Course recommendation method and device, equipment, medium and program product

Abstract

The invention provides a course recommendation method and device, equipment, a storage medium and a program product, and can be applied to the technical field of big data. The course recommendation method comprises the steps that N target associated objects are determined from M associated objects according to the similarity between historical scores of a course recommendation object and M associated objects associated with the course recommendation object for a plurality of course evaluation indexes, M is larger than N, and M and N are both positive integers; determining at least one target course evaluation index of which the historical scores of the N target associated objects are lower than a preset threshold value from the plurality of course evaluation indexes; determining a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index; and based on the candidate course subset, determining a target course, so that the target course is recommended to the course recommendation object.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of big data, in particular to a course recommendation method and device, equipment, medium and program product. BACKGROUND

[0002] Remote course training is mostly to use an intelligent training system to periodically train and practice seat students. Training courses are targetedly issued to target seats, and the seats can only passively accept and enter the courses, and then one-on-one practice with an intelligent voice robot.

[0003] In the process of implementing the present application concept, the inventors found that at least the following problems exist in the related art: the traditional timing batch course pushing training mode makes it difficult for the unified course content to meet the individual difference needs, the learning resources do not match the actual business ability of the seat students, and the accuracy of course recommendation is not high. SUMMARY

[0004] In view of the above problems, the present application provides a course recommendation method, device, equipment, medium and program product.

[0005] According to a first aspect of the present application, a course recommendation method is provided, comprising: determining N target associated objects from M associated objects according to the similarity between the historical scores of a course recommendation object and M associated objects associated with the course recommendation object for a plurality of course evaluation indexes, wherein M is greater than N and M and N are positive integers; determining at least one target course evaluation index whose historical score of the N target associated objects is lower than a preset threshold from a plurality of course evaluation indexes; determining a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index; determining a target course based on the candidate course subset, so as to recommend the target course to the course recommendation object.

[0006] According to an embodiment of the present application, the course recommendation method further comprises: obtaining a target historical course recommended to the course recommendation object within a predetermined historical period; determining an associated course set having a predetermined association relationship with the target historical course; determining a candidate course subset from the associated course set.

[0007] According to an embodiment of the present application, determining the target course based on the candidate course subset comprises: determining a first score of at least one course in the candidate course subset based on a first model; determining a second score of at least one course in the associated course set based on a second model; determining a target score of at least one course in the candidate course subset and the associated course set based on the first score and the second score; and taking the course whose target score meets a preset score condition as the target course.

[0008] According to an embodiment of the present application, determining the target score of each of the at least one course in the candidate course subset and the associated course set based on the first score and the second score comprises: determining the weight of each of the first model and the second model; and performing weighted summation on the first score and the second score based on the weight of each of the first model and the second model to obtain the target score of each of the at least one course in the candidate course subset and the associated course set.

[0009] According to an embodiment of the present application, the course recommendation method further comprises: adjusting the weight of each of the first model and the second model according to the feedback information of the target course by the course recommendation object.

[0010] According to an embodiment of the present application, determining the candidate course subset from the predetermined course set corresponding to the at least one target course evaluation index comprises: determining a predicted score of the at least one target course evaluation index according to the historical scores of the N target associated objects on the at least one target course evaluation index and the similarity between the historical scores of the N target associated objects and the course recommendation object; and obtaining the candidate course subset by taking the course corresponding to the target course evaluation index whose predicted score meets a preset condition as the candidate course.

[0011] According to an embodiment of the present application, the course recommendation method further comprises: obtaining a historical course set recommended to the M associated objects and the course recommendation object within a predetermined historical period; and determining the association relationship between a plurality of historical courses in the historical course set based on a preset prior probability algorithm, wherein the plurality of historical courses include a target historical course, and the association relationship comprises: the common recommendation frequency between at least two historical courses is higher than a preset frequency threshold.

[0012] A second aspect of the present application provides a course recommendation device, comprising: a first determination module configured to determine N target associated objects from M associated objects according to the similarity between the historical scores of the course recommendation object and the M associated objects on a plurality of course evaluation indexes, wherein M is greater than N and both M and N are positive integers; a second determination module configured to determine at least one target course evaluation index from the plurality of course evaluation indexes, wherein the historical scores of the N target associated objects on the at least one target course evaluation index are lower than a preset threshold; a third determination module configured to determine a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index; and a fourth determination module configured to determine a target course based on the candidate course subset, so as to recommend the target course to the course recommendation object.

[0013] A third aspect of the present application provides an electronic device, comprising: one or more processors; a memory for storing one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement the steps of the above method.

[0014] The fourth aspect of the present application also provides a computer readable storage medium, which stores a computer program or instructions, and the computer program or instructions are executed by a processor to realize the steps of the above method.

[0015] The fifth aspect of the present application also provides a computer program product, which includes a computer program or instructions, and the computer program or instructions are executed by a processor to realize the steps of the above method.

[0016] In the embodiments of the present application, by calculating the similarity of the course recommendation object and the associated object in the course evaluation index historical score, the associated objects with similar business mastery are filtered out, and the possible potential weaknesses of the course recommendation object are predicted according to the current exposed weaknesses of the associated objects, so as to push the courses to the course recommendation object in advance, avoid the actual occurrence of the problem, thereby meeting the difference needs of the students; at the same time, the indicators with scores lower than the preset threshold are filtered out, the indicators that the associated objects have triggered but the recommendation objects may trigger are located, and the corresponding courses are recommended. This way can accurately locate the weak links, improve the accuracy of course recommendation and training efficiency, avoid the risk of indicator triggering, and also reduce the time of students to filter courses and learn unnecessary content. BRIEF DESCRIPTION OF DRAWINGS

[0017] The above and other objects, features and advantages of the present application will become more apparent from the following description of the embodiments of the present application, taken in conjunction with the accompanying drawings, in which:

[0018] Figure 1 An application scenario diagram of a course recommendation method, device, equipment, medium and program product according to an embodiment of the present application is schematically shown;

[0019] Figure 2 A flowchart of a course recommendation method according to an embodiment of the present application is schematically shown;

[0020] Figure 3 A method flowchart for determining a target course according to an embodiment of the present application is schematically shown;

[0021] Figure 4 A method flowchart for determining a target score according to an embodiment of the present application is schematically shown;

[0022] Figure 5 A structural block diagram of a course recommendation device according to an embodiment of the present application is schematically shown; and

[0023] Figure 6 A block diagram of an electronic device suitable for implementing a course recommendation method according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0024] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It should be understood, however, that the description is merely exemplary of the present application, and is not intended to limit the scope of the present application. In the following detailed description of the embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the present application can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring aspects of the present application.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the term "comprising" or "comprises" or "including" or "includes" or "containing" or "contains" or "has" or "having" or the like is used to indicate the presence of stated features, steps, operations, and / or components but does not preclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art unless otherwise defined herein. It should be noted that the terms used herein are defined as having meanings that are consistent with the context of the specification in which the terms are used and should not be explained in an idealized or overly formal manner.

[0027] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally construed that the expression means to include at least one of the items, unless otherwise defined herein (for example, "a system having at least one of A, B, and C" should include a system having A alone, a system having B alone, a system having C alone, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.).

[0028] It should be noted that the course recommendation method and device of the present application can be used in the field of financial technology and the field of big data technology, and can also be used in any field other than the field of financial technology, and the application field of the course recommendation method and device of the present application is not limited.

[0029] In the technical solutions of the present application, the user information (including but not limited to user personal information, user image information, user equipment information such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0030] In the scenario of making automated decisions by using personal information, the method, device and system provided by the embodiments of the present application all provide corresponding operation entrances for users to select to agree or reject the automated decision result; if the user selects to reject, the expert decision process is entered. The expression "automated decision" herein refers to the activity of automatically analyzing, evaluating the behavior habits, interests and hobbies or economic, health, credit status of a person by a computer program, and making decisions. The expression "expert decision" herein refers to the activity of making decisions by personnel who are engaged in a certain field of work, have special experience, knowledge and skills, and reach a certain professional level.

[0031] The seat trainee refers to a trainee who, in a training scene, uses an intelligent training system to accept relevant business training with a specific seat as a learning position. Such trainees often aim to master specific business operations, service processes and the like so as to be able to perform corresponding post work later, such as telephone customer service seat trainees who will learn how to answer customer inquiry calls, handle customer problems and the like through seat equipment during training. The intelligent training system uses technologies such as speech recognition, speech synthesis and natural language processing to combine part of the man-machine interaction capabilities in "seeing, hearing, thinking, speaking and doing" for use, to provide immersive one-on-one intelligent practice services for trainees, to train seat trainees to accurately understand customer needs, clearly answer questions in telephone / online services, and to improve the business capabilities and service levels of seat personnel, so as to better meet customer needs and ensure efficient operation of business.

[0032] Since the businesses of different industries may be frequently updated (such as adding online products, adjusting operation processes and the like) according to policies and market demands, training seat trainees can help seats to timely master the latest business points and ensure service compliance. For example, in the field of financial business, telephone customer service seat trainees need to master the rules, processes and policies of various products of banks (such as credit cards, loans, financial products and the like), such as loan approval conditions, risk level division of financial products and the like. Familiar with the system operation of financial institutions (such as customer information query, business handling process, work order processing and the like). For another example, in the e-commerce business scene, telephone customer service seat trainees need to master order cancellation / modification rules, after-sales maintenance processes, violation behavior processing, and quickly query customer order status, logistics information and handle high-frequency problems through "quick reply templates" and the like.

[0033] It can be seen that the seat personnel need to have strong knowledge reserve, learning ability, business proficiency, etc. Due to the different proficiency of each student in the business, the traditional "fixed batch pushing course" training mode has problems, for example, the unified course content is difficult to match the individual needs, leading to the mismatch of learning resources and actual short board; the standardized pushing rhythm cannot adapt to the learning progress of the employees, some employees may have fear of difficulty due to the content being too difficult, while those with a solid foundation face the inefficient dilemma of "repeated learning". Ultimately, it results in low recommendation accuracy and learning conversion rate, and it is difficult to achieve the expected ability improvement goal. If all courses are uniformly pushed to all seat students, each seat student also needs to spend a lot of time selecting the required courses from the massive courses, and the learning efficiency is low.

[0034] Therefore, an embodiment of the present application provides a course recommendation method, comprising: determining N target associated objects from M associated objects according to the similarity between the historical scores of each of the course recommendation object and the M associated objects associated with the course recommendation object on a plurality of course evaluation indexes, wherein M is greater than N and M and N are positive integers; determining at least one target course evaluation index whose historical score of the N target associated objects is lower than a preset threshold from the plurality of course evaluation indexes; determining a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index; and determining a target course based on the candidate course subset, so as to recommend the target course to the course recommendation object.

[0035] Figure 1 An application scenario diagram of the course recommendation method according to an embodiment of the present application is schematically shown.

[0036] As shown in Figure 1 , the application scenario 100 according to the embodiment can include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is used as a medium to provide a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0037] The user can use the first terminal device 101, the second terminal device 102, the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as an example).

[0038] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0039] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0040] It should be noted that the course recommendation method provided in this application embodiment can generally be executed by server 105. Correspondingly, the course recommendation device provided in this application embodiment can generally be located in server 105. The course recommendation method provided in this application embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the course recommendation device provided in this application embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0041] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0042] The following will be based on Figure 1 The described scene, through Figures 2-4 The course recommendation method according to the embodiments of this application will be described in detail.

[0043] Figure 2 A flowchart illustrating a course recommendation method according to an embodiment of this application is shown.

[0044] like Figure 2 As shown, the course recommendation method in this embodiment includes operations S210 to S240.

[0045] Before operation S210, the course recommendation object needs to be determined, wherein the course recommendation object can be a new employee who needs to participate in training or an old employee who needs to be trained for a new business, etc. Secondly, the associated object associated with the course recommendation object needs to be determined, wherein the association with the course recommendation object can include the following cases. For example, the course recommendation object and the associated object are both new employees, and both need to be trained for general business; for example, the course recommendation object and the associated object need to handle the same type of new business, and the employee training needs to be strengthened for the new business. It can also be any scenario and situation that needs to be trained, which is not listed here.

[0046] In the embodiment of the present application, after determining the course recommendation object and the M associated objects related to the course recommendation object, the first historical score of the course recommendation object for a plurality of historical course evaluation indicators is obtained; the second historical score of the M associated objects for a plurality of course evaluation indicators is obtained; and the similarity of the course recommendation object and the M associated objects is calculated respectively according to the first historical score and the second historical score.

[0047] In the embodiment of the present application, the historical course evaluation indicator is a course evaluation indicator that the course recommendation object and the M associated objects have triggered at a historical time. In addition to the historical course evaluation indicator, there is also a target course evaluation indicator that the course recommendation object and / or the M associated objects have not triggered. The historical course evaluation indicator and the target course evaluation indicator constitute the total course evaluation indicator. The course evaluation indicator is a preset indicator triggered in the process of the agent trainee communicating with the customer or the training model, and includes a plurality of service taboos.

[0048] For example, the first course evaluation indicator is service taboo language, and the service personnel cannot use impolite, inappropriate, and possibly offensive language to the customer or the training model during communication. For example, the language includes words such as accusation, ridicule, impatience, and insulting words. The second course evaluation indicator is sensitive words, which are words that are not suitable for use, may cause risks or adverse effects in a specific business scenario and context. The third course evaluation indicator is colloquial expression, which is a language expression that is too casual, informal, and non-standard, and lacks professionalism. For example, the language includes frequently using dialect words, catchphrases, and incomplete expressions. Other course evaluation indicators can also include: not using standard opening and closing words, providing incorrect information, not responding to the customer in a timely manner, not processing the business according to the process, not effectively helping the customer solve the problem, etc., which are not listed here.

[0049] In the embodiments of the present application, the first historical score is a score calculated according to preset rules and deduction conditions after the course recommendation object triggers the corresponding course evaluation indicators in the process of dialogue with the customer or the training model; similarly, the second historical score is a score calculated according to preset rules and deduction conditions after the associated object triggers the corresponding course evaluation indicators in the process of dialogue with the customer or the training model. For example, trainee 1 violates the service taboo index in the dialogue process and is deducted 10 points, and the historical score of trainee 1 is 90 points in the case where other indicators are not deducted.

[0050] In operation S210, N target associated objects are determined from the M associated objects according to the similarity between the historical scores of the course recommendation object and each of the M associated objects associated with the course recommendation object for the plurality of course evaluation indicators, wherein M is greater than N and both M and N are positive integers.

[0051] In the embodiments of the present application, the similarity between the course recommendation object and each associated object is calculated according to the first historical score and the second historical score; and the target associated object with high similarity to the course recommendation object is determined according to the similarity threshold or the number of similarities.

[0052] It should be noted that the similarity between the course recommendation object and each associated object is calculated according to the first historical score and the second historical score, so the similarity between the course recommendation object and each associated object actually reflects the similarity between the degree of master of the business of the trainee trainees. For example, trainee A and trainee B have high similarity, indicating that the two trainees have similar degree of master of the business, or have similar business processing ability.

[0053] In operation S220, at least one target course evaluation indicator whose historical score of the N target associated objects is lower than a preset threshold is determined from the plurality of course evaluation indicators.

[0054] Table 1 exemplarily shows a plurality of course evaluation indicators and the deduction conditions of each target associated object on each course evaluation indicator.

[0055] Table 1

[0056]

[0057] In the embodiment of the present application, taking the score of each target associated object under each course evaluation index as an example, as shown in Table 1, the score of target associated object A under index 1 is 90 points, the score under index 2 is 80 points, and the score under index 3 is 95 points. Further, the preset threshold can be pre-set according to experience, for example, 80 points. Thus, at least one target course evaluation index of the historical scores of the N target associated objects from the plurality of course evaluation indexes is determined to be lower than the preset threshold, that is, the course evaluation index of the target associated object with a deduction of 20 points or more is screened out, which is used as the target course evaluation index. In other words, target associated object A has more deductions in sensitive words, indicating that the learning and mastering degree of sensitive words is not enough, and the learning of this aspect needs to be strengthened.

[0058] It should be noted that the plurality of course evaluation indexes refers to the course evaluation indexes that have been triggered by the target associated object but have not been triggered by the course recommendation object. Thus, in the case that the learning degree of the target associated object and the course recommendation object is similar, the course evaluation index that has been triggered by the target associated object, although not triggered by the course recommendation object, may be that the course recommendation object has not encountered the corresponding business, etc., and the course corresponding to the course evaluation index that the course recommendation object is likely to trigger is recommended to the course recommendation object before the course recommendation object triggers the course evaluation index, so as to make the course recommendation object learn in advance and avoid triggering the same course evaluation index.

[0059] In operation S230, a candidate course subset is determined from the predetermined course set corresponding to the at least one target course evaluation index.

[0060] In the embodiment of the present application, each course evaluation index has a corresponding course in the predetermined course set. For example, if the course evaluation index is “sensitive words”, there is a course in the predetermined course set that specifically explains the definition, scope, use scenario and avoidance method of sensitive words; if the course evaluation index is “service taboo”, there is a course in the predetermined course set that covers the types, hazards and correct service language specifications of service taboo; if the course evaluation index is “oral expression correction”, the corresponding course includes teaching content such as analysis of disadvantages of oral expression, standard language expression training and formal business language examples.

[0061] In the above case that it is determined that target associated object A has more deductions in sensitive words, a candidate course subset composed of a plurality or a plurality of series of courses related to the content of course evaluation index 2 (sensitive words) needs to be found from the predetermined course set.

[0062] In operation S240, based on the candidate course subset, a target course is determined, so as to recommend the target course to the course recommendation object.

[0063] In the embodiments of the present application, since the candidate course subset corresponds to the target course index content, in one case, all courses in the candidate course subset are directly determined as target courses and recommended to the course recommendation object. In another case, the courses in the candidate course subset that the course recommendation object has already learned are deleted, and the courses in the candidate course subset that the course recommendation object has not learned are recommended to him as target courses.

[0064] In the embodiments of the present application, by calculating the similarity of the course recommendation object and the associated object in the course evaluation index historical score, the associated objects with similar business mastery are screened out, the possible potential weaknesses of the course recommendation object are predicted according to the short board exposed by the associated object, so as to push the courses to the course recommendation object in advance, avoid the actual occurrence of the problem, thereby meeting the difference needs of the students; at the same time, the indicators with scores lower than the preset threshold are screened out, the indicators that the associated object has triggered but the recommendation object may trigger are located and the corresponding courses are recommended. This way can accurately locate the weak link, improve the accuracy of course recommendation and training efficiency, avoid the risk of index triggering, and also reduce the time of students to screen courses and learn unnecessary content.

[0065] Figure 3 A method flowchart for determining a target course according to an embodiment of the present application is schematically shown.

[0066] As shown in Figure 3 The method for determining a target course based on a candidate course subset in this embodiment includes operation S310~operation S320.

[0067] In operation S310, a predicted score of at least one target course evaluation index is determined according to the historical scores of N target associated objects for the at least one target course evaluation index, and the similarity between the historical scores of the N target associated objects and the course recommendation object.

[0068] In operation S320, the course corresponding to the target course evaluation index whose predicted score meets the preset condition is taken as a candidate course, and a candidate course subset is obtained.

[0069] In the embodiments of the present application, when the score of the target associated object in each target course evaluation index is calculated, one implementation is to directly take the historical score of the target associated object as the predicted score of the course recommendation object. This is because the two have high similarity, meaning that the knowledge mastery or business ability is similar. If both students are first exposed to a certain type of business, the problems encountered by the target associated object may also be encountered by the recommended object, but the relevant indicators have not been triggered. Therefore, the more points the target associated object loses on the indicators, the higher the tendency of the recommended object to recommend the course. The pre-set condition is used to filter the candidate courses because there are many course evaluation indicators. If all the courses corresponding to the indicators that do not meet the conditions are recommended, it will result in too many courses. Therefore, the pre-set condition can limit the courses corresponding to the indicators with serious deductions to be recommended, and the courses corresponding to the indicators with less serious deductions are not recommended.

[0070] In the embodiments of the present application, when the score of the target associated object in each target course evaluation index is calculated, another implementation is to calculate the predicted score of the course recommendation object in the target course evaluation index according to the product of the historical score of the target associated object in the target course evaluation index and the similarity between the historical score of the target associated object and the course recommendation object. As shown in Table 1, the score of the target associated object C in indicator 1 is 90 points, the score in indicator 2 is 100 points, and the score in indicator 3 is 82 points. The similarity between the course recommendation object A and the target associated object C is 0.9. Then the corresponding predicted score of the course recommendation object A in indicator 1 is 91 points, the corresponding predicted score in indicator 2 is 90 points, and the corresponding predicted score in indicator 3 is 73.8 points. If the pre-set condition is set to be that the predicted score needs to reach 90 points, the courses corresponding to the indicators with scores below 90 points are recommended to the course recommendation object.

[0071] In the embodiments of the present application, by analyzing the historical scores of similar associated objects and the similarity with the recommended object, the learning weaknesses of the students can be located in advance based on group experience, and preventive learning intervention can be performed on the courses with poor predicted performance, effectively helping the students to avoid learning risks, making the recommended results more suitable for the actual learning ability, significantly improving the accuracy and business adaptability of course recommendation, and reducing the cost of enterprise training and business trial and error. On the other hand, by setting the pre-set condition to filter the courses, not all courses are recommended to the course recommendation object, which reduces the time for course selection of the course recommendation object, narrows the course query range, and is beneficial to improve the learning efficiency.

[0072] In the embodiments of the present application, in addition to operation S210 to operation S240, the course recommendation method further comprises: obtaining a target historical course recommended to the course recommendation object within a predetermined historical period; determining an associated course set having a predetermined association relationship with the target historical course; and determining a candidate course subset from the associated course set.

[0073] In the embodiments of the present application, the predetermined historical period can be any time in the past, such as one day, one week, one month, etc. After obtaining the target historical course that has been recommended to the course recommendation object, the courses associated with the target historical course that has been recommended are determined from the predetermined course set and recommended to the course recommendation object. Among them, the associated courses can be the same field, the same theme, the same series or complementary content as the target historical course. For example, according to the difficulty gradient, a complete system from beginner to master is formed, which is suitable for systematic learning scenarios.

[0074] In the embodiments of the present application, by analyzing the historical recommended courses that the student has received, the courses associated with the historical recommended courses are screened, so that the recommended results are more suitable for the course content that the student has learned, thereby recommending the courses of the same series or training content to the student in a targeted manner, so as to avoid the student from blindly selecting from the full course library, and to improve the learning efficiency and training efficiency of the student, and to avoid the time wasted in screening courses from a large number of course contents.

[0075] In the embodiments of the present application, the method for determining the associated course set having a predetermined association relationship with the target historical course includes: obtaining a historical course set recommended to M associated objects and the course recommendation object within a predetermined historical period; determining the association relationship between a plurality of historical courses in the historical course set based on a preset prior probability algorithm, the plurality of historical courses including the target historical course, and the association relationship including: a common recommendation frequency between at least two historical courses being higher than a preset frequency threshold.

[0076] In the embodiments of the present application, the preset prior probability algorithm includes the following steps.

[0077] (1) Obtain the historical course training records of the seat student, and form a training transaction set.

[0078] (2) Set a minimum threshold of support, and determine the frequent course item set from the training transaction set. Set X-item set is used, and after X rounds of iteration calculation, the maximum frequent X-item set is converged. Then, the confidence is set in combination with experience, and the TOP-K associated rules with the highest frequency are determined, which are the association relationships between courses and courses.

[0079] Wherein, the X-item set is a combination of X courses (e.g., a 2-item set is a combination of 2 courses, and a 3-item set is a combination of 3 courses). The number of X can be directly set, i.e., the number of associated courses is set in advance. If X is set to 5, it means that 5 courses are associated, which can be courses in the same series. If the student has already learned 2 courses of the 5 courses, the remaining 3 courses can be recommended to the student to complete the learning of the series of courses. Wherein, the TOP-K associated rules with the highest frequency are determined according to the confidence. For example, the confidence of the course C→A is only 50%, which means that the people who learn course C do not necessarily learn course A, and the recommendation priority is low. However, the confidence of the course A→C is only 85%, which means that the people who learn course A will probably learn course A, and the recommendation priority is high.

[0080] (3) According to the list of courses not yet learned, a list of courses to be learned by the seat student is formed. The frequent X-item set is used to recommend a plurality of courses having an associated relationship to the course recommendation object according to the predetermined number, thereby avoiding recommending low-association courses.

[0081] Figure 4 A method flowchart for determining a target score according to an embodiment of the present application is schematically shown.

[0082] As shown in Figure 4 The method for determining the target score of at least one course in the candidate course subset and the associated course set according to the first score and the second score in the embodiment includes operations S410-S440.

[0083] In operation S410, the first score of at least one course in the candidate course subset is determined based on the first model.

[0084] In the embodiment of the present application, the candidate course subset is determined according to the similarity of the historical scores between the course recommendation object and the associated object. Courses with historical scores lower than a preset threshold value can be recommended to the course recommendation object to learn in advance to avoid triggering the same course evaluation index. Through the first model, the score of the course of this type is evaluated to evaluate the effect of the course recommendation object learning the course of this type.

[0085] In operation S420, the second score of at least one course in the associated course set is determined based on the second model.

[0086] In the embodiments of the present application, the associated course set is the course recommended for the course recommendation object according to the association relationship between the courses the course recommendation object has learned and the courses the course recommendation object has not learned, so as to filter out the possible relevant business courses from the massive courses to be learned, so as to narrow the course filtering range and save the course filtering time. The second model is used to score the courses of this type, so as to evaluate the effect of the course recommendation object learning the courses of this type.

[0087] In operation S430, based on the first score and the second score, a target score of each course in at least one of the candidate course subset and the associated course set is determined.

[0088] In the embodiments of the present application, the output results of the first model (candidate course subset score based on historical score similarity) and the second model (associated course set score based on course association relationship) are integrated to form a final target score, which provides a unified standard for course recommendation. Specifically, it includes step 10 and step 20.

[0089] Step 10: Determine the weight of each of the first model and the second model.

[0090] In the embodiments of the present application, in one case, if the business values "historical score similarity" more, the weight of the first model can be set higher.

[0091] For example, in the case that the students are in the early stage of learning, the course evaluation index is clear, and the course type is basic general, the historical score similarity can better reflect the weaknesses of the students, and if it is necessary to make up for the specific deficiencies of a certain or certain type of students, the weight of the first model can be adjusted higher. For example, the new seat students generally have more deductions in oralization, so the historical weaknesses of the new seat students are found out, and the students who have not or therefore have fewer deductions learn or consolidate the "Professional Terminology Standard" course corresponding to the content.

[0092] In another case, if "course association" is more critical to the prediction of learning effect, the weight of the second model can be set higher.

[0093] For example, in the case that the students have rich learning history, the course association relationship can excavate potential needs. For example, the seat student is an old student and has completed the basic course, and the high-level course can be recommended for him. Or, the courses are cross-domain related courses. For example, the student has completed all courses related to the loan business, but there are still repayment and other branch businesses in the loan business. If the customer does not repay in time, the account may be controlled, so the seat student may also receive the problem of account control raised by the user. It can be seen that the loan business itself seems to be independent of the account control business, but there is an internal connection. The student also needs to learn the content related to account control according to the recommendation.

[0094] Step 20: based on the respective weights of the first model and the second model, the first score and the second score are weighted and summed to obtain a target score of at least one course in the candidate course subset and the associated course set respectively. That is, the target score = the first score x the first model weight + the second score x the second model weight. In this way, the dual information of "historical score similarity" (the first model) and "course association" (the second model) is utilized simultaneously, avoiding the limitation of a single dimension. By adjusting the weights, different business scenarios can be flexibly adapted.

[0095] In operation S440, the course whose target score meets the preset score condition is taken as the target course.

[0096] In the embodiments of the present application, the respective weights of the first model and the second model are adjusted according to the feedback information of the course recommendation object on the target course.

[0097] In the embodiments of the present application, the two model weights are continuously optimized in a cross-validation manner to obtain a final series of course recommendation models. The feedback information of the course recommendation object on the target course can be the score of the course recommendation object on the corresponding target course evaluation index after completing the learning of the target course. It can also be the service quality of the evaluation agent, such as the decrease of customer complaint rate; it can also be the business conversion rate, such as the increase of the success rate of financial product recommendation, and it can also be the effectiveness of the "high net worth customer marketing" course recommended for the agent trainee. The accuracy of the series of course models is evaluated by comparing the learning courses of the agent trainee in the test set with the learning courses of the agent trainee in the last month. In the embodiments of the present application, the target courses obtained by the above method are formed into a list and visually displayed on the terminal device of the agent trainee, so that the agent trainee can timely obtain course resources when learning and receiving training. The target course list can be periodically summarized and sent to the intelligent training system of the agent trainee, and the trainee can obtain the course resources by clicking the corresponding part. For example, the terminal displays the "Guess You Want to Learn" area, and the agent trainee can timely see the updated course list during the use of the intelligent training system. In this way, the differentiated training demands of the agent trainee are met.

[0098] Based on the above course recommendation method, the present application also provides a course recommendation device. The following will be described in detail Figure 5 The device.

[0099] Figure 5 The structure block diagram of the course recommendation device according to the embodiments of the present application is schematically shown.

[0100] As Figure 5 shown, the course recommendation device 500 of the embodiments includes a first determination module 510, a second determination module 520, a third determination module 530, and a fourth determination module 540.

[0101] The first determining module 510 is configured to determine N target associated objects from M associated objects according to similarities between historical scores of the course recommendation object and each of the M associated objects on a plurality of course evaluation indexes, where M is greater than N and both M and N are positive integers. In an embodiment, the first determining module 510 can be configured to perform the operation S210 described above, and details are not repeated here.

[0102] The second determining module 520 is configured to determine at least one target course evaluation index whose historical score of the N target associated objects is lower than a preset threshold from the plurality of course evaluation indexes. In an embodiment, the second determining module 520 can be configured to perform the operation S220 described above, and details are not repeated here.

[0103] The third determining module 530 is configured to determine a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index. In an embodiment, the third determining module 530 can be configured to perform the operation S230 described above, and details are not repeated here.

[0104] The fourth determining module 540 is configured to determine a target course based on the candidate course subset, so as to recommend the target course to the course recommendation object. In an embodiment, the fourth determining module 540 can be configured to perform the operation S240 described above, and details are not repeated here.

[0105] In the embodiments of the present application, by calculating the similarity of the course recommendation object and the associated object in the historical score of the course evaluation index, the associated objects with similar business mastery are screened out, the possible potential weaknesses of the course recommendation object are predicted according to the current exposed weaknesses of the associated objects, the courses are pushed to the course recommendation object in advance, the problem is avoided from actually occurring, thereby meeting the difference needs of the students; meanwhile, the indexes with scores lower than the preset threshold are screened out, the indexes that have been triggered by the associated objects but may be triggered by the recommendation object are located and the corresponding courses are recommended. This way can accurately locate the weak links, improve the course recommendation accuracy and training efficiency, avoid the index triggering risk, and also reduce the time of the students to screen courses and learn unnecessary content.

[0106] According to the embodiments of the present application, the course recommendation device further comprises a first obtaining module, a fifth determining module and a sixth determining module.

[0107] The first obtaining module is configured to obtain a target historical course recommended to the course recommendation object in a predetermined historical period; the fifth determining module is configured to determine an associated course set having a predetermined association relationship with the target historical course; and the sixth determining module is configured to determine a candidate course subset from the associated course set.

[0108] According to an embodiment of the present application, the fourth determining module 540 comprises a first determining sub-module, a second determining sub-module, a third determining sub-module and a first obtaining sub-module.

[0109] The first determining sub-module is configured to determine a first score of each of the at least one course in the candidate course subset based on the first model; the second determining sub-module is configured to determine a second score of each of the at least one course in the associated course set based on the second model; the third determining sub-module is configured to determine a target score of each of the at least one course in the candidate course subset and the associated course set based on the first score and the second score; and the first obtaining sub-module is configured to take the course whose target score satisfies a preset score condition as the target course.

[0110] According to an embodiment of the present application, the third determining sub-module comprises a determining unit and a weighted sum unit.

[0111] The determining unit is configured to determine a weight of each of the first model and the second model; and the weighted sum unit is configured to perform weighted sum on the first score and the second score based on the weight of each of the first model and the second model to obtain the target score of each of the at least one course in the candidate course subset and the associated course set.

[0112] According to an embodiment of the present application, the course recommendation apparatus further comprises an adjusting module.

[0113] The adjusting module is configured to adjust the weight of each of the first model and the second model according to the feedback information of the target course by the course recommendation object.

[0114] According to an embodiment of the present application, the third determining module 530 comprises a fourth determining sub-module and a second obtaining sub-module.

[0115] The fourth determining sub-module is configured to determine a predicted score of the at least one target course evaluation index according to the historical score of each of the N target associated objects on the at least one target course evaluation index and the similarity between the historical score of the N target associated objects and the course recommendation object; and the second obtaining sub-module is configured to take the course corresponding to the target course evaluation index whose predicted score satisfies a preset condition as the candidate course to obtain the candidate course subset.

[0116] According to an embodiment of the present application, the course recommendation apparatus further comprises a second obtaining module and a seventh determining module.

[0117] The second obtaining module is configured to obtain a historical course set recommended to the M associated objects and the course recommendation object within a predetermined historical period; and the seventh determining module is configured to determine an association relationship between a plurality of historical courses in the historical course set based on a preset prior probability algorithm, the plurality of historical courses comprising a target historical course, and the association relationship comprising that a common recommendation frequency between at least two historical courses is higher than a preset frequency threshold.

[0118] According to an embodiment of the present application, any of the first determining module 510, the second determining module 520, the third determining module 530 and the fourth determining module 540 can be combined in one module, or any of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. According to an embodiment of the present application, at least one of the first determining module 510, the second determining module 520, the third determining module 530 and the fourth determining module 540 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware that can be integrated or packaged with a circuit, or implemented in any one of software, hardware and firmware or in a proper combination of any of them. Alternatively, at least one of the first determining module 510, the second determining module 520, the third determining module 530 and the fourth determining module 540 can be at least partially implemented as a computer program module that can perform corresponding functions when it is run.

[0119] Figure 6 A block diagram of an electronic device suitable for implementing the course recommendation method according to an embodiment of the present application is schematically shown.

[0120] As shown in Figure 6 The electronic device 600 according to an embodiment of the present application includes a processor 601 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 602 or loaded from a storage portion 608 into a random access memory (RAM) 603. The processor 601 can include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset, and / or a special-purpose microprocessor (such as an application specific integrated circuit (ASIC)), and the like. The processor 601 can also include an on-board memory for cache use. The processor 601 can include a single processing unit or multiple processing units for performing different actions of the method processes according to embodiments of the present application.

[0121] In the RAM 603, various programs and data required for the operation of the electronic device 600 are stored. The processor 601, the ROM 602, and the RAM 603 are connected to each other via the bus 604. The processor 601 performs various operations of the method flow according to the embodiments of the present application by executing the programs in the ROM 602 and / or the RAM 603. It should be noted that the programs can also be stored in one or more memories other than the ROM 602 and the RAM 603. The processor 601 can also perform various operations of the method flow according to the embodiments of the present application by executing the programs stored in the one or more memories.

[0122] According to the embodiments of the present application, the electronic device 600 can further include an input / output (I / O) interface 605, which is also connected to the bus 604. The electronic device 600 can further include one or more of the following components connected to the input / output (I / O) interface 605: an input part 606 including a keyboard, a mouse, and the like; an output part 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker, and the like; a storage part 608 including a hard disk, and the like; and a communication part 609 including a network interface card such as a LAN card, a modem, and the like. The communication part 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the input / output (I / O) interface 605 as necessary. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 610 as necessary, so that a computer program read therefrom is installed in the storage part 608 as necessary.

[0123] The present application also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, when the one or more programs are executed, the method according to the embodiments of the present application is implemented.

[0124] According to an embodiment of the present application, the computer readable storage medium can be a non-transitory computer readable storage medium, for example, can include but not limited to: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this application, a computer readable storage medium can be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, the computer readable storage medium can include the ROM 602 and / or the RAM 603 described above and / or one or more memory other than the ROM 602 and the RAM 603.

[0125] Embodiments of the present application also include a computer program product, which includes a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the course recommendation method provided by the embodiments of the present application.

[0126] The above functions defined in the system / device / apparatus of the embodiments of the present application are performed when the computer program is executed by the processor 601. According to an embodiment of the present application, the system, device, module, unit, etc. described above can be implemented by computer program modules.

[0127] In one embodiment, the computer program can rely on tangible storage media such as optical storage media, magnetic storage media, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of signals on a network medium, and be downloaded and installed through the communication part 609, and / or be installed from the detachable medium 611. The program codes contained in the computer program can be transmitted by any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

[0128] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or be installed from the detachable medium 611. When the computer program is executed by the processor 601, the above functions defined in the system of the embodiments of the present application are performed. According to an embodiment of the present application, the system, device, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0129] According to embodiments of the present application, program code for implementing the computer programs provided by embodiments of the present application can be written in any combination of one or more programming languages, and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. Programming languages include, but are not limited to, Java, C++, python, "C", or the like. Program code can execute entirely on a user's computing device, partly on the user's device, as a stand-alone software package, partly on a remote computing device, or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider.

[0130] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0131] Those skilled in the art will appreciate that features recited in the various embodiments of the present application can be combined and / or integrated in various combinations, even if such combinations have not been explicitly recited in the present application. In particular, the features recited in the various embodiments of the present application can be combined and / or integrated in various combinations, without departing from the spirit and teachings of the present application. All such combinations are within the scope of the present application.

Claims

1. A course recommendation method characterized by, The method comprises: determining N target associated objects from M associated objects associated with the course recommendation object according to the similarity between the historical scores of the course recommendation object and each of the M associated objects on a plurality of course evaluation indexes, wherein M is greater than N and both M and N are positive integers; determining at least one target course evaluation index whose historical score of the N target associated objects is lower than a preset threshold from the plurality of course evaluation indexes; determining a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index; determining a target course based on the candidate course subset, so as to recommend the target course to the course recommendation object.

2. The method of claim 1, wherein, The method further comprises: obtaining a target historical course recommended to the course recommendation object within a predetermined historical period; determining an associated course set having a predetermined association relationship with the target historical course; determining the candidate course subset from the associated course set.

3. The method of claim 2, wherein, The determination of the target course based on the candidate course subset comprises: determining a first score of at least one course in the candidate course subset based on a first model; determining a second score of at least one course in the associated course set based on a second model; determining a target score of at least one course in the candidate course subset and the associated course set based on the first score and the second score; determining a course whose target score meets a preset score condition as the target course.

4. The method of claim 3, wherein, The determination of the target score of at least one course in the candidate course subset and the associated course set based on the first score and the second score comprises: determining a weight of each of the first model and the second model; performing weighted summation on the first score and the second score based on the weight of each of the first model and the second model to obtain the target score of at least one course in the candidate course subset and the associated course set.

5. The method of claim 3, wherein, The method further comprises: adjusting the weight of each of the first model and the second model according to feedback information of the course recommendation object on the target course.

6. The method of claim 1, wherein, The determination of the candidate course subset from the predetermined course set corresponding to the at least one target course evaluation index comprises: determining a predicted score of the at least one target course evaluation index according to the historical score of each of the N target associated objects on the at least one target course evaluation index and the similarity between the historical scores of the N target associated objects and the course recommendation object; determining a course corresponding to a target course evaluation index whose predicted score meets a preset condition as a candidate course to obtain the candidate course subset.

7. The method of claim 2, wherein, The method further comprises: obtaining a historical course set recommended to the M associated objects and the course recommendation object within the predetermined historical period; determining an association relationship between a plurality of historical courses in the historical course set based on a preset prior probability algorithm, wherein the plurality of historical courses include the target historical course, and the association relationship includes that the common recommendation frequency between at least two historical courses is higher than a preset frequency threshold.

8. A course recommendation apparatus characterized by comprising: The device comprises: The first determining module is configured to determine N target associated objects from the M associated objects according to similarities between historical scores of a plurality of course evaluation indexes of a course recommendation object and the M associated objects associated with the course recommendation object, where M is greater than N and M and N are positive integers; The second determining module is configured to determine at least one target course evaluation index whose historical score of the N target associated objects is lower than a preset threshold from the plurality of course evaluation indexes; The third determining module is configured to determine a candidate course subset from a predetermined course set corresponding to the at least one target course evaluation index; The fourth determining module is configured to determine a target course based on the candidate course subset, so as to recommend the target course to the course recommendation object. 9.An electronic device comprising: one or more processors; memory for storing one or more computer programs, characterized in that the one or more processors execute the one or more computer programs to implement the steps of the method according to any one of claims 1-7.

10. A computer readable storage medium having stored thereon a computer program or instructions, characterized in that, The computer program or instruction is executed by the processor to implement the steps of the method according to any one of claims 1-7.

Images