferably, the operator can configure different preset supervisor plans for different types of users. In this implementation scenario, users can be divided into different user types according to their age, purchased courses and / or address information.

[0068] Therefore, when matching the user's supervisor information sequence with the preset supervisor plan, the user type can be determined based on the user's age, purchased courses and / or address information, and the preset supervisor plan corresponding to the user type can be determined as the target supervisor plan. Then, the user's supervisor information sequence and the target supervisor plan can be matched to obtain a supervisor information distribution list that is exclusive to the user.

[0069] Finally, at step S206, the method 200 may sequentially send multiple supervisor information according to the supervisor information distribution list. Figure 1 and Figure 2 This paper describes a supervised learning method applied to the server. Through this supervised learning method, the server can generate and distribute more interesting and rich supervision information that can stimulate the enthusiasm of users. Corresponding to the operations performed by the server, the client can perform the following combined Figure 3 The supervised learning method 300 applied to a client is described.

[0070] It is understood that the client refers to the software or device that the user directly interacts with during online learning. The client usually runs on the user's personal computer, smart terminal or other device, and is used to make requests to the server, receive data from the server, and display it to the user. Therefore, method 300 can be executed by any appropriate device with data processing capabilities, such as but not limited to a processor, a terminal, and a server.

[0071] Figure 3 FIG. 3 is an exemplary flow chart of a method 300 for supervised learning applied to a client according to an embodiment of the present disclosure. Figure 3As shown, at step S301, method 300 can receive inspector information issued by the server. It should be noted that the inspector information here is generated and issued according to the aforementioned supervised learning method applied to the server and its multiple embodiments. Combined with the previous description, it can be seen that the inspector information may include inspector location and inspector content. The inspector location may include desktop components and / or desktop icons, and the inspector content may include text and / or pictures.

[0072] Next, at step S302, the method 300 may display the supervisor information to urge the user to study. Specifically, the supervisor information may be parsed first to obtain the supervisor position (for distinction, it may be referred to as the current supervisor position) and supervisor content (for distinction, it may be referred to as the current supervisor content). Then, the current supervisor content may be displayed at the current supervisor position to urge the user to study.

[0073] Due to differences in system settings and user-defined settings, the preset template styles of desktop icons and desktop components of different users' clients may also be different. The preset template style can usually include information such as size, position layout, text style, and image style. The position layout can identify the reserved position of text and / or images. The text style can identify the font, font size, and color of the text. The image style can identify the shape, size, and resolution of the image.

[0074] Therefore, when method 300 displays the current supervisor content at the current supervisor position, the preset template style of the current supervisor position can be obtained first. Then, the text in the current supervisor content is adjusted in style according to the text style in the preset template style, and / or the picture in the current supervisor content is adjusted in style according to the picture style in the preset template style, so as to obtain text and / or pictures that conform to the preset template style. Finally, the text and / or pictures that conform to the preset template style can be displayed at the current supervisor position according to the position layout in the preset template style.

[0075] Here, you can refer to Figure 4 and Figure 5 Gain an understanding of how to present inspector information. Figure 4 FIG. 2 shows an exemplary effect diagram of displaying the content of the supervisor on the desktop icon according to an embodiment of the present disclosure. Figure 4 As shown, Figure a is a preset template style for desktop icons, under which only picture information is displayed without text information. Therefore, the desktop icons shown in Figure b for user 1 and the desktop icons shown in Figure c for user 2 both have only picture information without text information. However, the picture information seen by user 1 is completely different from the picture information seen by user 2, so that different faces can be achieved.

[0076] Figure 5FIG. 2 shows an exemplary effect diagram of displaying the supervisor content on the desktop component of the embodiment of the present disclosure. Figure 5 As shown, Figure a-1 is a preset template style of a square desktop component. Under this style, text information and picture information can be displayed at the same time, and the text information is displayed in the upper left corner. Therefore, the desktop component seen by user 1 shown in Figure a-2 and the desktop component seen by user 2 shown in Figure a-3 both have text information and picture information, and the text information is located in the upper left corner. However, the picture information and text information seen by user 1 ("It's time to go to class~") are completely different from the picture information and text information seen by user 2 ("Did you forget me?"), so that each person can have a different look.

[0077] Figure b-1 is a preset template style for a rectangular desktop component. In this style, text information and image information can be displayed at the same time, and the text information is displayed in the upper left corner. Therefore, the desktop component shown in Figure b-2 that user 1 sees and the desktop component shown in Figure b-3 that user 2 sees both have text information and image information, and the text information is located in the upper left corner. However, the image information and text information seen by user 1 ("Friend XX has completed today's study") are completely different from the image information and text information seen by user 2 ("You are the only one in the class who has not studied yet!"), so that each person can have a different look.

[0078] To facilitate understanding, the supervised learning method provided in this disclosure is explained with an example.

[0079] Assume that user A has purchased a writing course on an online learning platform, but has not taken the course on time. His friend user B has also purchased the course and has taken the course on time. At the same time, it is also assumed that user A has completed the application download and desktop component addition on the client. Next, the online learning platform can perform the following operations to urge user A to participate in the course.

[0080] On the server side:

[0081] At 23:00 on a certain day, all courses on the online learning platform have been completed. The platform obtains the learning status of user A in multiple dimensions, and obtains multiple supervisor tags of user A based on the learning status in multiple dimensions;

[0082] After the user completes labeling, multiple inspector labels or first prompt words are input into a preset generation model to perform an inspector information generation operation to obtain multiple inspector information;

[0083] After obtaining multiple inspector information, obtain the user's historical click data for the historical inspector information, and input the historical click data and the second prompt word into a preset judgment model to perform an inspector preference judgment operation to obtain the user's inspector preference;

[0084] Next, multiple inspector information, inspector preferences and the third prompt word are input into a preset determination model to perform an inspector weight determination operation to obtain the inspector weight of each inspector information;

[0085] Next, multiple inspector information is sorted according to the inspector weights to obtain an inspector information sequence;

[0086] Finally, the inspector information sequence and the preset inspector plan are matched to obtain the inspector information distribution list, and multiple inspector information are sent to the client of user A in sequence according to the inspector information distribution list.

[0087] On the client side:

[0088] Receive the supervisor information sent by the server;

[0089] The inspector information is parsed to obtain the current inspector position and current inspector content contained therein, and the current inspector content is displayed at the current inspector position, so that user A can see different inspector content at the preset inspector time.

[0090] Next, combine Figure 6 An electronic device 600 provided by the embodiment of the present disclosure is exemplarily introduced. Figure 6 As shown, the electronic device 600 of the embodiment of the present disclosure may include a processor 601 , a memory 602 , and a communication bus 603 .

[0091] In the process of a specific embodiment, the processor 601 may be at least one of an application-specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing image processing device (DSPD), a programmable logic image processing device (PLD), a field programmable gate array (FPGA), a CPU, a controller, a microcontroller, and a microprocessor. It can be understood that for different devices, the electronic device used to implement the function of the processor may also be other, which is not specifically limited in this embodiment.

[0092] In the embodiment of the present disclosure, the communication bus 603 is used to realize the connection communication between the processor 601 and the memory 602; the memory 602 stores program instructions applied to the server to supervise the learning or applied to the client to supervise the learning; when the processor 601 executes the program instructions stored in the memory 602, the present disclosure is realized. Figure 1 and Figure 2 The described supervised learning method applied to the server, or the present disclosure in combination with Figure 3 The described supervised learning method is applied to the client.

[0093] Combination of the above Figure 6 An electronic device that can be used to execute the disclosed supervised learning method applied to the server or the supervised learning method applied to the client is described. It should be understood that the device structure or architecture here is merely exemplary, and the implementation method and implementation entity of the present application are not limited thereto, but can be changed without departing from the spirit of the present application. It can be understood that the description of each embodiment in the present disclosure emphasizes the differences between the various embodiments, and the same or corresponding parts can be referenced to each other. For the purpose of brevity, the present disclosure will not go into details one by one.

[0094] According to the above description in combination with the accompanying drawings, those skilled in the art can also understand that the embodiments of the present application can also be implemented by a software program. Therefore, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores program instructions for controlling the startup of the device, and the program instructions can be used to implement the present disclosure in combination with the software program. Figure 1 and Figure 2 The described supervised learning method applied to the server, or the present disclosure in combination with Figure 3 The described supervised learning method is applied to the client.

[0095] It should be noted that although the operations of the method of the present application are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0096] Although multiple embodiments of the present disclosure have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art may think of many changes, modifications, and alternatives without departing from the thought and spirit of the present disclosure. It should be understood that in the process of practicing the present disclosure, various alternatives to the embodiments of the present disclosure described herein may be adopted. The attached claims are intended to define the scope of protection of the present disclosure, and therefore cover equivalents or alternatives within the scope of these claims.

[0097] The collection and acquisition of various data in this application complies with relevant laws and regulations and is authorized by the data provider. Any organization or individual that needs to obtain external data must obtain authorization in accordance with the law and ensure data security. It is not allowed to illegally collect, use, process, or transmit unauthorized or unprotected data, or to illegally buy, sell, provide, or disclose unauthorized or unprotected data.

Claims

1. A supervised learning method applied to a server, comprising: Acquire the learning status of the user in multiple dimensions, wherein the multiple dimensions include the user himself, the user's friends and / or the class the user is in; Determining a plurality of supervisor tags of the user according to the learning status information of the plurality of dimensions; Inputting the plurality of supervisor labels and the first prompt word into a preset generation model to perform supervisor information generation operation to obtain a plurality of supervisor information; and The multiple supervisor information are sent out in sequence to urge the user to study.

2. The method according to claim 1, wherein: The learning status includes the user's own learning status, the user's friend's learning status and / or the user's class learning status; the supervisor tag includes the user's own supervisor tag, the user's friend's supervisor tag and / or the user's class supervisor tag; the supervisor information includes the supervisor's location and supervisor's content; the supervisor's location includes desktop components and / or desktop icons, and the supervisor's content includes text and / or pictures.

3. The method according to claim 1 or 2, wherein: The multiple supervisor information is sent out in sequence, including: Determining the inspector weight of each inspector information, and sorting the plurality of inspector information according to the inspector weight to obtain an inspector information sequence; Matching the inspector information sequence with the preset inspector plan to obtain an inspector information distribution list; and According to the inspector information distribution list, the multiple inspector information are issued in sequence.

4. The method according to claim 3, wherein: The inspector weights for determining each inspector information include: Obtaining historical click data of the user on historical supervisory information; Inputting the historical click data and the second prompt word into a preset determination model to perform an inspector preference determination operation to obtain the user's inspector preference, wherein the inspector preference includes an inspector position preference and an inspector content preference; and The plurality of inspector information, inspector preferences and the third prompt word are input into the preset determination model to perform an inspector weight determination operation to obtain the inspector weight of each inspector information.

5. The method according to claim 3, wherein: The preset supervisor plan includes multiple supervisor time periods, multiple supervisor weights and the corresponding relationships between them; The inspector information sequence is matched with the preset inspector plan to obtain the inspector information distribution list including: Matching the inspector information sequence with a preset inspector plan according to the inspector weight to determine the inspector time of each inspector information in the inspector information sequence; The plurality of inspector information are sorted according to the inspector time to obtain an inspector information distribution list.

6. A method for urging learning applied to a client, comprising: Receiving the supervision information issued by the method according to any one of claims 1 to 5; The supervisor information is displayed to urge the user to study.

7. The method according to claim 6, wherein: The supervisory information includes supervisory position and supervisory content; The displaying of the supervisor information to urge the user to learn includes: Parsing the inspector information to obtain the current inspector position and current inspector content; as well as The current supervisor content is displayed at the current supervisor position to urge the user to study.

8. The method according to claim 7, wherein: The supervisor position includes a desktop component and / or a desktop icon, the supervisor content includes text and / or a picture, and the current supervisor content displayed at the current supervisor position includes: Get the preset template style of the current supervisor position; Adjusting the text style according to the text style in the preset template style, and / or adjusting the image style according to the image style in the preset template style, so as to obtain text and / or image that conforms to the preset template style; and According to the position layout in the preset template style, text and / or pictures that conform to the preset template style are displayed at the current supervisor position.

9. An electronic device, comprising: processor; And a memory storing program instructions for urging learning applied to a server or a client, wherein when the program instructions are executed by the processor, the electronic device executes the method according to any one of claims 1-5 or 6-8.

10. A computer-readable storage medium storing program instructions for promoting learning applied to a server or a client, wherein when the program instructions are executed by a processor, the method according to any one of claims 1-5 or 6-8 is implemented.

Images