Content recommendation method and device based on dynamic weight and cyclic sorting, terminal and medium

Abstract

The invention provides a content recommendation method and device based on dynamic weight and cyclic sorting, a terminal and a medium. The method comprises the following steps: executing a scoring operation based on a dynamic weight based on obtained interactive behavior information of each content in a current content library to obtain a current score of each content in the current content library; and in response to a content switching request of a target user terminal, recommending corresponding contents to the target user terminal according to the current scores of all the contents in the current content library based on a content cyclic sorting switching rule. Through the scoring operation based on the dynamic weight and the content cyclic sorting switching rule, new content exposure and historical high-quality content retention are balanced, and the ecological health degree of the content is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a content recommendation method, device, terminal, and medium based on dynamic weighting and cyclic sorting. Background Art

[0002] Current content recommendations generally rely on static weight allocation and user tag matching mechanisms, resulting in newly released content having difficulty breaking through the cold start bottleneck due to insufficient exposure, and historical high-quality content will be ignored by the algorithm for a long time due to time decay, thus forming a "Matthew effect" in the content ecosystem. In existing technologies, scoring models based on fixed behavioral weights lack dynamic perception of the content declaration cycle and cannot balance the needs of supporting new content and retaining historical content. For example, existing algorithms use the same weight coefficient for newly released content as for regular content, making it difficult for it to gain effective exposure in the early stages. At the same time, historical high-value content is downgraded by the system due to its long release time, resulting in a waste of resources.

[0003] In addition, the existing recommendation interaction logic generally uses a one-way descending sort when swiping up. After users browse to the highest score, they are easily trapped in a recommendation gap; pulling down to review often leads to redundant or invalid operations due to the lack of a historical record association mechanism. Summary of the Invention

[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of this application is to provide a content recommendation method, device, terminal and medium based on dynamic weighting and cyclic sorting, so as to solve at least one problem existing in the above-mentioned content recommendation method.

[0005] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a content recommendation method based on dynamic weight and circular sorting, including: based on the interactive behavior information of each content in the current content library obtained, performing a scoring operation based on dynamic weight to obtain the current score of each content in the current content library; in response to the content switching request of the target user terminal, according to the current score of all the content in the current content library, based on the content circular sorting switching rules, recommending corresponding content to the target user terminal.

[0006] In some embodiments of the first aspect of the present application, based on the obtained interaction behavior information of each content in the current content library, a dynamic weight-based scoring operation is performed to obtain the current score of each content in the current content library, including: based on the obtained interaction behavior information of each content in the current content library, according to the interaction behavior scoring rules, calculating the interaction behavior score of each content in the current content library; determining the type weight of each content in the current content library according to the type and interaction behavior information of each content in the current content library; and calculating the current score of each content in the current content library based on the interaction behavior score and type weight of each content in the current content library according to the first scoring calculation formula.

[0007] In some embodiments of the first aspect of the present application, the interactive behavior information of each content in the current content library includes: the number of likes, the number of collections, the number of follows, and the number of comments; the interactive behavior score of each content in the current content library includes: the like score, the collection score, the follow score, and the comment score; the first scoring calculation formula is: G1 = (a1+b1+c1+d1)×w; where G1 is the current score, a1 is the like score, b1 is the collection score, c1 is the follow score, d1 is the comment score, and w is the type weight.

[0008] In some embodiments of the first aspect of the present application, based on the interaction behavior information obtained for each content in the current content library, a scoring operation based on dynamic weights is performed to obtain the current score of each content in the current content library, and also includes: if the target user terminal selects a content tag, then according to the content tag selected by the target terminal, the content weight of each content in the current content library is determined; and then according to the second scoring calculation formula, based on the interaction behavior score, type weight and content weight of each content in the current content library, the current score of each content in the current content library is calculated.

[0009] In some embodiments of the first aspect of the present application, the second score calculation formula is: G2 = (a2+b2+c2+d2)×w1×w2; wherein G2 is the current score, a2 is the like score, b2 is the collection score, c2 is the attention score, d2 is the comment score, w1 is the type weight, and w2 is the content weight.

[0010] In some embodiments of the first aspect of the present application, the types of content include: newly released content, historical content, and regular content; wherein the type of each content in the current content library is determined based on a set release time threshold and a viewing volume threshold.

[0011] In some embodiments of the first aspect of the present application, the content loop sorting switching rules include: sorting all contents in the current content library in descending order according to the current scores of all contents in the current content library; determining the content in the current content library with a score higher than and closest to the current recommended content as the next recommended content, and pushing the content to the target user terminal in order from low to high scores starting from the next recommended content; after the content with the highest score is pushed, pushing the content to the target user terminal in order from low to high scores starting from the content with the lowest score.

[0012] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a content recommendation device based on dynamic weight and circular sorting, including: a data acquisition layer, used to obtain interactive behavior information of each content in the current content library; a computing engine layer, used to perform a scoring operation based on dynamic weight based on the acquired interactive behavior information of each content in the current content library, and obtain the current score of each content in the current content library; a content recommendation layer, used to respond to a content switching request of a target user terminal, and recommend corresponding content to the target user terminal based on the current score of all content in the current content library and the content circular sorting switching rules.

[0013] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the content recommendation method based on dynamic weight and cyclic sorting when executed by a processor.

[0014] To achieve the above-mentioned objectives and other related objectives, the fourth aspect of the present application provides a computer program product, which includes computer program code. When the computer program code is run on a computer, the computer implements the content recommendation method based on dynamic weight and cyclic sorting.

[0015] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the content recommendation method based on dynamic weight and cyclic sorting.

[0016] As described above, the content recommendation method, device, terminal, and medium based on dynamic weighting and cyclic sorting of the present application have the following beneficial effects:

[0017] This application balances the exposure of new content and the retention of historical high-quality content through dynamic weight-based scoring operations and content loop sorting switching rules, thereby improving the health of the content ecosystem. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Shown is a flowchart of a content recommendation method based on dynamic weighting and cyclic sorting in one embodiment of the present application.

[0019] Figure 2 Shown is a schematic block diagram of a content recommendation device based on dynamic weighting and cyclic sorting in one embodiment of the present application.

[0020] Figure 3 Shown is a structural schematic diagram of an electronic terminal in one embodiment of the present application. DETAILED DESCRIPTION

[0021] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0022] In the embodiments of this application, terms such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that terms such as "first" and "second" do not limit the quantity or order of execution, and that terms such as "first" and "second" do not necessarily define differences.

[0023] It should be noted that in the embodiments of this application, words such as "exemplary" or "for example" represent examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0024] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0025] To facilitate understanding of the embodiments of this application, first Figure 1 Detailed description. Figure 1 The following is a flow chart of a content recommendation method based on dynamic weighting and cyclic sorting in an embodiment of the present invention. The content recommendation method based on dynamic weighting and cyclic sorting in this embodiment mainly includes the following steps:

[0026] Step S11: Based on the obtained interactive behavior information of each content in the current content library, a scoring operation based on dynamic weights is performed to obtain a current score of each content in the current content library.

[0027] It should be understood that the content library refers to a systematic and structured storage space for centrally storing, managing and retrieving various types of content resources. The content can be video or text, which is not limited in this embodiment.

[0028] In one embodiment, based on the obtained interaction behavior information of each content in the current content library, a dynamic weight-based scoring operation is performed to obtain a current score for each content in the current content library, including: calculating an interaction behavior score for each content in the current content library according to an interaction behavior scoring rule based on the obtained interaction behavior information of each content in the current content library; determining a type weight for each content in the current content library according to the type and interaction behavior information of each content in the current content library; and calculating a current score for each content in the current content library according to a first scoring calculation formula based on the interaction behavior score and type weight of each content in the current content library.

[0029] If the target user terminal selects a content tag, the content weight of each content in the current content library is determined based on the content tag selected by the target terminal; then, according to the second scoring calculation formula, based on the interaction behavior score, type weight and content weight of each content in the current content library, the current score of each content in the current content library is calculated.

[0030] In one embodiment, the interactive behavior information of each content in the current content library includes: the number of likes, the number of favorites, the number of follows, and the number of comments; the interactive behavior score of each content in the current content library includes: the like score, the favorite score, the follow score, and the comment score.

[0031] In one embodiment, the first rating calculation formula is: G1 = (a1 + b1 + c1 + d1) × w; wherein G1 is the current rating, a1 is the like score, b1 is the collection score, c1 is the attention score, d1 is the comment score, and w is the type weight.

[0032] In one embodiment, the second score calculation formula is: G2 = (a2+b2+c2+d2)×w1×w2; where G2 is the current score, a2 is the like score, b2 is the collection score, c2 is the attention score, d2 is the comment score, w1 is the type weight, and w2 is the content weight.

[0033] The following describes the specific process of calculating content scores based on dynamic weighted scoring rules:

[0034] Get the number of likes, favorites, followers, and comments for each content in the current content library. Calculate the like score, favorite score, follow score, and comment score for each content based on the interactive behavior scoring rules. The interactive behavior scoring rules define the score for each like, each favorite, each follow, and each comment. The like score, favorite score, follow score, and comment score for each content constitute the interactive behavior score for each content. The like score for each content is equal to the score for each like multiplied by the number of likes for each content. The favorite score for each content is equal to the score for each favorite multiplied by the number of favorites for each content. The follow score for each content is equal to the score for each follow multiplied by the number of followers for each content. The comment score for each content is equal to the score for each comment multiplied by the number of comments for each content.

[0035] For example, the score for each like can be set to 1, the score for each favorite can be set to 1, the score for each follow can be set to 4, and the score for each comment can be set to 0. If the number of likes for a piece of content is 10, the corresponding like score is 10. It should be noted that the score for each like, each favorite, each follow, and each comment can be set as required and is not limited in this invention.

[0036] Furthermore, the type of each content in the current content library is determined based on the set release time threshold and view count threshold. Specifically, the release time threshold includes a newly released content threshold and a historical content threshold. Content with a time less than the newly released content threshold and less than the view count threshold is determined as newly released content; content with a time not less than the historical content threshold is determined as historical content. Content with a time greater than the newly released content threshold and less than the historical content threshold is determined as regular content.

[0037] For example, content with a publishing time of less than 90 days and a view count of less than 3,000 is considered newly published content; content with a publishing time of at least 180 days is considered historical content; and content with a publishing time of more than 90 days but less than 180 days is considered regular content. It should be noted that the publishing time threshold and the view count threshold can be set as needed and are not limited in this invention.

[0038] Furthermore, the type weight corresponding to each content is determined based on the type and interactive behavior information of each content. The type weights of content of the same type may be the same or different. For example, the type weights of all newly released content are set to 2 to accelerate the exposure of cold start content, the type weights of all historical content are set to 0.8 to reduce the recommendation priority of outdated content, and the type weights of all regular content are set to 1 to maintain natural sorting. If the type weights are different, the type weights of content of the same type can be set separately based on the interactive behavior information by setting the interactive behavior threshold. For example, the interactive behavior threshold can be a collection number threshold. The type weight of content with a collection number exceeding the collection number threshold among all content of the type newly released content is set to 2.5, and the type weight of content with a collection number less than the collection number threshold is set to 2. It should be understood that since the interactive behavior information of the content changes over time, the type weight of the content also changes accordingly, realizing dynamic weight. It should be noted that those skilled in the art can set the interactive behavior threshold as needed, and the present invention does not limit this.

[0039] Furthermore, it is determined whether the target user terminal has selected a content tag; if the target user terminal has not selected a user tag, the current score of each content in the content library is calculated based on the interaction behavior score and type weight of each content in the current content library according to the first score calculation formula.

[0040] The first score calculation formula refers to the following formula 1:

[0041] G1=(a1+b1+c1+d1)×w; (Formula 1)

[0042] Among them, G1 is the current score, a1 is the like score, b1 is the collection score, c1 is the follow score, d1 is the comment score, and w is the type weight.

[0043] If the target user terminal selects a content tag, the content weight of each content in the current content library is determined according to the content tag selected by the target terminal.

[0044] Furthermore, it is determined whether each content in the current content library matches the content tag selected by the target user terminal; if so, the content weight of the content is set to the matching content weight; if not, the content weight of the content is set to the non-matching content weight.

[0045] For example, the matching content weight can be set to 2, and the non-matching content weight can be set to 1. It should be noted that those skilled in the art can set the matching content weight and the non-matching content weight to other values ​​as needed, and the present invention is not limited thereto.

[0046] For another example, the content label selected by the target user terminal is technology. When a content is technology-related content, it is judged that the content matches the content label selected by the target user terminal; when a content is education-related content, it is judged that the content does not match the content label selected by the target user terminal.

[0047] Furthermore, when the target user terminal selects a content tag, the current score of each content in the current content library is calculated according to the second score calculation formula based on the interaction behavior score, type weight and content weight of each content in the current content library.

[0048] The second scoring calculation formula refers to the following formula 2:

[0049] G2=(a2+b2+c2+d2)×w1×w2; (Formula 2)

[0050] Among them, G2 is the current score, a2 is the like score, b2 is the collection score, c2 is the follow score, d2 is the comment score, w1 is the type weight, and w2 is the content weight.

[0051] It should be noted that the present invention balances the exposure of new content with the retention of historical high-quality content through a scoring rule based on dynamic weights, thereby improving the health of the content ecosystem. The content switching cycle strategy avoids excessive concentration of high-scoring content and prolongs user stay time. The replay function enhances the user's sense of control over the content flow and reduces the risk of misoperation. Parameters (such as scores, weights, and time thresholds) support dynamic adjustment to adapt to the needs of different business scenarios.

[0052] Step S12: In response to the content switching request of the target user terminal, corresponding content is recommended to the target user terminal according to the current scores of all the content in the content library and based on the content circular sorting switching rules.

[0053] In one embodiment, the types of target user terminals include but are not limited to mobile phones, computers, tablet computers, etc.

[0054] In one embodiment, the content loop sorting switching rules include: sorting all contents in the current content library in descending order according to the current scores of all contents in the current content library; determining the content in the current content library with a score higher than and closest to the current recommended content as the next recommended content, and pushing the content to the target user terminal in order from low to high scores starting from the next recommended content; after the content with the highest score is pushed, pushing the content to the target user terminal in order from low to high scores starting from the content with the lowest score.

[0055] Specifically, each time the target user terminal sends a content switching request, a content is recommended to the target user terminal; when the target user terminal sends multiple content switching requests continuously, the target user will sequentially send the same number of content as the number of requests to the target user terminal. After watching the current recommended content on the target user terminal, if a content switch is performed on the target user terminal, the content in the current content library that has a higher score than and is closest to the current recommended content will be determined as the next recommended content after the current recommended content. If continuous content switching is performed on the target user terminal, content will be pushed to the target user terminal in order of score from low to high starting from the next recommended content; after the content with the highest score is pushed, content will be pushed to the target user terminal in order of score from low to high starting from the content with the lowest score. In order to better illustrate the content loop sorting switching rules, it will be explained by way of examples:

[0056] After the target user finishes watching the currently recommended content on the target user terminal, the target user terminal switches to the content continuously. Assuming the current recommended content has a score of 45, the next recommended content will be the content with a score of at least 45 and closest to 45 (for example, a content with a score of 46). Starting with the next recommended content, the content will be pushed to the target user terminal in ascending order of score. After the highest-scoring content is pushed, the content will be pushed to the target user terminal in ascending order of score, starting with the lowest-scoring content in the current content library.

[0057] In one embodiment, in response to a playback request sent by a target user terminal, the previous content is accurately located through historical records to improve interaction continuity.

[0058] In one embodiment, when the target user terminal sends a replay request, if the current recommended content is the first recommended content received by the target user terminal, no response is given to the replay request to prevent invalid operations from interfering with the user experience.

[0059] It should be noted that the present invention integrates objective behavioral data (likes, favorites, and followers) and timeliness parameters (release time, viewing volume) in the scoring operation based on dynamic weights through type weights (such as doubling the weight of new content and attenuating the weight of historical content), thereby achieving dual optimization of cold start acceleration and retention of high-quality content. At the same time, a content loop sorting switching rule is introduced to jump according to the content score, and automatically switch to the low-scoring queue cycle after the highest-scoring content to avoid recommendation gaps; the pull-down logic accurately locates the previous content through historical playback records to improve interactive continuity. This application breaks through the existing algorithm's reliance on static weights and user tags, and adapts to multiple business scenarios with a configurable dynamic parameter system.

[0060] To better illustrate the content recommendation method of the present invention, three specific scenarios are provided:

[0061] Scenario 1: A user browses a short video platform on their terminal. Newly released content is recommended first due to its high rating.

[0062] Scenario 2: When the user swipes up continuously, the app automatically switches to content with higher ratings, and after reaching the maximum rating, it jumps to content with lower ratings and plays them in a loop.

[0063] Scenario 3: The user pulls down to return to the previous video, and the system calls the playback history to achieve seamless connection.

[0064] Figure 2 Schematic block diagram of a content recommendation device based on dynamic weight and cyclic sorting provided by an embodiment of the present application. Figure 2 As shown, the content recommendation device 2 based on dynamic weight and cyclic sorting includes:

[0065] The data collection layer 21 is used to obtain the interactive behavior information of each content in the current content library;

[0066] The calculation engine layer 22 is used to perform a dynamic weight-based scoring operation based on the obtained interaction behavior information of each content in the current content library to obtain the current score of each content in the current content library;

[0067] The content recommendation layer 23 is used to respond to a content switching request from a target user terminal and recommend corresponding content to the target user terminal according to the current scores of all content in the current content library and based on content cyclic sorting switching rules.

[0068] It should be understood that the specific process of each layer executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0069] It should also be understood that the division of layers in the embodiments of the present application is illustrative and represents only a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional layers in the various embodiments of the present application may be integrated into a single processor, exist physically as separate layers, or two or more layers may be integrated into a single layer. The aforementioned integrated layers may be implemented in either hardware or software functional modules.

[0070] In one embodiment, based on the obtained interaction behavior information of each content in the current content library, a scoring operation based on dynamic weights is performed to obtain the current score of each content in the current content library, including: based on the obtained interaction behavior information of each content in the current content library, according to the interaction behavior scoring rules, calculating the interaction behavior score of each content in the current content library; determining the type weight of each content in the current content library according to the type and interaction behavior information of each content in the current content library; and calculating the current score of each content in the current content library based on the interaction behavior score and type weight of each content in the current content library according to the first scoring calculation formula.

[0071] In one embodiment, the interactive behavior information of each content in the current content library includes: the number of likes, the number of favorites, the number of follows, and the number of comments; the interactive behavior score of each content in the current content library includes: the like score, the favorite score, the follow score, and the comment score; the first scoring calculation formula is: G1 = (a1+b1+c1+d1)×w; where G1 is the current score, a1 is the like score, b1 is the favorite score, c1 is the follow score, d1 is the comment score, and w is the type weight.

[0072] In one embodiment, based on the interaction behavior information obtained for each content in the current content library, a scoring operation based on dynamic weights is performed to obtain the current score of each content in the current content library. The process also includes: if the target user terminal selects a content tag, determining the content weight of each content in the current content library based on the content tag selected by the target terminal; and then calculating the current score of each content in the current content library based on the interaction behavior score, type weight, and content weight of each content in the current content library according to a second scoring calculation formula.

[0073] In one embodiment, the second score calculation formula is: G2 = (a2+b2+c2+d2)×w1×w2; where G2 is the current score, a2 is the like score, b2 is the collection score, c2 is the attention score, d2 is the comment score, w1 is the type weight, and w2 is the content weight.

[0074] In one embodiment, the types of content include: newly released content, historical content, and regular content; wherein the type of each content in the current content library is determined based on a set release time threshold and a viewing volume threshold.

[0075] In one embodiment, the content loop sorting switching rules include: sorting all contents in the current content library in descending order according to the current scores of all contents in the current content library; determining the content in the current content library with a score higher than and closest to the current recommended content as the next recommended content, and pushing the content to the target user terminal in order from low to high scores starting from the next recommended content; after the content with the highest score is pushed, pushing the content to the target user terminal in order from low to high scores starting from the content with the lowest score. Figure 3 : is a schematic block diagram of an electronic terminal provided in an embodiment of the present application. Figure 3 As shown, the electronic terminal includes: at least one processor 301, memory 302, at least one network interface 303 and a user interface 305. The various components in the device are coupled together through a bus system 304. It is understood that the bus system 304 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 304 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 3 Various buses are labeled as bus systems.

[0076] The user interface 305 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0077] It will be appreciated that the memory 302 may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM) or a programmable read-only memory (PROM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memory described in the embodiments of the present invention is intended to include, but is not limited to, these and any other suitable types of memory.

[0078] The memory 302 in the embodiment of the present invention is used to store various categories of data to support the operation of the electronic terminal 300. Examples of these data include: any executable program for operating on the electronic terminal 300, such as an operating system 3021 and an application 3022; the operating system 3021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 3022 can include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The content recommendation method based on dynamic weighting and circular sorting provided in the embodiment of the present invention can be included in the application 3022.

[0079] The methods disclosed in the above embodiments of the present invention can be applied to or implemented by processor 301. Processor 301 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in processor 301 or by software instructions. The above processor 301 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 301 can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor 301 can be a microprocessor or any conventional processor. The steps of the accessory optimization method provided in the embodiments of the present invention can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium located in a memory. The processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method.

[0080] In an exemplary embodiment, the electronic terminal 300 may be configured to execute the aforementioned method using one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), or complex programmable logic devices (CPLDs).

[0081] According to the method provided in the embodiment of the present application, the present application also provides a computer program product, which includes: a computer program code, which, when executed on a computer, causes the computer to execute Figure 1The content recommendation method based on dynamic weight and cyclic sorting in the illustrated embodiment.

[0082] According to the method provided in the embodiment of the present application, the present application also provides a computer-readable storage medium, which stores a program code, and when the program code is run on a computer, the computer executes Figure 1 The content recommendation method based on dynamic weight and cyclic sorting in the illustrated embodiment.

[0083] As used in this specification, the terms "component," "module," "system," and the like are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. By way of illustration, both an application running on a computing device and a computing device can be a component. One or more components can reside in a process and / or an execution thread, and a component can be located on a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures stored thereon. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component on a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).

[0084] Those skilled in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0085] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0086] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0087] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0089] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (program) are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs)).

[0090] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and other media that can store program codes.

[0091] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0092] In summary, the present application provides a content recommendation method, device, terminal and medium based on dynamic weight and circular sorting. The method includes: based on the interactive behavior information of each content in the current content library obtained, performing a scoring operation based on dynamic weight to obtain the current score of each content in the current content library; responding to the content switching request of the target user terminal, according to the current score of all the content in the current content library, based on the content circular sorting switching rules, recommending the corresponding content to the target user terminal. The present application balances the exposure of new content and the retention of historical high-quality content through the scoring operation based on dynamic weight and the content circular sorting switching rules, thereby improving the health of the content ecology. Therefore, the present application effectively overcomes the various shortcomings in the existing technology and has a high industrial utilization value.

[0093] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A content recommendation method based on dynamic weight and cyclic sorting, characterized in that: include: Based on the obtained interactive behavior information of each content in the current content library, a scoring operation based on dynamic weight is performed to obtain the current score of each content in the current content library; In response to a content switching request from a target user terminal, corresponding content is recommended to the target user terminal according to current scores of all content in the current content library and based on content cyclic sorting switching rules.

2. The content recommendation method based on dynamic weight and cyclic sorting according to claim 1, characterized in that: Based on the interaction behavior information obtained for each content in the current content library, a scoring operation based on dynamic weights is performed to obtain the current score of each content in the current content library, including: Based on the obtained interaction behavior information of each content in the current content library, according to the interaction behavior scoring rules, the interaction behavior score of each content in the current content library is calculated; Determine the type weight of each content in the current content library based on the type of each content in the current content library and the interactive behavior information; According to the first rating calculation formula, based on the interaction behavior score and type weight of each content in the current content library, the current rating of each content in the current content library is calculated.

3. The content recommendation method based on dynamic weight and cyclic sorting according to claim 2, characterized in that: The interactive behavior information of each content in the current content library includes: the number of likes, the number of collections, the number of follows, and the number of comments; the interactive behavior score of each content in the current content library includes: the like score, the collection score, the follow score, and the comment score; the first scoring calculation formula is: G1 = (a1+b1+c1+d1)×w; where G1 is the current score, a1 is the like score, b1 is the collection score, c1 is the follow score, d1 is the comment score, and w is the type weight.

4. The content recommendation method based on dynamic weight and cyclic sorting according to claim 3, characterized in that: Based on the interaction behavior information obtained for each content in the current content library, a scoring operation based on dynamic weights is performed to obtain the current score of each content in the current content library, which also includes: If the target user terminal selects a content tag, the content weight of each content in the current content library is determined based on the content tag selected by the target terminal; then, according to the second scoring calculation formula, based on the interaction behavior score, type weight and content weight of each content in the current content library, the current score of each content in the current content library is calculated.

5. The content recommendation method based on dynamic weight and cyclic sorting according to claim 4, characterized in that: The second rating calculation formula is: G2 = (a2+b2+c2+d2)×w1×w2; where G2 is the current rating, a2 is the like score, b2 is the collection score, c2 is the follow score, d2 is the comment score, w1 is the type weight, and w2 is the content weight.

6. The content recommendation method based on dynamic weight and cyclic sorting according to claim 1, characterized in that: The types of content include: newly released content, historical content, and regular content; among them, the type of each content in the current content library is determined based on the set release time threshold and viewing volume threshold.

7. The content recommendation method based on dynamic weight and cyclic sorting according to claim 1, characterized in that: The content loop sorting switching rules include: Sort all the content in the current content library in descending order according to the current rating of all the content in the current content library; The content in the current content library with a higher score than and closest to the current recommended content is determined as the next recommended content, and starting from the next recommended content, the content is pushed to the target user terminal in order of score from low to high; after the content with the highest score is pushed, starting from the content with the lowest score, the content is pushed to the target user terminal in order of score from low to high.

8. A content recommendation device based on dynamic weight and cyclic sorting, characterized in that: include: The data collection layer is used to obtain the interactive behavior information of each content in the current content library; The calculation engine layer is used to perform a dynamic weight-based scoring operation based on the interaction behavior information of each content in the current content library, and obtain the current score of each content in the current content library; The content recommendation layer is used to respond to the content switching request of the target user terminal and recommend corresponding content to the target user terminal based on the current scores of all content in the current content library and the content circular sorting switching rules.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic terminal comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the method according to any one of claims 1 to 7.

Images