Knowledge recommendation method and device, electronic equipment and storage medium
By acquiring a set of candidate knowledge points and using a multi-factor decision model to calculate the recommendation index, the problem of poor knowledge recommendation performance in existing technologies is solved, and more accurate knowledge recommendation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING YUANLI WEILAI SCI & TECH CO LTD
- Filing Date
- 2021-08-17
- Publication Date
- 2026-07-03
AI Technical Summary
Existing knowledge recommendation methods simply filter knowledge from a large amount of review data and recommend it to users, which is ineffective and fails to effectively consider multiple evaluation factors of knowledge points.
By acquiring a set of candidate knowledge points, the evaluation information of each knowledge point on multiple evaluation factors is determined. A recommendation index is calculated using a multi-factor decision model, and target knowledge points are recommended based on the index. Evaluation factors include the degree of knowledge point mastery, forgetting characteristics, and the degree of repeated review.
It improves the effectiveness of knowledge recommendation by considering multiple evaluation factors to accurately recommend target knowledge points, thereby enhancing users' learning efficiency.
Smart Images
Figure CN115905669B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to knowledge recommendation methods, devices, electronic devices, and storage media. Background Technology
[0002] With the development of the internet, online learning has developed rapidly. To facilitate effective review of courses, online learning devices can select and recommend review material from a large amount of review data. However, current methods of recommending knowledge simply involve filtering from vast amounts of review data and presenting it to the user, resulting in poor effectiveness. Summary of the Invention
[0003] This disclosure provides a method, apparatus, electronic device, and storage medium for knowledge recommendation.
[0004] According to one aspect of this disclosure, a knowledge recommendation method is provided, comprising: obtaining a set of candidate knowledge points; determining evaluation information for each candidate knowledge point in the set of candidate knowledge points on a plurality of set evaluation factors; determining a recommendation index for each candidate knowledge point using a multi-factor decision model based on the evaluation information of each candidate knowledge point on the plurality of evaluation factors; determining a target recommended knowledge point from the set of candidate knowledge points based on the recommendation index of each candidate knowledge point in the set of candidate knowledge points, and recommending the target recommended knowledge point.
[0005] In the technical solution disclosed herein, the recommendation index of each candidate knowledge point is determined by combining the evaluation information of each candidate knowledge point on multiple evaluation factors with a multi-factor decision model. Then, the target knowledge is recommended based on the recommendation index. Thus, multiple evaluation factors of knowledge points are considered when recommending knowledge, thereby improving the effectiveness of knowledge recommendation.
[0006] According to another aspect of this disclosure, a knowledge recommendation device is provided, comprising: a first acquisition module for acquiring a set of candidate knowledge points; a first determination module for determining evaluation information on multiple set evaluation factors for each candidate knowledge point in the set of candidate knowledge points; the first determination module is further configured to determine a recommendation index for each candidate knowledge point using a multi-factor decision model based on the evaluation information of each candidate knowledge point on the multiple evaluation factors; and a recommendation module for determining a target recommended knowledge point from the set of candidate knowledge points based on the recommendation index of each candidate knowledge point in the set of candidate knowledge points, and recommending the target recommended knowledge point.
[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method described in the first aspect of this disclosure.
[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are configured to cause the computer to perform the method described in the first aspect of this disclosure.
[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description
[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:
[0011] Figure 1 A flowchart illustrating a knowledge recommendation method provided in an embodiment of this disclosure;
[0012] Figure 2 A flowchart illustrating another knowledge recommendation method provided in an embodiment of this disclosure;
[0013] Figure 3 A flowchart illustrating another knowledge recommendation method provided in an embodiment of this disclosure;
[0014] Figure 4 A flowchart illustrating another knowledge recommendation method provided in an embodiment of this disclosure;
[0015] Figure 5 A flowchart illustrating another knowledge recommendation method provided in an embodiment of this disclosure;
[0016] Figure 6 A schematic diagram illustrating the process of determining the recommendation index for each candidate knowledge point using the multi-factor decision-making model provided in this embodiment of the disclosure;
[0017] Figure 7 This is a flowchart illustrating another knowledge recommendation method provided in an embodiment of this disclosure;
[0018] Figure 8 This is a schematic diagram of the structure of a knowledge recommendation device provided in an embodiment of this disclosure;
[0019] Figure 9This is a block diagram of an electronic device used to implement the knowledge recommendation method of the embodiments of this disclosure. Detailed Implementation
[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0021] The knowledge recommendation method, apparatus, electronic device, and storage medium of this disclosure are described below with reference to the accompanying drawings. The knowledge recommendation method of this disclosure can be applied to the knowledge recommendation apparatus of this disclosure, which can be configured in an electronic device. The electronic device can be a mobile terminal, such as a mobile phone, tablet computer, personal digital assistant, or other hardware device with various operating systems.
[0022] Figure 1 This is a schematic flowchart of a knowledge recommendation method provided in an embodiment of this disclosure.
[0023] like Figure 1 As shown, this knowledge recommendation method may include the following steps:
[0024] Step 101: Obtain the set of candidate knowledge points.
[0025] In this embodiment of the disclosure, the user's historical learning knowledge points can be recorded, and the recorded results of the user's historical learning knowledge points can be used as a set of candidate knowledge points.
[0026] Step 102: For each candidate knowledge point in the candidate knowledge point set, determine the evaluation information on the set of multiple evaluation factors.
[0027] In other words, for each candidate knowledge point in the candidate knowledge point set, different processing methods can be used to obtain evaluation information of the candidate knowledge point on multiple set evaluation factors. It should be noted that the multiple set evaluation factors may include: the degree of mastery of the knowledge point, the forgetting characteristics of the knowledge point, and the degree of repeated review of the knowledge point.
[0028] Step 103: Based on the evaluation information of each candidate knowledge point on multiple evaluation factors, a multi-factor decision model is used to determine the recommendation index of each candidate knowledge point.
[0029] Furthermore, the evaluation information of each candidate knowledge point on multiple evaluation factors is input into a pre-defined multi-factor decision model, and the output of this multi-factor decision model is used as the recommendation index for each candidate knowledge point. The pre-defined multi-factor decision model can be expressed as the following formula:
[0030]
[0031] Where Q represents the set of evaluation information for multiple evaluation factors of each candidate knowledge, P(Q) represents the recommendation index for each candidate knowledge point, and w n r represents the preset importance. n This represents the evaluation information for each evaluation factor. It should be noted that the preset importance w... n Adjustments can be made based on the effectiveness of knowledge recommendation.
[0032] Step 104: Based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, determine the target recommended knowledge point from the candidate knowledge point set, and recommend the target recommended knowledge point.
[0033] Optionally, the recommendation indices of all candidate knowledge points in the candidate knowledge set are sorted to determine the candidate knowledge point with the highest recommendation index in the candidate knowledge set, and the candidate knowledge point with the highest recommendation index is taken as the target recommended knowledge point, and the knowledge recommendation device recommends the target recommended knowledge point.
[0034] In summary, by combining the evaluation information of each candidate knowledge point on multiple evaluation factors with a multi-factor decision-making model to determine the recommendation index of each candidate knowledge point, and then recommending the target knowledge based on the recommendation index, multiple evaluation factors of knowledge points are considered during knowledge recommendation, thus improving the effectiveness of knowledge recommendation.
[0035] To accurately determine the evaluation information of each candidate knowledge point on multiple evaluation factors, such as Figure 2 As shown, Figure 2 This disclosure provides another knowledge recommendation method. In this embodiment, the evaluation factors may include: the degree of mastery of knowledge points. The answer results for candidate knowledge points can be input into a knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point at a set degree of mastery. Figure 2 The illustrated embodiment may include the following steps:
[0036] Step 201: Obtain the set of candidate knowledge points.
[0037] Step 202: Obtain the answer results for each candidate knowledge point.
[0038] In this embodiment of the disclosure, the user's current answer result for each candidate knowledge point can be obtained.
[0039] Step 203: Input the answer results into the knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point in terms of the set knowledge point mastery level.
[0040] Next, the user's current answer for each candidate knowledge point is input into the knowledge point mastery prediction model. This model can output evaluation information for each candidate knowledge point in terms of the set level of mastery. For example, the model can output a knowledge point mastery value for each candidate knowledge point, which represents the user's level of mastery of each point. The knowledge point mastery value can be a percentage between 0 and 1.
[0041] In order to accurately determine the evaluation information of each candidate knowledge point in terms of the set knowledge point mastery level, the knowledge point mastery prediction model needs to be obtained before inputting the answer results into the knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point in terms of the knowledge point mastery level.
[0042] Optionally, obtain the historical answer results for each candidate knowledge; use a preset proportion of the historical answer results as a training dataset; use the training dataset to train the initial knowledge point mastery prediction model to generate a knowledge point mastery prediction model.
[0043] In other words, the historical answer results of users for each candidate knowledge can be recorded to obtain the historical answer results for each candidate knowledge. A preset proportion (e.g., 80%) of the historical answer results can be used as a training dataset, and the initial knowledge point mastery prediction model can be trained using this training dataset to generate the knowledge point mastery prediction model.
[0044] It should be noted that, in order to improve the prediction performance of the knowledge point mastery prediction model, multiple initial knowledge point mastery prediction models can be trained simultaneously using a training dataset to generate multiple trained knowledge point mastery prediction models. The AUC (Area Under Curve) of the prediction results output by the multiple trained knowledge point mastery prediction models is compared, and the trained knowledge point mastery prediction model with the highest AUC (Area Under Curve) is selected as the knowledge point mastery prediction model.
[0045] In addition, to further improve the accuracy of the knowledge point mastery prediction model, in this embodiment of the disclosure, before inputting the answer results into the knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point in terms of knowledge point mastery, a test dataset can also be used to test the knowledge point mastery prediction model to determine the accuracy of the prediction results of the knowledge point mastery prediction model.
[0046] Step 204: Based on the evaluation information of the mastery level of each candidate knowledge point, a multi-factor decision model is used to determine the recommendation index of each candidate knowledge point.
[0047] Step 205: Based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, determine the target recommended knowledge point from the candidate knowledge point set, and recommend the target recommended knowledge point.
[0048] In summary, by obtaining the answer results for each candidate knowledge point and inputting these results into the knowledge point mastery prediction model, the evaluation information of each candidate knowledge point in terms of the set knowledge point mastery level can be determined. Thus, the evaluation information of each candidate knowledge point in terms of the set knowledge point mastery level can be accurately determined.
[0049] To accurately determine the evaluation information for each candidate knowledge point based on its forgetting characteristics, such as... Figure 3 As shown, Figure 3 This is another knowledge recommendation method provided by an embodiment of the present disclosure. In this embodiment, the forgetting characteristic curve can be queried based on the time interval between the last answer and the historical adjacent answers for each candidate knowledge, thereby determining the evaluation information of each candidate knowledge on the forgetting characteristics of the set knowledge points. Figure 3 The illustrated embodiment may include the following steps:
[0050] Step 301: Obtain the set of candidate knowledge points.
[0051] Step 302: Query the forgetting characteristic curve based on the time interval between the last answer and the historical adjacent answers for each candidate knowledge point to determine the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristics.
[0052] In other words, we can first obtain the time interval between the last answer and the historical adjacent answers for each candidate knowledge point, query the forgetting characteristic curve based on the time interval, and use the query result as the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristic.
[0053] Before querying the forgetting characteristic curve based on the time interval between the last answer and the historical adjacent answers for each candidate knowledge point, the forgetting characteristic curve can be obtained first.
[0054] Optionally, for each candidate knowledge point, the historical answer time and corresponding answer accuracy are obtained; the forgetting parameters of multiple candidate forgetting curves are obtained; based on the historical answer time, the corresponding answer accuracy, and the forgetting parameters of each candidate forgetting curve, the error value corresponding to each candidate forgetting curve is determined; wherein, the error value is used to indicate the fitting error between the mapping relationship curve of historical answer time and answer accuracy and each candidate forgetting curve; the candidate forgetting curve with the smallest error value is taken as the forgetting characteristic curve.
[0055] In other words, by obtaining the historical answer time and corresponding accuracy rate for each candidate knowledge point, multiple answer intervals can be determined for each candidate knowledge point based on its historical adjacent answer times. Furthermore, the change in accuracy rate corresponding to each answer interval can be determined based on the historical answer time for each candidate knowledge point. Then, based on the multiple answer intervals for each candidate knowledge point, the change in accuracy rate for each time interval, and the forgetting parameters of each candidate forgetting curve, the error value corresponding to each candidate forgetting curve can be determined. The candidate forgetting curve with the smallest error value is taken as the forgetting characteristic curve. It should be noted that the error value indicates the fitting error between the mapping curve of historical answer time and answer accuracy rate and each candidate forgetting curve. Specifically, the error value corresponding to each candidate forgetting curve can be expressed by the following formula:
[0056]
[0057] Where all(t,y) represents all answer time intervals and the corresponding change in answer accuracy, t represents the time interval, y represents the change in answer accuracy corresponding to the answer time interval, n represents the number of answer time intervals and the corresponding change in answer accuracy in all(t,y), and D represents the forgetting parameter of the candidate curve.
[0058] In this embodiment of the disclosure, each candidate knowledge point can be fitted with a different candidate forgetting curve e. -Dt Different candidate forgetting curves e -Dt For different forgetting parameters D, the mapping relationship curve between the historical answering time and answering accuracy of each candidate knowledge point and the fitting error value between each candidate forgetting curve are determined. The candidate forgetting curve with the smallest error value is taken as the forgetting characteristic curve.
[0059] For example, if user 1 answers questions multiple times on candidate knowledge point A, the time interval t between two consecutive answers can be calculated, and the change in accuracy y corresponding to that time interval can be determined based on the accuracy rates of those two consecutive answers. For instance, if user 1 answers questions on candidate knowledge point A on the first day with an accuracy rate of 80%, and then answers on the same question on the fifth day (4 days later) with an accuracy rate of 60%, the corresponding time interval t is 4 days, and the change in accuracy y is 20%. Each time interval on candidate knowledge point A and the corresponding change in accuracy can be represented as (t, y). Furthermore, all time intervals on candidate knowledge point A and the corresponding changes in accuracy can be represented as all(t, y) = {(t, y)}. n Finally, based on the multiple answer intervals for candidate knowledge point A, the change in answer accuracy corresponding to each time interval, and the forgetting parameter D of each candidate forgetting curve (different candidate forgetting curves correspond to different forgetting parameters), the error value corresponding to each candidate forgetting curve can be determined. When the error value is minimized, the corresponding forgetting parameter D can be determined, and the candidate forgetting curve corresponding to the forgetting parameter D can be used as the forgetting characteristic curve.
[0060] Step 303: Based on the evaluation information of each candidate knowledge point in terms of knowledge point forgetting characteristics, a multi-factor decision model is used to determine the recommendation index of each candidate knowledge point.
[0061] Step 304: Based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, determine the target recommended knowledge point from the candidate knowledge point set, and recommend the target recommended knowledge point.
[0062] In summary, by querying the forgetting characteristic curve based on the time interval between the last answer and the historical adjacent answers for each candidate knowledge point, the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristic can be determined. Thus, the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristic can be accurately determined.
[0063] To accurately determine the evaluation information for each candidate knowledge point in terms of the degree of repeated review of the set knowledge points, such as Figure 4 As shown, Figure 4 This disclosure provides another knowledge recommendation method. In this embodiment, the difference between the number of times each candidate knowledge point is reviewed and the average number of times each candidate knowledge point is reviewed is normalized according to a normalization function to determine the evaluation information of each candidate knowledge point in terms of the set degree of repeated review. Figure 4 The illustrated embodiment may include the following steps:
[0064] Step 401: Obtain the set of candidate knowledge points.
[0065] Step 402: Obtain the number of times the target client reviews each candidate knowledge point and the average number of times the target client reviews each candidate knowledge point.
[0066] In this embodiment of the disclosure, the number of times the target client reviews each candidate knowledge point can be recorded to obtain the number of times the target client reviews each candidate knowledge point. The number of times the target client reviews each candidate knowledge point can be added together, and the sum can be compared with the total number of candidate knowledge points to obtain the average number of times the target client reviews each candidate knowledge point.
[0067] For example, the candidate knowledge point set includes: candidate knowledge point 1, candidate knowledge point 2, candidate knowledge point 3, and candidate knowledge point 4. The user reviewed candidate knowledge point 1 6 times, candidate knowledge point 2 4 times, candidate knowledge point 3 6 times, and candidate knowledge point 4 8 times. Then, the review counts for candidate knowledge points 1, 2, 3, and 4 are added together, and the result (6+4+6+8=24) is compared with the total number of candidate knowledge points, 4, to obtain the target client's average review count for each candidate knowledge point as 6 times.
[0068] Step 403: Using a preset normalization function, the difference between the number of times each candidate knowledge point is reviewed and the average number of times each candidate knowledge point is reviewed is normalized to determine the evaluation information of each candidate knowledge point in terms of the degree of repeated review of the set knowledge points.
[0069] For example, the difference between the number of times each candidate knowledge point was reviewed and the average number of times all candidate knowledge points were reviewed can be input into the normalization function Sigmoid. The output of the normalization function Sigmoid can then be used as the evaluation information for each candidate knowledge point in terms of the degree of repeated review of the set knowledge point. For instance, if the number of times candidate knowledge point A was reviewed is 6, and the average number of times all candidate knowledge points were reviewed is 4, the difference between 6 and 4 can be input into the normalization function Sigmoid, and the output of the normalization function Sigmoid can then be used as the evaluation information for each candidate knowledge point in terms of the degree of repeated review of the set knowledge point.
[0070] It should be noted that the output of the normalization function Sigmoid has a value range of (0,1). The output value can represent the degree of repeated review of each candidate knowledge at the set knowledge point. The higher the output value, the higher the degree of repeated review of each candidate knowledge at the set knowledge point.
[0071] Step 404: Based on the evaluation information of the degree of repeated review of each candidate knowledge point, a multi-factor decision model is used to determine the recommendation index of each candidate knowledge point.
[0072] Step 405: Based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, determine the target recommended knowledge point from the candidate knowledge point set, and recommend the target recommended knowledge point.
[0073] In summary, by obtaining the number of times the target client reviews each candidate knowledge point and the average number of times the target client reviews each candidate knowledge point, and by using a preset normalization function to normalize the difference between the number of times each candidate knowledge point is reviewed and the average number of times each candidate knowledge point is reviewed, the evaluation information of each candidate knowledge point in terms of the set degree of repeated review can be determined. Thus, the evaluation information of each candidate knowledge point in terms of the set degree of repeated review can be accurately determined.
[0074] To accurately determine the recommendation index for each candidate knowledge point, such as Figure 5 As shown, Figure 5 This disclosure provides another knowledge recommendation method. In this embodiment, evaluation factors may include: the degree of mastery of the knowledge point, the forgetting characteristics of the knowledge point, and the degree of repeated review of the knowledge point. A multi-factor decision model can be used to determine the recommendation index of each candidate knowledge point based on the evaluation information of each candidate knowledge point on multiple evaluation factors. Figure 5 The illustrated embodiment may include the following steps:
[0075] Step 501: Obtain the set of candidate knowledge points.
[0076] Step 502: For each candidate knowledge point in the candidate knowledge point set, determine the evaluation information on multiple set evaluation factors; wherein, the evaluation factors may include: the degree of mastery of the knowledge point, the forgetting characteristics of the knowledge point, and the degree of repeated review of the knowledge point.
[0077] In this embodiment of the disclosure, the evaluation factors may include: the degree of mastery of knowledge points, the forgetting characteristics of knowledge points, and the degree of repeated review of knowledge points. For each candidate knowledge point in the candidate knowledge point set, the evaluation information on the degree of mastery of knowledge points can be determined by a knowledge point mastery prediction model, the evaluation information on the forgetting characteristics of knowledge points can be determined by a forgetting characteristic curve, and a preset normalization function can be used to normalize the difference between the number of reviews for each candidate knowledge point and the average number of reviews for each candidate knowledge point, thereby determining the evaluation information on the degree of repeated review of each candidate knowledge point. For specific implementation details, please refer to the above embodiments; this disclosure will not repeat them further.
[0078] Step 503: Based on the evaluation information of each candidate knowledge point in terms of knowledge point mastery, knowledge point forgetting characteristics, and knowledge point repetition and review, a multi-factor decision model is used to determine the recommendation index of each candidate knowledge point.
[0079] For example, such as Figure 6 As shown, the evaluation information for each candidate knowledge point in terms of knowledge point mastery, forgetting characteristics, and repeated review is r1, r2, and r3, respectively. This evaluation information is input into a pre-defined multi-factor decision model, and can be represented by the following formula:
[0080]
[0081] Where Q represents the set of evaluation information for each candidate knowledge point in terms of mastery, forgetting characteristics, and repetition frequency; w1, w2, and w3 are preset importance values. P(Q) represents the recommendation index for each candidate knowledge point. w1, w2, and w3 can be adjusted based on recommendation effectiveness (such as online experimental results).
[0082] Step 504: Based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, determine the target recommended knowledge point from the candidate knowledge point set, and recommend the target recommended knowledge point.
[0083] In summary, this method involves obtaining a set of candidate knowledge points; for each candidate knowledge point, determining its evaluation information based on multiple predetermined evaluation factors, including the degree of knowledge point mastery, forgetting characteristics, and frequency of repeated review; using a multi-factor decision model to determine the recommendation index for each candidate knowledge point based on these evaluations; and finally, identifying and recommending target knowledge points based on their recommendation indices. This approach considers multiple evaluation factors during knowledge recommendation, thus improving its effectiveness.
[0084] To illustrate the above embodiments more clearly, examples are given below.
[0085] For example, such as Figure 7As shown, taking the recommendation of review knowledge points for user A as an example, firstly, a candidate set of review knowledge points for user A can be obtained, such as all knowledge points that user A has learned in the past three months; secondly, the mastery factor, forgetting factor, and user experience factor of user A on all candidate knowledge points are calculated; then, based on the importance of each factor, the recommendation index of user A on different candidate knowledge points is calculated by a multi-factor decision formula; finally, the knowledge point with the highest recommendation index is selected as the output of the review knowledge point recommendation system according to the required number of review knowledge points.
[0086] The knowledge recommendation method of this disclosure involves: acquiring a set of candidate knowledge points; determining the evaluation information of each candidate knowledge point on multiple predefined evaluation factors; determining a recommendation index for each candidate knowledge point using a multi-factor decision model based on the evaluation information of each candidate knowledge point on the multiple evaluation factors; determining a target recommended knowledge point from the set of candidate knowledge points based on the recommendation index of each candidate knowledge point, and recommending the target recommended knowledge point. Therefore, multiple evaluation factors of knowledge points are considered during knowledge recommendation, improving the effectiveness of knowledge recommendation.
[0087] To implement the above embodiments, this disclosure also proposes a knowledge recommendation device.
[0088] like Figure 8 As shown, Figure 8 A knowledge recommendation device 800 provided in this embodiment of the present disclosure may include: a first acquisition module 810, a first determination module 820, and a recommendation module 830.
[0089] The first acquisition module 810 is used to acquire a set of candidate knowledge points; the first determination module 820 is used to determine the evaluation information of each candidate knowledge point in the set of candidate knowledge points on multiple set evaluation factors; the first determination module 820 is also used to determine the recommendation index of each candidate knowledge point by using a multi-factor decision model based on the evaluation information of each candidate knowledge point on multiple evaluation factors; and the recommendation module 830 is used to determine the target recommended knowledge point from the set of candidate knowledge points based on the recommendation index of each candidate knowledge point in the set of candidate knowledge points, and recommend the target recommended knowledge point.
[0090] As one possible implementation of this disclosure, the evaluation factors include: the degree of mastery of knowledge points. The first determining module is specifically used to: obtain the answer result of each candidate knowledge point; input the answer result into the knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point in the set degree of mastery of knowledge points.
[0091] As one possible implementation of this disclosure, the knowledge recommendation device 800 further includes a second acquisition module and a training module.
[0092] The second acquisition module is used to acquire the historical answer results for each candidate knowledge point; the second acquisition module is also used to use a preset proportion of the historical answer results as a training dataset; the training module is used to train the initial knowledge point mastery prediction model using the training dataset to generate the knowledge point mastery prediction model.
[0093] As one possible implementation of this disclosure, the knowledge recommendation device 800 further includes a third acquisition module and a testing module.
[0094] The third acquisition module is used to use historical answer results other than the training dataset as the test dataset; the testing module is used to test the knowledge point mastery prediction model using the test dataset.
[0095] As one possible implementation of this disclosure, the evaluation factors include: the forgetting characteristics of knowledge points. The first determining module 820 is further configured to: query the forgetting characteristic curve based on the time interval between the last answer and the historical adjacent answers of each candidate knowledge point, so as to determine the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristics.
[0096] As one possible implementation of this disclosure, the knowledge recommendation device 800 further includes: a fourth acquisition module and a second determination module.
[0097] The fourth acquisition module is used to acquire the historical answer time and corresponding answer accuracy for each candidate knowledge point; the fourth acquisition module is also used to acquire the forgetting parameters of multiple candidate forgetting curves; the second determination module is used to determine the error value corresponding to each candidate forgetting curve based on the historical answer time, the corresponding answer accuracy, and the forgetting parameters of each candidate forgetting curve; wherein, the error value is used to indicate the fitting error between the mapping relationship curve of historical answer time and answer accuracy and each candidate forgetting curve; the second determination module is also used to select the candidate forgetting curve with the smallest error value as the forgetting characteristic curve.
[0098] As one possible implementation of this disclosure, the evaluation factors include: the degree of repeated review of knowledge points. The first determining module 820 is further configured to: obtain the number of times the target client reviews each of the candidate knowledge points and the average number of times the target client reviews each candidate knowledge point; and use a preset normalization function to normalize the difference between the number of times each candidate knowledge point is reviewed and the average number of times it is reviewed, so as to determine the evaluation information of each candidate knowledge point in the set degree of repeated review of knowledge points.
[0099] The knowledge recommendation device of this disclosure acquires a set of candidate knowledge points; for each candidate knowledge point in the set, it determines evaluation information on multiple predefined evaluation factors; based on the evaluation information of each candidate knowledge point on the multiple evaluation factors, it uses a multi-factor decision model to determine a recommendation index for each candidate knowledge point; based on the recommendation index of each candidate knowledge point in the set, it determines a target recommended knowledge point from the set of candidate knowledge points and recommends the target recommended knowledge point. Therefore, multiple evaluation factors of knowledge points are considered during knowledge recommendation, improving the effectiveness of knowledge recommendation.
[0100] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.
[0101] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.
[0102] Figure 9 This is a block diagram illustrating an electronic device 900 according to an exemplary embodiment. For example... Figure 9 As shown, the above-mentioned electronic device 900 includes:
[0103] The system includes a memory 910 and a processor 920, and a bus 930 connecting different components (including the memory 910 and the processor 920). The memory 910 stores a computer program, which, when executed by the processor 920, implements the knowledge recommendation method described in this embodiment.
[0104] Bus 930 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.
[0105] Electronic device 900 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 900, including volatile and non-volatile media, removable and non-removable media.
[0106] The memory 910 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 940 and / or cache memory 950. The electronic device 900 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 960 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 9 Not shown; usually referred to as a "hard drive"). Although Figure 9 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 930 via one or more data media interfaces. Memory 910 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.
[0107] A program / utility 980 having a set (at least one) of program modules 970 may be stored, for example, in memory 910. Such program modules 970 include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 970 typically perform the functions and / or methods described in the embodiments of this disclosure.
[0108] Electronic device 900 can also communicate with one or more external devices 990 (e.g., keyboard, pointing device, display 991, etc.), and with one or more devices that enable a user to interact with the electronic device 900, and / or with any device that enables the electronic device 900 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 992. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 993. Figure 9 As shown, network adapter 993 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.
[0109] The processor 920 performs various functional applications and data processing by running programs stored in the memory 910.
[0110] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0111] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this disclosure, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0112] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this disclosure includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of this disclosure pertain.
[0113] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0114] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0115] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it includes one or a combination of the steps of the method embodiments.
[0116] Furthermore, the functional units in the various embodiments of this disclosure can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0117] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present disclosure have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present disclosure.
Claims
1. A knowledge recommendation method, characterized in that, include: Obtain a candidate knowledge point set, which includes the user's historical learning knowledge point records; For each candidate knowledge point in the candidate knowledge point set, evaluation information is determined on multiple set evaluation factors, wherein the evaluation factors include the degree of mastery of the knowledge point, the forgetting characteristics of the knowledge point, and the degree of repeated review of the knowledge point. Based on the evaluation information of each candidate knowledge point on multiple evaluation factors, a multi-factor decision model is used to determine the recommendation index of each candidate knowledge point, wherein the expression of the multi-factor decision model is: Where Q represents the set of evaluation information for multiple evaluation factors of each candidate knowledge, P(Q) represents the recommendation index for each candidate knowledge point, and w n r represents the preset importance. n This indicates the evaluation information for each evaluation factor; Based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, a target recommended knowledge point is determined from the candidate knowledge point set, and the target recommended knowledge point is recommended. If the evaluation factor is the forgetting characteristic of the knowledge point, then determining the evaluation information for each candidate knowledge point in the candidate knowledge point set on the set of multiple evaluation factors includes: Based on the time interval between the last answer and the historical adjacent answer for each candidate knowledge point, the forgetting characteristic curve is queried to determine the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristic; Before querying the forgetting characteristic curve based on the time interval between the last answer and the historical adjacent answers for each candidate knowledge point, the method further includes: For each candidate knowledge point, obtain the historical answer time and corresponding answer accuracy rate; Obtain the forgetting parameters of multiple candidate forgetting curves; Based on the historical answering time, the corresponding answering accuracy rate, and the forgetting parameters of each candidate forgetting curve, an error value corresponding to each candidate forgetting curve is determined; wherein, the error value is used to indicate the fitting error between the mapping relationship curve of the historical answering time and the answering accuracy rate and each candidate forgetting curve, and the error value corresponding to each candidate forgetting curve is expressed by the following formula: Where all(t,y) represents all answer time intervals and the corresponding change in answer accuracy, t represents the time interval, y represents the change in answer accuracy corresponding to the answer time interval, and n represents the number of answer time intervals and the corresponding change in answer accuracy in all(t,y). Each candidate knowledge point is fitted with a different candidate forgetting curve e. -Dt Different candidate forgetting curves e -Dt Corresponding to different forgetting parameters D; The candidate forgetting curve with the smallest error value is taken as the forgetting characteristic curve; If the evaluation factor is the degree of repeated review of the knowledge point, then for each candidate knowledge point in the candidate knowledge point set, determining the evaluation information on the set of multiple evaluation factors includes: Obtain the number of times the target client reviews each of the candidate knowledge points and the average number of times the target client reviews each of the candidate knowledge points; A preset normalization function is used to normalize the difference between the number of times each candidate knowledge point is reviewed and the average number of times each candidate knowledge point is reviewed, so as to determine the evaluation information of each candidate knowledge point in terms of the degree of repeated review of the set knowledge points.
2. The method according to claim 1, wherein, If the evaluation factor is the degree of mastery of the knowledge point, then for each candidate knowledge point in the candidate knowledge point set, determining the evaluation information on the set of multiple evaluation factors includes: Obtain the answer result for each of the candidate knowledge points; The answer results are input into the knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point in terms of the set knowledge point mastery level.
3. The method according to claim 2, wherein, Before inputting the answer results into the knowledge point mastery prediction model to determine the evaluation information of the knowledge point mastery level for each candidate knowledge point, the method further includes: Obtain the historical answer results for each of the candidate knowledge points; Use a predetermined proportion of the historical answer results as the training dataset; The initial knowledge point mastery prediction model is trained using the training dataset to generate a knowledge point mastery prediction model.
4. The method according to claim 3, wherein, The method further includes: The historical answer results other than those in the training dataset are used as the test dataset. The knowledge point mastery prediction model was tested using the test dataset.
5. A knowledge recommendation device, characterized in that, include: The first acquisition module is used to acquire a set of candidate knowledge points, which includes the user's historical learning knowledge point records. The first determining module is used to determine the evaluation information of each candidate knowledge point in the candidate knowledge point set on multiple set evaluation factors, wherein the multiple evaluation factors include the degree of mastery of the knowledge point, the forgetting characteristics of the knowledge point, and the degree of repeated review of the knowledge point. The first determining module is further configured to determine the recommendation index of each candidate knowledge point based on the evaluation information of each candidate knowledge point on multiple evaluation factors using a multi-factor decision model, wherein the expression of the multi-factor decision model is: Where Q represents the set of evaluation information for multiple evaluation factors of each candidate knowledge, P(Q) represents the recommendation index for each candidate knowledge point, and w n r represents the preset importance. n This indicates the evaluation information for each evaluation factor; The recommendation module is used to determine a target recommended knowledge point from the candidate knowledge point set based on the recommendation index of each candidate knowledge point in the candidate knowledge point set, and to recommend the target recommended knowledge point. If the evaluation factor is the forgetting characteristic of the knowledge point, then determining the evaluation information for each candidate knowledge point in the candidate knowledge point set on the set of multiple evaluation factors includes: Based on the time interval between the last answer and the historical adjacent answer for each candidate knowledge point, the forgetting characteristic curve is queried to determine the evaluation information of each candidate knowledge point on the set knowledge point forgetting characteristic; The device further includes: The fourth acquisition module is used to acquire the historical answer time and corresponding answer accuracy for each candidate knowledge point; The fourth acquisition module is also used to acquire forgetting parameters of multiple candidate forgetting curves; The second determining module is used to determine the error value corresponding to each candidate forgetting curve based on the historical answering time, the corresponding answering accuracy rate, and the forgetting parameter of each candidate forgetting curve; wherein, the error value is used to indicate the fitting error between the mapping relationship curve of the historical answering time and the answering accuracy rate and each candidate forgetting curve; The second determining module is further configured to use the candidate forgetting curve with the smallest error value as the forgetting characteristic curve; If the evaluation factor is the degree of repeated review of the knowledge point, then for each candidate knowledge point in the candidate knowledge point set, determining the evaluation information on the set of multiple evaluation factors includes: Obtain the number of times the target client reviews each of the candidate knowledge points and the average number of times the target client reviews each of the candidate knowledge points; A preset normalization function is used to normalize the difference between the number of times each candidate knowledge point is reviewed and the average number of times it is reviewed, so as to determine the evaluation information of each candidate knowledge point in terms of the degree of repeated review.
6. The apparatus according to claim 5, wherein, If the evaluation factor is the degree of mastery of the knowledge point, then for each candidate knowledge point in the candidate knowledge point set, determining the evaluation information on the set of multiple evaluation factors includes: Obtain the answer result for each of the candidate knowledge points; The answer results are input into the knowledge point mastery prediction model to determine the evaluation information of each candidate knowledge point in terms of the set knowledge point mastery level.
7. The apparatus according to claim 6, wherein, The device further includes: The second acquisition module is used to acquire the historical answer results for each of the candidate knowledge points; The second acquisition module is further configured to use a preset proportion of the historical answer results as a training dataset; The training module is used to train the initial knowledge point mastery prediction model using the training dataset to generate a knowledge point mastery prediction model.
8. The apparatus according to claim 7, wherein, The device further includes: The third acquisition module is used to take the historical answer results other than the training dataset from the historical answer results as the test dataset. The testing module is used to test the knowledge point mastery prediction model using the test dataset.
9. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-4.
10. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method as described in any one of claims 1-4.
11. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-4.