A course recommendation method and device, equipment and medium

Abstract

A course recommendation method, device, equipment and medium are disclosed. The method comprises: acquiring actual interaction messages between a target user in real time; determining a current interest value of the target user according to the actual interaction messages and a user label of the target user; determining a corresponding target recommendation strategy according to a comparison result between the current interest value and a preset interest threshold value, and using the target recommendation strategy to recommend a course to the target user. The present application solves the problem that the course recommendation in the prior art is subjective and based on human experience, resulting in low recommendation pertinence, and achieves targeted course recommendation to the target user, improves the course recommendation efficiency, and enhances the user experience.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a course recommendation method, apparatus, device, and medium. Background Technology

[0002] With the continuous development of technology, online courses have gained popularity due to their flexibility in terms of time and location. Consequently, course recommendations to users are also being conducted online.

[0003] In existing technologies, course recommendations can be made based on user interactions, but these recommendations rely on subjective human experience, resulting in low relevance. Therefore, how to provide targeted course recommendations to users is a pressing issue that needs to be addressed. Summary of the Invention

[0004] This invention provides a course recommendation method, apparatus, device, and medium to solve the problem of low recommendation specificity caused by subjective course recommendations to users based on human experience in the prior art.

[0005] According to one aspect of the present invention, a course recommendation method is provided, comprising:

[0006] Real-time acquisition of actual interaction messages with target users;

[0007] The current interest value of the target user is determined based on the actual interaction messages and the target user's user tags;

[0008] Based on the comparison between the current interest value and the preset interest threshold, a corresponding target recommendation strategy is determined, and the target recommendation strategy is used to recommend courses to the target user.

[0009] According to another aspect of the present invention, a course recommendation device is provided, comprising:

[0010] The first acquisition module is used to acquire actual interaction messages with the target user in real time;

[0011] The determination module is used to determine the current interest value of the target user based on the actual interaction messages and the target user's user tags;

[0012] The recommendation module is used to determine the corresponding target recommendation strategy based on the comparison result between the current interest value and the preset interest threshold, so as to recommend courses to the target user using the target recommendation strategy.

[0013] According to another aspect of the present invention, a course recommendation electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the course recommendation method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the course recommendation method described in any embodiment of the present invention.

[0018] The technical solution of this invention acquires real-time interaction messages with the target user, determines the target user's current interest value based on the real interaction messages and the target user's user tags, and then determines a target recommendation strategy based on the comparison between the current interest value and a preset interest threshold. This strategy is then used to recommend courses to the target user, solving the problem of low recommendation targeting caused by subjective course recommendations based on human experience in the prior art. This achieves targeted course recommendations to the target user, improves course recommendation efficiency, and enhances the user experience.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a course recommendation method provided in an embodiment of the present invention;

[0022] Figure 2 This is a flowchart of another course recommendation method provided in an embodiment of the present invention;

[0023] Figure 3 This is a flowchart of another course recommendation method provided by an embodiment of the present invention;

[0024] Figure 4This is a schematic diagram of the structure of a course recommendation device provided in an embodiment of the present invention;

[0025] Figure 5 This is a structural block diagram of a course recommendation electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] In one embodiment, Figure 1 This is a flowchart of a course recommendation method provided in an embodiment of the present invention. This embodiment is applicable to situations where courses are automatically recommended to users. This method can be executed by a course recommendation device, which can be implemented in hardware and / or software and can be configured in a course recommendation electronic device. Figure 1 As shown, the method includes:

[0029] S110: Real-time acquisition of actual interaction messages with target users.

[0030] In this context, "actual interaction messages" refers to information related to interactions with the target user. During operation, any chat tool can be used to interact with the target user, and upon detecting interaction, the interaction messages between the user and the target user are retrieved in real time as the corresponding actual interaction messages.

[0031] S120. Determine the target user's current interest value based on the actual interaction messages and the target user's user tags.

[0032] The user tag indicates whether the target user has been successfully recommended a course. In one embodiment, the user tag includes one of the following: successfully recommended user; unsuccessfully recommended user. A successfully recommended user refers to a user whose course has been successfully recommended; an unsuccessfully recommended user refers to a user whose course has not been successfully recommended. In this embodiment, if the target user's user tag is "successfully recommended user," other courses can be recommended to the target user based on actual interaction messages, or the course can be recommended to the target user again.

[0033] In one embodiment, S120 includes S1201-S1202:

[0034] S1201. Determine the user tags of the target user based on the target user's recommendation record information.

[0035] The recommendation record information refers to the record information of successfully recommending courses to the target user. This recommendation record information may include, but is not limited to, publicly available personal information of the target user, as well as information related to successfully recommended courses. Specifically, the information related to successfully recommended courses may include, but is not limited to, course type and course duration; the publicly available personal information of the target user may include, but is not limited to, information such as age, gender, and occupation.

[0036] In this embodiment, it can be determined whether a course has been successfully recommended to the target user based on the target user's recommendation record information, thereby determining the user tag corresponding to the target user.

[0037] S1202. Input the actual interaction messages and user tags into the pre-created target recognition model to obtain the current interest value of the target user.

[0038] Here, the object recognition model refers to a pre-created and trained recognition model. For example, the object recognition model can be an OpenAI model. In this embodiment, the current interest value is used to characterize the target user's interest in the recommended courses. It can be understood that the higher the current interest value, the more interested the target user is in the recommended courses.

[0039] In one embodiment, inputting actual interaction messages and user tags into a pre-created target recognition model to obtain the current interest value of the target user includes: inputting user tags into the pre-created target recognition model to obtain a target reference system that matches the target user in the target recognition model; inputting actual interaction messages into the pre-created target recognition model to obtain the actual vector value of the actual interaction messages in the target reference system; determining the relative distance between the actual vector value and the target vector value corresponding to the benchmark interaction message in the target reference system as the similarity between the actual interaction message and the benchmark interaction message; and determining the current interest value of the target user based on the weight value of each similarity and the corresponding actual interaction message.

[0040] It should be noted that the target recognition model can include one or more reference frames, and each reference frame is obtained by classifying according to user tags; that is, the number of reference frames is equal to the number of user tags. The actual vector value is used to represent the coordinate point of the actual interaction message in the target reference frame. Natural language processing (NLP) tools are configured in the target recognition model. In actual operation, the actual interaction message can include one or more sentences. The NLP tools in the target recognition model can be used to perform semantic analysis on each sentence in the actual interaction message to determine the coordinate point position of that sentence in the target reference frame, i.e., to determine the corresponding actual vector value.

[0041] Among them, the benchmark interactive message refers to the relevant interactive message that has been successfully recommended to the user; similarity is used to characterize the relative distance between the actual interactive message and the benchmark interactive message, which can also be called the proximity between the two.

[0042] In this embodiment, the target user's user tags are input into the target recognition model, enabling the model to directly determine the corresponding target reference frame based on the user tags. Simultaneously, the natural language processing (NLP) tool within the target recognition model performs semantic analysis on the actual interaction messages to obtain the actual vector values ​​of the actual interaction messages in the target reference frame. Then, the relative distance between the actual vector value of the actual interaction message in the target reference frame (i.e., the corresponding coordinate point position) and the target vector value (i.e., the corresponding coordinate point position) of the baseline interaction message is calculated as the similarity between the two. Then, based on the similarity of all actual interaction messages with the target user and the weight values ​​of the corresponding actual interaction messages, the target user's current interest value is determined. This is achieved by multiplying the similarity of each actual interaction message by its corresponding weight value. All these product values ​​are then summed to obtain the target user's current interest value. The weight values ​​of the actual interaction messages can be determined based on the interaction message type, and the sum of the weight values ​​for all interaction message types is 1. For example, interaction message types include type 1, type 2, and type 3, and the weight values ​​for each interaction message type are a, b, and c, respectively. The sum of a, b, and c is then 1.

[0043] S130. Determine the corresponding target recommendation strategy based on the comparison result between the current interest value and the preset interest threshold, and use the target recommendation strategy to recommend courses to the target users.

[0044] The preset interest threshold is used to characterize whether a target user is interested in the course. In this embodiment, if the target user's current interest value reaches the preset interest threshold, it indicates that the target user is interested in the course, and the course can be recommended to the target user according to the corresponding target recommendation strategy; conversely, if the target user's current interest value does not reach the preset interest threshold, it indicates that the target user is not interested in the course, and course recommendations to the target user are stopped, or other courses are recommended to the target user.

[0045] The technical solution of this embodiment obtains the actual interaction messages between the target user in real time, determines the target user's current interest value based on the actual interaction messages and the target user's user tags, and then determines the target recommendation strategy based on the comparison result between the current interest value and the preset interest threshold. The target recommendation strategy is then used to recommend courses to the target user. This solves the problem of low recommendation targeting caused by subjective course recommendations based on human experience in the prior art. It enables targeted course recommendations to target users, improves course recommendation efficiency, and enhances the user experience.

[0046] In one embodiment, Figure 2This is a flowchart of another course recommendation method provided by an embodiment of the present invention. This embodiment describes the creation process of the target recognition model based on the above embodiments. Figure 2 As shown, the method includes:

[0047] S210. Obtain the original training dataset.

[0048] The original training dataset includes original historical recommendation data and original historical interaction messages. In this embodiment, the original training dataset includes positive data and negative data, where positive data refers to data related to successfully recommended courses, and negative data refers to data related to unsuccessfully recommended courses. The original historical recommendation data includes: original historical positive recommendation data and original historical negative recommendation data; the original historical interaction messages include: original historical positive interaction messages and original historical negative interaction messages; where original historical positive recommendation data refers to information about courses that have been successfully recommended; original historical negative recommendation data refers to information about courses that have not been successfully recommended; original historical positive interaction messages refer to interaction messages about courses that have been successfully recommended to users; and original historical negative interaction messages refer to interaction messages about courses that have not been successfully recommended to users.

[0049] S220. Filter the original historical interaction messages according to the preset filtering rules to obtain the corresponding target historical interaction messages.

[0050] In one embodiment, S220 includes S2201-S2202:

[0051] S2201. Perform semantic analysis on the original historical interaction messages and filter out the corresponding dirty data.

[0052] Dirty data refers to data that is useless for model training. In this embodiment, natural language processing tools can be used to perform semantic analysis on the original historical interaction messages to filter out the corresponding dirty data. For example, dirty data may include, but is not limited to, greetings.

[0053] S2202. Filter dirty data from the original historical interaction messages according to the preset filtering rules to obtain the corresponding target historical interaction messages.

[0054] The target historical interaction messages refer to the interaction messages that can be used to train the original recognition model. In practice, the interaction messages with the target user may include some useful data and some useless data. In order to improve the effectiveness of the data input into the training data of the original recognition model, the original historical interaction messages can be filtered to obtain the corresponding target historical interaction messages.

[0055] S230. Train the pre-created original recognition model based on the target's historical interaction messages and original historical recommendation data to obtain the corresponding target recognition model.

[0056] The target recognition model can be understood as a model that meets the current recommended course scenario. In this embodiment, the target's historical interaction messages and original historical recommendation data can be directly input into the original recognition model to train the original recognition model and obtain the corresponding target recognition model.

[0057] S240: Real-time acquisition of actual interaction messages with the target user.

[0058] S250. Determine the target user's current interest value based on actual interaction messages and the target user's user tags.

[0059] S260. Determine the corresponding target recommendation strategy based on the comparison result between the current interest value and the preset interest threshold, and use the target recommendation strategy to recommend courses to the target users.

[0060] The technical solution of this embodiment, based on the above embodiments, obtains an original training dataset containing original historical recommendation data and original historical interaction messages, and filters the original historical interaction messages according to preset filtering rules to obtain the corresponding target historical interaction messages; the pre-created original recognition model is trained based on the target historical interaction messages and the original historical recommendation data to obtain the corresponding target recognition model, thereby improving the effectiveness and relevance of the training data input into the original recognition model, and thus improving the judgment accuracy of the target recognition model.

[0061] In one embodiment, the course recommendation method further includes: displaying the current interest value on the corresponding display interface in real time. In this embodiment, a separate component and window can be configured on the display interface to display the target user's current interest value in real time, allowing for real-time monitoring of the target user's current interest value and a more intuitive view of it.

[0062] In one embodiment, Figure 3 This is a flowchart of another course recommendation method provided by an embodiment of the present invention. This embodiment, based on the above embodiments, is a preferred embodiment used to illustrate the course recommendation process. Figure 3 As shown, the course recommendation process in this embodiment includes the following steps:

[0063] S310, Send interactive messages to the target user.

[0064] S320: Should the course be recommended to the target user? If yes, proceed to S340; otherwise, proceed to S330.

[0065] S330, No action taken.

[0066] S340. Determine the current interest value of the target user.

[0067] S350: Display the current interest value in real time on the corresponding display interface.

[0068] In this embodiment, before the live course begins, the course start time and content are sent to the target user. If the target user replies with "Okay," "No problem," or "Thank you," their current interest value is incremented by one. If they do not reply, their current interest value remains unchanged. If they reply with "No time" or "Don't bother me!", their current interest value is decremented by one. The current interest value can be calculated by the machine learning from historical recommendation data and interaction messages.

[0069] After a live course ends, relevant interactive messages from the target user (such as post-course questions, course evaluations, and post-course feelings) can be used to increment or decrement the target user's current interest value. If the target user's current interest value reaches a preset interest threshold, a corresponding target recommendation strategy can be adopted to recommend courses to the target user. This allows for targeted course recommendations to the target user and improves the user experience.

[0070] In one embodiment, Figure 4 This is a schematic diagram of the structure of a course recommendation device provided in an embodiment of the present invention. Figure 4 As shown, the device includes: a first acquisition module 410, a determination module 420, and a recommendation module 430.

[0071] The first acquisition module 410 is used to acquire actual interaction messages with the target user in real time.

[0072] The determination module 420 is used to determine the current interest value of the target user based on the actual interactive messages and the target user's user tags;

[0073] The recommendation module 430 is used to determine the corresponding target recommendation strategy based on the comparison result between the current interest value and the preset interest threshold, so as to recommend courses to the target users using the target recommendation strategy.

[0074] In one embodiment, the determining module 420 includes:

[0075] The first determining unit is used to determine the user tags of the target user based on the target user's recommendation record information;

[0076] The second determining unit is used to input the actual interaction messages and user tags into the pre-created target recognition model to obtain the current interest value of the target user.

[0077] In one embodiment, the second determining unit includes:

[0078] The first determining subunit is used to input user tags into a pre-created target recognition model to obtain a target reference system that matches the target user in the target recognition model;

[0079] The second determining subunit is used to input the actual interaction message into the pre-created target recognition model to obtain the actual vector value of the actual interaction message in the target reference frame;

[0080] The third determining subunit is used to determine the relative distance between the actual vector value and the target vector value corresponding to the benchmark interactive message in the target reference frame, which is used as the similarity between the actual interactive message and the benchmark interactive message.

[0081] The fourth determination subunit is used to determine the current interest value of the target user based on the weight value of each similarity and the corresponding actual interaction message.

[0082] In one embodiment, the course recommendation device further includes:

[0083] The second acquisition module is used to acquire the original training dataset; the original training dataset includes the original historical recommendation data and the original historical interaction messages.

[0084] The filtering module is used to filter the original historical interaction messages according to preset filtering rules to obtain the corresponding target historical interaction messages;

[0085] The training module is used to train a pre-created original recognition model based on the target's historical interaction messages and original historical recommendation data to obtain the corresponding target recognition model.

[0086] In one embodiment, the filtering module includes:

[0087] The semantic analysis unit is used to perform semantic analysis on the original historical interaction messages and filter out the corresponding dirty data.

[0088] The filtering unit is used to filter dirty data from the original historical interaction messages according to preset filtering rules to obtain the corresponding target historical interaction messages.

[0089] In one embodiment, the course recommendation device further includes:

[0090] The display module is used to display the current interest value in real time on the corresponding display interface.

[0091] In one embodiment, the user tag includes one of the following: successfully recommended user; unsuccessfully recommended user.

[0092] The course recommendation device provided in this embodiment of the invention can execute the course recommendation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0093] In one embodiment, Figure 5 This is a structural block diagram of a course recommendation electronic device provided in an embodiment of the present invention, such as... Figure 5 The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0094] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0095] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0096] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the course recommendation method.

[0097] In some embodiments, the course recommendation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the course recommendation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the course recommendation method by any other suitable means (e.g., by means of firmware).

[0098] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0099] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0100] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0101] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0102] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0103] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0104] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A course recommendation method, characterized in that, include: Real-time acquisition of actual interaction messages with target users; The current interest value of the target user is determined based on the actual interaction messages and the target user's user tags; Based on the comparison result between the current interest value and the preset interest threshold, a corresponding target recommendation strategy is determined, and the target recommendation strategy is used to recommend courses to the target user. The step of determining the current interest value of the target user based on the actual interaction messages and the target user's user tags includes: The user tag of the target user is determined based on the recommendation record information of the target user, wherein the recommendation record information refers to the record information of successfully recommending courses to the target user; The actual interaction messages and the user tags are input into a pre-created target recognition model to obtain the current interest value of the target user, including: The user tags are input into a pre-created target recognition model to obtain a target reference system that matches the target user in the target recognition model; The actual interaction message is input into a pre-created target recognition model to obtain the actual vector value of the actual interaction message in the target reference frame; The relative distance between the actual vector value and the target vector value corresponding to the benchmark interactive message in the target reference frame is determined as the similarity between the actual interactive message and the benchmark interactive message, where the benchmark interactive message is the relevant interactive message that has been successfully recommended to the user. The target user's current interest value is determined based on the weight value of each similarity and the corresponding actual interaction message.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the original training dataset; wherein, the original training dataset includes original historical recommendation data and original historical interaction messages; The original historical interaction messages are filtered according to preset filtering rules to obtain the corresponding target historical interaction messages; The pre-created original recognition model is trained based on the target's historical interaction messages and the original historical recommendation data to obtain the corresponding target recognition model.

3. The method according to claim 2, characterized in that, The step of filtering the original historical interaction messages according to preset filtering rules to obtain the corresponding target historical interaction messages includes: Semantic analysis is performed on the original historical interaction messages to filter out the corresponding dirty data; The dirty data is filtered from the original historical interaction messages according to the preset filtering rules to obtain the corresponding target historical interaction messages.

4. The method according to claim 1, characterized in that, The method further includes: The current interest value is displayed in real time on the corresponding display interface.

5. The method according to claim 1, characterized in that, The user tags include one of the following: successfully recommended users; unsuccessfully recommended users.

6. A course recommendation device, characterized in that, include: The first acquisition module is used to acquire actual interaction messages with the target user in real time; The determination module is used to determine the current interest value of the target user based on the actual interaction messages and the target user's user tags; The recommendation module is used to determine the corresponding target recommendation strategy based on the comparison result between the current interest value and the preset interest threshold, so as to recommend courses to the target user using the target recommendation strategy; The determining module includes: The first determining unit is used to determine the user tag of the target user based on the recommendation record information of the target user, wherein the recommendation record information refers to the record information of successfully recommending courses to the target user; The second determining unit is used to input the actual interaction message and the user tag into a pre-created target recognition model to obtain the current interest value of the target user; The second determining unit includes: The first determining subunit is used to input the user tag into a pre-created target recognition model to obtain a target reference system that matches the target user in the target recognition model; The second determining subunit is used to input the actual interaction message into a pre-created target recognition model to obtain the actual vector value of the actual interaction message in the target reference frame; The third determining subunit is used to determine the relative distance between the actual vector value and the target vector value corresponding to the benchmark interactive message in the target reference frame, as the similarity between the actual interactive message and the benchmark interactive message, wherein the benchmark interactive message is the relevant interactive message that has been successfully recommended to the user; The fourth determining subunit is used to determine the current interest value of the target user based on the weight value of each similarity and the corresponding actual interaction message.

7. An electronic device for recommending courses, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the course recommendation method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the course recommendation method according to any one of claims 1-5.

Images